Compare commits

..
Author SHA1 Message Date
Sharang ParnerkarandClaude Fable 5 463d4f6eb2 feat(werkbank): job/result contract in compliance-core (WB-01)
CI / Check (pull_request) Successful in 5m44s
CI / Detect Changes (pull_request) Has been skipped
CI / Deploy Agent (pull_request) Has been skipped
CI / Deploy Dashboard (pull_request) Has been skipped
CI / Deploy Docs (pull_request) Has been skipped
CI / Deploy MCP (pull_request) Has been skipped
The shared, dependency-free vocabulary the control plane and the Werkbank
execution runner agree on: Job (declarative — TOML on disk, JSON on the wire),
JobType (plc-provision/qemu-boot/dast/pentest), Executor (shell/docker/k8s),
JobStatus lifecycle, InputRef (blob/url — the artifact resolves on the runner,
never through the control plane), JobRuntime, JobCollect, and JobResult (reusing
Finding/DastFinding/SbomEntry so the runner produces exactly what the control
plane persists).

Lives in a mongodb/axum-feature-free module so the runner can depend on
compliance-core without the server stack (verified: cargo check -p
compliance-core --no-default-features). Tests round-trip through JSON and parse
the exact plc-provision + qemu-boot TOML from the Werkbank design doc.

First story of the Werkbank epic (sharang/werkbank#1); implements
sharang/werkbank#2.

Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>
2026-07-17 10:24:49 +02:00
sharang 7ad7bce9db feat(plc): dynamic PLC testing via ephemeral soft-PLC (#193)
CI / Check (push) Has been skipped
CI / Detect Changes (push) Successful in 3s
CI / Deploy MCP (push) Successful in 1m49s
CI / Deploy Agent (push) Successful in 3m55s
CI / Deploy Dashboard (push) Successful in 2m37s
CI / Deploy Docs (push) Has been skipped
2026-07-17 07:47:43 +00:00
sharang 1aba85b28e docs(plc): PLC Runtime Landscape reference + support watch-list (#185)
CI / Check (push) Has been skipped
CI / Detect Changes (push) Successful in 3s
CI / Deploy Agent (push) Has been skipped
CI / Deploy Dashboard (push) Has been skipped
CI / Deploy Docs (push) Successful in 49s
CI / Deploy MCP (push) Has been skipped
2026-07-16 22:05:39 +00:00
sharang c6a84b327f docs(plc): soft-PLC architecture + CODESYS/Yocto lifecycle diagram (#184)
CI / Check (push) Waiting to run
CI / Detect Changes (push) Waiting to run
CI / Deploy Agent (push) Blocked by required conditions
CI / Deploy Dashboard (push) Blocked by required conditions
CI / Deploy Docs (push) Blocked by required conditions
CI / Deploy MCP (push) Blocked by required conditions
2026-07-16 22:00:17 +00:00
sharang 0f4c75b6b3 fix(matrix): DAST needs an http(s) endpoint; don't offer/run it on modbus:// (#182)
CI / Check (push) Has been skipped
CI / Detect Changes (push) Successful in 4s
CI / Deploy Agent (push) Successful in 3m34s
CI / Deploy Dashboard (push) Successful in 2m37s
CI / Deploy Docs (push) Has been skipped
CI / Deploy MCP (push) Successful in 2m0s
2026-07-16 21:28:47 +00:00
sharang cd65fa345c feat(onboarding): enable opt-in scans from the wizard success step (#181)
CI / Check (push) Has been skipped
CI / Deploy Dashboard (push) Successful in 2m38s
CI / Deploy Docs (push) Has been skipped
CI / Deploy MCP (push) Has been skipped
CI / Detect Changes (push) Successful in 4s
CI / Deploy Agent (push) Has been skipped
2026-07-16 20:52:50 +00:00
sharang 097f86243e feat(cve): match the CODESYS runtime against NVD by CPE (#180)
CI / Detect Changes (push) Successful in 3s
CI / Check (push) Has been skipped
CI / Deploy Agent (push) Successful in 3m45s
CI / Deploy Dashboard (push) Has been skipped
CI / Deploy Docs (push) Has been skipped
CI / Deploy MCP (push) Has been skipped
2026-07-16 20:10:18 +00:00
sharang b7406eca15 feat(onboarding): Project-archive PLC format + auto-detect (#179)
CI / Check (push) Waiting to run
CI / Detect Changes (push) Waiting to run
CI / Deploy Agent (push) Blocked by required conditions
CI / Deploy Dashboard (push) Blocked by required conditions
CI / Deploy Docs (push) Blocked by required conditions
CI / Deploy MCP (push) Blocked by required conditions
2026-07-16 20:05:05 +00:00
sharang 4f9e2c2828 fix(plc): scan every PLC-source artifact, not just the first (#178)
CI / Check (push) Has been skipped
CI / Deploy Agent (push) Has been cancelled
CI / Deploy Dashboard (push) Has been cancelled
CI / Deploy Docs (push) Has been cancelled
CI / Detect Changes (push) Successful in 3s
CI / Deploy MCP (push) Has been cancelled
2026-07-16 19:59:58 +00:00
sharang 98357cae10 fix(upload): raise body-size limit to 512 MiB + surface upload errors (#177)
CI / Deploy Agent (push) Successful in 3m33s
CI / Deploy Dashboard (push) Successful in 2m39s
CI / Deploy Docs (push) Has been skipped
CI / Deploy MCP (push) Has been skipped
CI / Check (push) Has been skipped
CI / Detect Changes (push) Successful in 3s
2026-07-16 18:03:40 +00:00
sharang 55e4117369 fix(dashboard): preselect saved type/kind in edit-target form (#176)
CI / Check (push) Has been skipped
CI / Detect Changes (push) Successful in 4s
CI / Deploy Dashboard (push) Successful in 2m36s
CI / Deploy Docs (push) Has been skipped
CI / Deploy Agent (push) Has been skipped
CI / Deploy MCP (push) Has been skipped
2026-07-16 17:52:27 +00:00
sharang 7932f60ab9 feat(ics): EtherNet/IP probe + OT service-discovery port scan (#175)
CI / Check (push) Has been skipped
CI / Detect Changes (push) Successful in 3s
CI / Deploy Agent (push) Successful in 3m29s
CI / Deploy Dashboard (push) Has been skipped
CI / Deploy Docs (push) Has been skipped
CI / Deploy MCP (push) Has been skipped
2026-07-16 16:48:22 +00:00
sharang b96c4d594c feat(ics): OPC UA reachability probe (#174)
CI / Check (push) Has been skipped
CI / Detect Changes (push) Successful in 3s
CI / Deploy Agent (push) Successful in 3m27s
CI / Deploy Dashboard (push) Has been skipped
CI / Deploy Docs (push) Has been skipped
CI / Deploy MCP (push) Has been skipped
2026-07-16 16:35:54 +00:00
sharang d2003eb3c0 feat(cve): notifications for the PLC control-app SBOM (#173)
CI / Check (push) Waiting to run
CI / Detect Changes (push) Waiting to run
CI / Deploy Agent (push) Blocked by required conditions
CI / Deploy Dashboard (push) Blocked by required conditions
CI / Deploy Docs (push) Blocked by required conditions
CI / Deploy MCP (push) Blocked by required conditions
2026-07-16 16:30:19 +00:00
sharang 77eced8314 feat(ics): dynamic Modbus/TCP probe for PLC/SPS devices (#172)
CI / Check (push) Has been skipped
CI / Detect Changes (push) Successful in 5s
CI / Deploy Agent (push) Has been cancelled
CI / Deploy Dashboard (push) Has been cancelled
CI / Deploy Docs (push) Has been cancelled
CI / Deploy MCP (push) Has been cancelled
2026-07-16 16:25:04 +00:00
sharang a3f3f1d4f5 feat(plc): ingest CODESYS projects from a git repo (SAST + SBOM) (#171)
CI / Deploy Agent (push) Successful in 11m7s
CI / Check (push) Has been skipped
CI / Detect Changes (push) Successful in 3s
CI / Deploy Dashboard (push) Successful in 7m0s
CI / Deploy Docs (push) Successful in 57s
CI / Deploy MCP (push) Successful in 1m48s
2026-07-16 15:47:04 +00:00
sharang 7369e031c4 feat(plc): control-application SBOM from CODESYS .projectarchive (#170)
CI / Check (push) Has been skipped
CI / Detect Changes (push) Successful in 3s
CI / Deploy Agent (push) Successful in 3m28s
CI / Deploy Dashboard (push) Has been skipped
CI / Deploy Docs (push) Has been skipped
CI / Deploy MCP (push) Has been skipped
2026-07-16 15:28:42 +00:00
sharang 386d8457d6 feat(plc): analyse graphical logic (FBD/LD) from PLCopen XML (#169)
CI / Check (push) Has been skipped
CI / Detect Changes (push) Successful in 3s
CI / Deploy Agent (push) Successful in 5m23s
CI / Deploy Dashboard (push) Has been skipped
CI / Deploy Docs (push) Has been skipped
CI / Deploy MCP (push) Has been skipped
2026-07-16 11:43:49 +00:00
sharang 3a53a1d7f2 feat(matrix): PlcSps composite device target (SBOM/CVE/DAST/pentest) (#168)
CI / Check (push) Has been skipped
CI / Detect Changes (push) Successful in 4s
CI / Deploy MCP (push) Successful in 2m9s
CI / Deploy Agent (push) Successful in 3m51s
CI / Deploy Dashboard (push) Successful in 3m1s
CI / Deploy Docs (push) Has been skipped
2026-07-16 10:56:36 +00:00
sharang afa5c985ee feat(onboarding): PLC/blob file upload (multipart) + single-file ingest fix (#163)
CI / Deploy Agent (push) Successful in 5m39s
CI / Deploy Dashboard (push) Successful in 4m7s
CI / Deploy Docs (push) Has been skipped
CI / Deploy MCP (push) Successful in 2m38s
CI / Check (push) Has been skipped
CI / Detect Changes (push) Successful in 3s
2026-07-16 09:41:12 +00:00
sharang 6d02b138c6 feat(pipeline): PLC/SPS control-logic security scanner (IEC 61131-3) (#162)
CI / Check (push) Has been skipped
CI / Detect Changes (push) Successful in 3s
CI / Deploy Agent (push) Successful in 3m48s
CI / Deploy Dashboard (push) Successful in 2m51s
CI / Deploy Docs (push) Has been skipped
CI / Deploy MCP (push) Successful in 2m2s
2026-07-16 08:31:43 +00:00
sharang a981311413 refactor: rip out the legacy TrackedRepository / repositories path (#161)
CI / Check (push) Has been skipped
CI / Detect Changes (push) Successful in 3s
CI / Deploy Agent (push) Successful in 8m20s
CI / Deploy Dashboard (push) Successful in 3m13s
CI / Deploy Docs (push) Has been skipped
CI / Deploy MCP (push) Successful in 2m7s
2026-07-16 07:25:45 +00:00
sharang 87f240b26f feat(onboarding): input validation + editable targets (#160)
CI / Check (push) Has been skipped
CI / Detect Changes (push) Successful in 3s
CI / Deploy Agent (push) Successful in 4m6s
CI / Deploy Dashboard (push) Successful in 3m11s
CI / Deploy Docs (push) Has been skipped
CI / Deploy MCP (push) Has been skipped
2026-07-13 17:57:48 +00:00
sharang 613847d4d3 feat(agent): real nix (sandbox=false) for firmware SBOM, replacing nix-portable (#159)
CI / Deploy Agent (push) Successful in 4m7s
CI / Deploy Dashboard (push) Has been skipped
CI / Deploy Docs (push) Has been skipped
CI / Deploy MCP (push) Has been skipped
CI / Check (push) Has been skipped
CI / Detect Changes (push) Successful in 4s
2026-07-13 16:01:09 +00:00
sharang 71aceafa26 fix(deps): bump tramiton to v0.4.1 (proot-safe firmware build) (#158)
CI / Check (push) Has been skipped
CI / Detect Changes (push) Successful in 3s
CI / Deploy MCP (push) Successful in 1m44s
CI / Deploy Agent (push) Successful in 3m44s
CI / Deploy Dashboard (push) Successful in 2m34s
CI / Deploy Docs (push) Has been skipped
2026-07-13 11:21:43 +00:00
sharang b12d18d99d feat(pipeline): firmware SBOM via tramiton reproducible build (phase 2) (#157)
CI / Check (push) Has been skipped
CI / Detect Changes (push) Successful in 4s
CI / Deploy Agent (push) Successful in 4m53s
CI / Deploy Dashboard (push) Successful in 2m37s
CI / Deploy Docs (push) Has been skipped
CI / Deploy MCP (push) Successful in 1m45s
2026-07-13 10:15:06 +00:00
sharang eaaafc0621 feat(pipeline): analysis-based firmware SBOM from tramiton (#156)
CI / Check (push) Has been skipped
CI / Detect Changes (push) Successful in 3s
CI / Deploy Agent (push) Successful in 5m3s
CI / Deploy Dashboard (push) Successful in 3m46s
CI / Deploy Docs (push) Has been skipped
CI / Deploy MCP (push) Successful in 2m14s
2026-07-13 08:31:33 +00:00
sharang 0ec5fd8295 fix(dashboard): Findings/SBOM filter by targets + accurate target findings_count (#155)
CI / Deploy Agent (push) Successful in 5m7s
CI / Deploy Dashboard (push) Successful in 2m57s
CI / Deploy Docs (push) Has been skipped
CI / Deploy MCP (push) Has been skipped
CI / Check (push) Has been skipped
CI / Detect Changes (push) Successful in 3s
2026-07-13 07:59:45 +00:00
sharang bf32b9939a fix(onboarding): targets visibility + unified pipeline by default (#154)
CI / Detect Changes (push) Successful in 3s
CI / Check (push) Has been skipped
CI / Deploy Agent (push) Successful in 3m41s
CI / Deploy Dashboard (push) Successful in 2m46s
CI / Deploy Docs (push) Has been skipped
CI / Deploy MCP (push) Successful in 1m46s
2026-07-13 07:29:04 +00:00
sharang 669e1f1b03 feat(onboarding): scan-trigger endpoint + wizard Run-Scan button (#153)
CI / Check (push) Has been skipped
CI / Detect Changes (push) Successful in 4s
CI / Deploy Agent (push) Successful in 3m34s
CI / Deploy Dashboard (push) Successful in 2m56s
CI / Deploy Docs (push) Has been skipped
CI / Deploy MCP (push) Has been skipped
2026-07-12 22:19:32 +00:00
sharang 9e70bd1c8e ci: don't cancel-in-progress for main-branch runs (only pull_request) (#152)
CI / Detect Changes (push) Successful in 3s
CI / Check (push) Has been skipped
CI / Deploy Agent (push) Has been skipped
CI / Deploy Dashboard (push) Has been skipped
CI / Deploy Docs (push) Has been skipped
CI / Deploy MCP (push) Has been skipped
2026-07-12 22:08:58 +00:00
sharang 9ec07ff7a1 fix(ci): authenticate tramiton fetch in dashboard + mcp image builds (#147)
CI / Check (push) Has been skipped
CI / Detect Changes (push) Successful in 3s
CI / Deploy Agent (push) Has been skipped
CI / Deploy MCP (push) Successful in 1m47s
CI / Deploy Dashboard (push) Successful in 2m37s
CI / Deploy Docs (push) Has been skipped
2026-07-12 21:52:38 +00:00
sharang 0e57c2d7a7 feat(pipeline): run tramiton classification + provision DAST in run_target (#146)
CI / Deploy Agent (push) Successful in 3m40s
CI / Deploy Dashboard (push) Has been skipped
CI / Deploy Docs (push) Has been skipped
CI / Check (push) Has been skipped
CI / Detect Changes (push) Successful in 3s
CI / Deploy MCP (push) Has been skipped
2026-07-12 21:49:22 +00:00
sharang c6a02f0ac3 feat(pipeline): unified run_target execution behind UNIFIED_PIPELINE (#145)
CI / Check (push) Has been skipped
CI / Detect Changes (push) Successful in 3s
CI / Deploy Agent (push) Successful in 3m47s
CI / Deploy Dashboard (push) Failing after 4m28s
CI / Deploy Docs (push) Has been skipped
CI / Deploy MCP (push) Failing after 5s
2026-07-12 21:31:21 +00:00
sharang 17f788858d feat(dashboard): onboarding wizard UI (#144)
CI / Detect Changes (push) Successful in 3s
CI / Check (push) Has been skipped
CI / Deploy Docs (push) Has been cancelled
CI / Deploy MCP (push) Has been cancelled
CI / Deploy Dashboard (push) Has been cancelled
CI / Deploy Agent (push) Has been skipped
2026-07-12 21:28:52 +00:00
sharangandSharang Parnerkar c6b5622113 fix(ci): authenticate tramiton-core fetch in the agent image build (main deploys) (#143)
CI / Check (push) Has been skipped
CI / Detect Changes (push) Successful in 5s
CI / Deploy Agent (push) Successful in 7m46s
CI / Deploy Dashboard (push) Has been skipped
CI / Deploy Docs (push) Has been skipped
CI / Deploy MCP (push) Has been skipped
The PR `check` job authenticates the private tramiton-core git fetch, but the main-branch **`deploy-agent`** job builds `Dockerfile.agent` where cargo also fetches tramiton-core — inside the image build, with no credentials — so **agent image builds on main fail**.

Fix: inject the PAT as a **BuildKit secret** (never baked into an image layer).
- `Dockerfile.agent`: `RUN --mount=type=secret,id=tramiton_token …` applies the same `https`-insteadOf rewrite + `CARGO_NET_GIT_FETCH_WITH_CLI=true` before `cargo build`.
- `deploy-agent`: `DOCKER_BUILDKIT=1 docker build --secret id=tramiton_token,env=TRAMITON_FETCH_TOKEN …`, reusing the existing `TRAMITON_FETCH_TOKEN` secret.

Only the agent image depends on tramiton-core (dashboard/mcp/docs unaffected). **Self-tests on merge** — changing `Dockerfile.agent` makes `detect-changes` run `deploy-agent`.

Note: couldn't fully run the image build locally (no PAT value on hand + no `.dockerignore` so the context is large), but this mirrors the working PR-stage auth and uses standard BuildKit secret injection. Assumes the deploy runner's Docker daemon supports BuildKit (docker:27-cli → yes).
---------

Co-authored-by: Sharang Parnerkar <30073382+mighty840@users.noreply.github.com>
Reviewed-on: #143
2026-07-12 20:25:39 +00:00
sharang a204f0c59c feat(api): onboarding endpoints for unified targets (#142)
CI / Check (push) Has been skipped
CI / Detect Changes (push) Successful in 3s
CI / Deploy Agent (push) Failing after 5s
CI / Deploy Dashboard (push) Has been skipped
CI / Deploy Docs (push) Has been skipped
CI / Deploy MCP (push) Has been skipped
2026-07-12 20:15:22 +00:00
sharang cf4afdda1b feat(migrate): onboarding backfill (repositories + dast_targets -> onboarded_targets) (#141)
CI / Check (push) Has been skipped
CI / Detect Changes (push) Successful in 3s
CI / Deploy Agent (push) Failing after 5s
CI / Deploy Dashboard (push) Has been skipped
CI / Deploy Docs (push) Has been skipped
CI / Deploy MCP (push) Has been skipped
2026-07-12 20:11:16 +00:00
sharang a074efd0b4 ci: Kellnr crates.io mirror + persistent S3-backed sccache (#140)
CI / Check (push) Has been skipped
CI / Detect Changes (push) Successful in 3s
CI / Deploy Agent (push) Has been skipped
CI / Deploy Dashboard (push) Has been skipped
CI / Deploy Docs (push) Has been skipped
CI / Deploy MCP (push) Has been skipped
2026-07-10 16:30:51 +00:00
sharang ef6ee3dcd1 feat(onboarding): artifact ingest + classifier + native tramiton + suite seams (#138)
CI / Check (push) Has been skipped
CI / Detect Changes (push) Successful in 3s
CI / Deploy Agent (push) Failing after 5s
CI / Deploy Dashboard (push) Failing after 5s
CI / Deploy Docs (push) Has been skipped
CI / Deploy MCP (push) Failing after 4s
2026-07-10 16:00:51 +00:00
sharang 675c4ef699 feat(onboarding): unified multi-target model + scan matrix foundation (#134)
CI / Check (push) Has been skipped
CI / Detect Changes (push) Successful in 5s
CI / Deploy Agent (push) Successful in 7m36s
CI / Deploy Dashboard (push) Successful in 7m9s
CI / Deploy Docs (push) Has been skipped
CI / Deploy MCP (push) Successful in 1m44s
2026-07-10 13:41:25 +00:00
sharang aed551231c feat(dashboard): UI for managing MCP tokens (#94)
CI / Check (push) Has been skipped
CI / Detect Changes (push) Successful in 4s
CI / Deploy Agent (push) Has been skipped
CI / Deploy Dashboard (push) Successful in 3m3s
CI / Deploy Docs (push) Has been skipped
CI / Deploy MCP (push) Has been skipped
Adds /mcp-tokens page so a logged-in user can mint, list, and revoke bearer tokens for the MCP server without curl. Pairs with #92's tenant-scoped MCP middleware — copy a token from the dashboard straight into an LLM client config.
2026-06-30 16:32:54 +00:00
sharang b851f4267a feat(m7.3): scheduler pulls tenants from registry, env as fallback (#96)
CI / Check (push) Has been skipped
CI / Detect Changes (push) Successful in 3s
CI / Deploy Dashboard (push) Has been cancelled
CI / Deploy Docs (push) Has been cancelled
CI / Deploy MCP (push) Has been cancelled
CI / Deploy Agent (push) Has been cancelled
Replaces M7.2-C static SCHEDULER_TENANT_IDS with a live query to the tenant-registry at every tick. New tenants picked up without an agent restart; env stays as fallback so a registry outage never silences the scheduler. Resolution order: registry -> SCHEDULER_TENANT_IDS env -> DEFAULT_SCHEDULER_TENANT_ID. Logs the active source on startup.
2026-06-30 16:32:35 +00:00
sharang e9536b6d98 fix(audit): bump quinn-proto + ignore rmcp DNS-rebinding advisory (#97)
CI / Check (push) Has been skipped
CI / Detect Changes (push) Successful in 3s
CI / Deploy Agent (push) Successful in 3m55s
CI / Deploy Dashboard (push) Successful in 2m44s
CI / Deploy Docs (push) Has been skipped
CI / Deploy MCP (push) Successful in 1m50s
RUSTSEC-2026-0185 (quinn-proto 0.11.14): patch-bump to 0.11.15. RUSTSEC-2026-0189 (rmcp 0.16 DNS rebinding): added to ignore with public-hostname + bearer-auth threat-model justification; rmcp 0.16->2.x migration tracked as a separate multi-hour PR.
2026-06-30 16:07:01 +00:00
sharang a3a96fe2cc feat(m7.3): MCP tenant-scoped bearer tokens (#92)
CI / Check (push) Has been skipped
CI / Detect Changes (push) Successful in 5s
CI / Deploy Agent (push) Successful in 8m13s
CI / Deploy Dashboard (push) Successful in 7m3s
CI / Deploy Docs (push) Has been skipped
CI / Deploy MCP (push) Successful in 1m50s
MCP server validates per-tenant bearer tokens on incoming calls and routes each tool to the caller's tenant DB. Closes the cross-tenant data leak in the MCP path identified in M7.3.
2026-06-30 15:27:21 +00:00
sharang ac24ca766a feat(m7.3): cross-tenant admin HTTP endpoints (#95)
CI / Check (push) Has been skipped
CI / Detect Changes (push) Successful in 4s
CI / Deploy Dashboard (push) Has been cancelled
CI / Deploy Docs (push) Has been cancelled
CI / Deploy MCP (push) Has been cancelled
CI / Deploy Agent (push) Has been cancelled
GET /api/admin/tenants lists tenant DBs; DELETE /api/admin/tenants/{tenant_id} drops them (GDPR). Behind a separate auth path that rejects customer realm tokens.
2026-06-30 15:23:39 +00:00
sharang 485c3ff45e chore(agent): remove stale unscoped webhook routes from API router (#93)
CI / Check (push) Has been skipped
CI / Detect Changes (push) Successful in 4s
CI / Deploy Dashboard (push) Has been cancelled
CI / Deploy Docs (push) Has been cancelled
CI / Deploy MCP (push) Has been cancelled
CI / Deploy Agent (push) Has been cancelled
Webhook routes live on the separate webhook server (port 3002). M7.2-C URL form is /webhook/{tenant_id}/{platform}/{repo_id}; mounting unscoped variants on the API router would mismatch handler signatures.
2026-06-30 15:18:31 +00:00
112 changed files with 14083 additions and 1820 deletions
+13
View File
@@ -7,4 +7,17 @@ ignore = [
# not a realistic attack surface here. Revisit when mongodb bumps hickory.
"RUSTSEC-2026-0118", # NSEC3 loop, no fix available upstream
"RUSTSEC-2026-0119", # O(n²) name compression, fixed in hickory-proto >=0.26.1
# rmcp 0.16.0 — DNS rebinding in Streamable HTTP server transport (missing
# Host header validation). Patched in rmcp >= 1.4.0, which is a major API
# version jump from our pin; rmcp shipped 0.x → 1.x → 2.x in three months
# and the migration touches every tool handler + the auth middleware we
# just landed in #92. Threat model in our deployment: the MCP server is
# exposed at a public hostname (comp-mcp-dev.meghsakha.com) behind orca's
# TLS-terminating ingress with per-tenant bearer auth — the attack model
# (browser DNS-rebinding into localhost MCP server) doesn't directly apply.
# Defense-in-depth Host-header check is still a worthwhile follow-up.
# FOLLOW-UP: bump rmcp to 2.x in a dedicated PR (M7.3 follow-up, sized
# multi-hour due to API surface change).
"RUSTSEC-2026-0189",
]
+13
View File
@@ -34,6 +34,19 @@ SCAN_SCHEDULE=0 0 */6 * * *
CVE_MONITOR_SCHEDULE=0 0 0 * * *
GIT_CLONE_BASE_PATH=/tmp/compliance-scanner/repos
# Dynamic PLC testing — ephemeral soft-PLC provisioning (#183). Off unless
# enabled; requires the agent container to have Docker access (socket mount).
# When on, a PLC/SPS target with control logic but no reachable device gets its
# logic instantiated on a throwaway OpenPLC, probed, then torn down.
PLC_RUNTIME_ENABLED=0
PLC_RUNTIME_IMAGE=registry.meghsakha.com/openplc:latest
PLC_RUNTIME_NETWORK=certifai
PLC_RUNTIME_MEMORY=512m
PLC_RUNTIME_CPUS=0.5
PLC_RUNTIME_MAX_LIFETIME_SECS=180
PLC_RUNTIME_OPENPLC_USER=openplc
PLC_RUNTIME_OPENPLC_PASSWORD=openplc
# Dashboard
DASHBOARD_PORT=8080
AGENT_API_URL=http://localhost:3001
+67 -10
View File
@@ -9,15 +9,33 @@ on:
env:
CARGO_TERM_COLOR: always
RUSTFLAGS: "-D warnings"
# sccache caches compilation artifacts within a job so that compiling
# both --features server and --features web shares common crate work.
# Compile cache: sccache -> Hetzner S3 (breakpilot-sccache), runner-independent
# and persistent across CI runs (own key prefix). Reuses the shared cluster S3
# creds (same bucket as werkpilot). Requires repo secrets HETZNER_S3_ACCESS_KEY
# and HETZNER_S3_SECRET_KEY.
RUSTC_WRAPPER: /usr/local/bin/sccache
SCCACHE_DIR: /tmp/sccache
SCCACHE_BUCKET: breakpilot-sccache
SCCACHE_ENDPOINT: https://nbg1.your-objectstorage.com
SCCACHE_REGION: auto
SCCACHE_S3_USE_SSL: "true"
SCCACHE_S3_KEY_PREFIX: compliance-scanner
AWS_ACCESS_KEY_ID: ${{ secrets.HETZNER_S3_ACCESS_KEY }}
AWS_SECRET_ACCESS_KEY: ${{ secrets.HETZNER_S3_SECRET_KEY }}
# compliance-agent depends on tramiton-core via git; use the system git so the
# credential rewrite below (see "Configure git auth ...") is honored on fetch.
CARGO_NET_GIT_FETCH_WITH_CLI: "true"
# Throttle cargo so a ~670-crate concurrent download burst doesn't 429 the
# Kellnr mirror: fewer concurrent connections (HTTP/1.1) + more retries.
CARGO_NET_RETRY: "10"
CARGO_HTTP_MULTIPLEXING: "false"
# Cancel in-progress runs for the same branch/PR
# Cancel superseded PR runs, but NEVER cancel main-branch runs — those build and
# deploy per-service images, and cancelling one merge's deploy when the next
# merge lands leaves a service un-deployed (as happened between two back-to-back
# merges). So cancel-in-progress only for pull_request events.
concurrency:
group: ${{ github.workflow }}-${{ github.ref }}
cancel-in-progress: true
cancel-in-progress: ${{ github.event_name == 'pull_request' }}
jobs:
# ---------------------------------------------------------------------------
@@ -36,16 +54,44 @@ jobs:
git remote add origin "${GITHUB_SERVER_URL}/${GITHUB_REPOSITORY}.git"
git fetch --depth=1 origin "${GITHUB_SHA}"
git checkout FETCH_HEAD
# Resolve crates.io deps through the self-hosted Kellnr mirror (cached,
# crates.io-independent). Git deps (tramiton-core) are unaffected — source
# replacement only applies to crates.io-sourced crates.
- name: Use Kellnr crates.io mirror
run: |
: "${CARGO_HOME:=/usr/local/cargo}"
mkdir -p "$CARGO_HOME"
{
echo '[source.crates-io]'
echo 'replace-with = "kellnr"'
echo '[registries.kellnr]'
echo 'index = "sparse+https://crates.meghsakha.com/api/v1/cratesio/"'
} >> "$CARGO_HOME/config.toml"
env:
RUSTC_WRAPPER: ""
- name: Install tools
run: |
rustup component add rustfmt clippy
curl -fsSL https://github.com/mozilla/sccache/releases/download/v0.9.1/sccache-v0.9.1-x86_64-unknown-linux-musl.tar.gz \
| tar xz --strip-components=1 -C /usr/local/bin/ sccache-v0.9.1-x86_64-unknown-linux-musl/sccache
curl -fsSL https://github.com/mozilla/sccache/releases/download/v0.10.0/sccache-v0.10.0-x86_64-unknown-linux-musl.tar.gz \
| tar xz --strip-components=1 -C /usr/local/bin/ sccache-v0.10.0-x86_64-unknown-linux-musl/sccache
chmod +x /usr/local/bin/sccache
cargo install cargo-audit --locked
env:
RUSTC_WRAPPER: ""
# compliance-agent has a git dependency on tramiton-core (a private repo on
# this Gitea instance). Rewrite its SSH URL to HTTPS + a PAT so the runner
# can fetch it. Requires the repo secret TRAMITON_FETCH_TOKEN (a Gitea PAT
# with read:repository, owned by a user with access to sharang/tramiton).
# (Honored on fetch because CARGO_NET_GIT_FETCH_WITH_CLI=true uses system git.)
- name: Configure git auth for private tramiton dependency
run: |
git config --global \
url."https://sharang:${{ secrets.TRAMITON_FETCH_TOKEN }}@gitea.meghsakha.com/".insteadOf \
"ssh://git@gitea.meghsakha.com:22222/"
env:
RUSTC_WRAPPER: ""
# Format (no compilation needed)
- name: Format
run: cargo fmt --all --check
@@ -148,13 +194,18 @@ jobs:
image: docker:27-cli
steps:
- name: Build, push and trigger orca redeploy
env:
# PAT for fetching the private tramiton-core git dependency during the
# image build (injected as a BuildKit secret, never baked into a layer).
TRAMITON_FETCH_TOKEN: ${{ secrets.TRAMITON_FETCH_TOKEN }}
run: |
apk add --no-cache git curl openssl
git init && git remote add origin "${GITHUB_SERVER_URL}/${GITHUB_REPOSITORY}.git"
git fetch --depth=1 origin "${GITHUB_SHA}" && git checkout FETCH_HEAD
IMAGE=registry.meghsakha.com/compliance-agent
echo "${{ secrets.REGISTRY_PASSWORD }}" | docker login registry.meghsakha.com -u "${{ secrets.REGISTRY_USERNAME }}" --password-stdin
docker build -f Dockerfile.agent -t "$IMAGE:latest" -t "$IMAGE:${GITHUB_SHA}" .
DOCKER_BUILDKIT=1 docker build --secret id=tramiton_token,env=TRAMITON_FETCH_TOKEN \
-f Dockerfile.agent -t "$IMAGE:latest" -t "$IMAGE:${GITHUB_SHA}" .
docker push "$IMAGE:latest" && docker push "$IMAGE:${GITHUB_SHA}"
PAYLOAD=$(printf '{"ref":"refs/heads/main","repository":{"full_name":"sharang/compliance-scanner-agent"},"head_commit":{"id":"%s","message":"deploy agent"}}' "${GITHUB_SHA}")
SIG=$(printf '%s' "$PAYLOAD" | openssl dgst -sha256 -hmac "${{ secrets.ORCA_WEBHOOK_SECRET }}" | awk '{print $2}')
@@ -169,13 +220,16 @@ jobs:
image: docker:27-cli
steps:
- name: Build, push and trigger orca redeploy
env:
TRAMITON_FETCH_TOKEN: ${{ secrets.TRAMITON_FETCH_TOKEN }}
run: |
apk add --no-cache git curl openssl
git init && git remote add origin "${GITHUB_SERVER_URL}/${GITHUB_REPOSITORY}.git"
git fetch --depth=1 origin "${GITHUB_SHA}" && git checkout FETCH_HEAD
IMAGE=registry.meghsakha.com/compliance-dashboard
echo "${{ secrets.REGISTRY_PASSWORD }}" | docker login registry.meghsakha.com -u "${{ secrets.REGISTRY_USERNAME }}" --password-stdin
docker build -f Dockerfile.dashboard -t "$IMAGE:latest" -t "$IMAGE:${GITHUB_SHA}" .
DOCKER_BUILDKIT=1 docker build --secret id=tramiton_token,env=TRAMITON_FETCH_TOKEN \
-f Dockerfile.dashboard -t "$IMAGE:latest" -t "$IMAGE:${GITHUB_SHA}" .
docker push "$IMAGE:latest" && docker push "$IMAGE:${GITHUB_SHA}"
PAYLOAD=$(printf '{"ref":"refs/heads/main","repository":{"full_name":"sharang/compliance-scanner-agent"},"head_commit":{"id":"%s","message":"deploy dashboard"}}' "${GITHUB_SHA}")
SIG=$(printf '%s' "$PAYLOAD" | openssl dgst -sha256 -hmac "${{ secrets.ORCA_WEBHOOK_SECRET }}" | awk '{print $2}')
@@ -211,13 +265,16 @@ jobs:
image: docker:27-cli
steps:
- name: Build, push and trigger orca redeploy
env:
TRAMITON_FETCH_TOKEN: ${{ secrets.TRAMITON_FETCH_TOKEN }}
run: |
apk add --no-cache git curl openssl
git init && git remote add origin "${GITHUB_SERVER_URL}/${GITHUB_REPOSITORY}.git"
git fetch --depth=1 origin "${GITHUB_SHA}" && git checkout FETCH_HEAD
IMAGE=registry.meghsakha.com/compliance-mcp
echo "${{ secrets.REGISTRY_PASSWORD }}" | docker login registry.meghsakha.com -u "${{ secrets.REGISTRY_USERNAME }}" --password-stdin
docker build -f Dockerfile.mcp -t "$IMAGE:latest" -t "$IMAGE:${GITHUB_SHA}" .
DOCKER_BUILDKIT=1 docker build --secret id=tramiton_token,env=TRAMITON_FETCH_TOKEN \
-f Dockerfile.mcp -t "$IMAGE:latest" -t "$IMAGE:${GITHUB_SHA}" .
docker push "$IMAGE:latest" && docker push "$IMAGE:${GITHUB_SHA}"
PAYLOAD=$(printf '{"ref":"refs/heads/main","repository":{"full_name":"sharang/compliance-scanner-agent"},"head_commit":{"id":"%s","message":"deploy mcp"}}' "${GITHUB_SHA}")
SIG=$(printf '%s' "$PAYLOAD" | openssl dgst -sha256 -hmac "${{ secrets.ORCA_WEBHOOK_SECRET }}" | awk '{print $2}')
Generated
+121 -7
View File
@@ -676,8 +676,10 @@ dependencies = [
"jsonwebtoken",
"mongodb",
"octocrab",
"rand 0.9.2",
"regex",
"reqwest",
"roxmltree",
"secrecy",
"serde",
"serde_json",
@@ -691,6 +693,9 @@ dependencies = [
"tower-http",
"tracing",
"tracing-subscriber",
"tramiton-core",
"tramiton-repro",
"tramiton-sbom",
"urlencoding",
"uuid",
"walkdir",
@@ -718,6 +723,7 @@ dependencies = [
"sha2",
"thiserror 2.0.18",
"tokio",
"toml",
"tracing",
"tracing-opentelemetry",
"tracing-subscriber",
@@ -818,12 +824,15 @@ dependencies = [
"bson",
"chrono",
"compliance-core",
"dashmap",
"dotenvy",
"hex",
"mongodb",
"rmcp",
"schemars 1.2.1",
"serde",
"serde_json",
"sha2",
"thiserror 2.0.18",
"tokio",
"tower-http",
@@ -1114,9 +1123,9 @@ dependencies = [
[[package]]
name = "crossbeam-epoch"
version = "0.9.18"
version = "0.9.20"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "5b82ac4a3c2ca9c3460964f020e1402edd5753411d7737aa39c3714ad1b5420e"
checksum = "2d6914041f254d6e9176c01941b21115dcfb7089e55135a35411081bd106ef3f"
dependencies = [
"crossbeam-utils",
]
@@ -3762,6 +3771,15 @@ dependencies = [
"syn",
]
[[package]]
name = "object"
version = "0.36.7"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "62948e14d923ea95ea2c7c86c71013138b66525b86bdc08d2dcc262bdb497b87"
dependencies = [
"memchr",
]
[[package]]
name = "octocrab"
version = "0.44.1"
@@ -4193,7 +4211,7 @@ version = "3.4.0"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "219cb19e96be00ab2e37d6e299658a0cfa83e52429179969b0f0121b4ac46983"
dependencies = [
"toml_edit",
"toml_edit 0.23.10+spec-1.0.0",
]
[[package]]
@@ -4278,9 +4296,9 @@ dependencies = [
[[package]]
name = "quinn-proto"
version = "0.11.14"
version = "0.11.15"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "434b42fec591c96ef50e21e886936e66d3cc3f737104fdb9b737c40ffb94c098"
checksum = "4fcb935c5bec503c2f0e306bdd3e58bb9029dcb14fa8d9ac76e3a5256ac0763e"
dependencies = [
"bytes",
"getrandom 0.3.4",
@@ -4612,6 +4630,12 @@ dependencies = [
"syn",
]
[[package]]
name = "roxmltree"
version = "0.20.0"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "6c20b6793b5c2fa6553b250154b78d6d0db37e72700ae35fad9387a46f487c97"
[[package]]
name = "rust-stemmers"
version = "1.2.0"
@@ -4992,6 +5016,15 @@ dependencies = [
"syn",
]
[[package]]
name = "serde_spanned"
version = "0.6.9"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "bf41e0cfaf7226dca15e8197172c295a782857fcb97fad1808a166870dee75a3"
dependencies = [
"serde",
]
[[package]]
name = "serde_urlencoded"
version = "0.7.1"
@@ -5190,7 +5223,7 @@ version = "0.8.9"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "c1c97747dbf44bb1ca44a561ece23508e99cb592e862f22222dcf42f51d1e451"
dependencies = [
"heck 0.4.1",
"heck 0.5.0",
"proc-macro2",
"quote",
"syn",
@@ -5806,6 +5839,27 @@ dependencies = [
"tokio",
]
[[package]]
name = "toml"
version = "0.8.23"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "dc1beb996b9d83529a9e75c17a1686767d148d70663143c7854d8b4a09ced362"
dependencies = [
"serde",
"serde_spanned",
"toml_datetime 0.6.11",
"toml_edit 0.22.27",
]
[[package]]
name = "toml_datetime"
version = "0.6.11"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "22cddaf88f4fbc13c51aebbf5f8eceb5c7c5a9da2ac40a13519eb5b0a0e8f11c"
dependencies = [
"serde",
]
[[package]]
name = "toml_datetime"
version = "0.7.5+spec-1.1.0"
@@ -5815,6 +5869,20 @@ dependencies = [
"serde_core",
]
[[package]]
name = "toml_edit"
version = "0.22.27"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "41fe8c660ae4257887cf66394862d21dbca4a6ddd26f04a3560410406a2f819a"
dependencies = [
"indexmap 2.13.0",
"serde",
"serde_spanned",
"toml_datetime 0.6.11",
"toml_write",
"winnow",
]
[[package]]
name = "toml_edit"
version = "0.23.10+spec-1.0.0"
@@ -5822,7 +5890,7 @@ source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "84c8b9f757e028cee9fa244aea147aab2a9ec09d5325a9b01e0a49730c2b5269"
dependencies = [
"indexmap 2.13.0",
"toml_datetime",
"toml_datetime 0.7.5+spec-1.1.0",
"toml_parser",
"winnow",
]
@@ -5836,6 +5904,12 @@ dependencies = [
"winnow",
]
[[package]]
name = "toml_write"
version = "0.1.2"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "5d99f8c9a7727884afe522e9bd5edbfc91a3312b36a77b5fb8926e4c31a41801"
[[package]]
name = "tonic"
version = "0.12.3"
@@ -6082,6 +6156,46 @@ dependencies = [
"wasm-bindgen",
]
[[package]]
name = "tramiton-core"
version = "0.4.1"
source = "git+ssh://git@gitea.meghsakha.com:22222/sharang/tramiton.git?tag=v0.4.1#ae4fc1376279f9edb9882605b20877335e7ba8ba"
dependencies = [
"serde",
"tempfile",
"thiserror 1.0.69",
"toml",
"walkdir",
]
[[package]]
name = "tramiton-repro"
version = "0.4.1"
source = "git+ssh://git@gitea.meghsakha.com:22222/sharang/tramiton.git?tag=v0.4.1#ae4fc1376279f9edb9882605b20877335e7ba8ba"
dependencies = [
"serde",
"serde_json",
"sha2",
"tempfile",
"thiserror 1.0.69",
"toml",
"tramiton-core",
"walkdir",
]
[[package]]
name = "tramiton-sbom"
version = "0.4.1"
source = "git+ssh://git@gitea.meghsakha.com:22222/sharang/tramiton.git?tag=v0.4.1#ae4fc1376279f9edb9882605b20877335e7ba8ba"
dependencies = [
"object",
"serde",
"serde_json",
"sha2",
"tramiton-core",
"tramiton-repro",
]
[[package]]
name = "tree-sitter"
version = "0.24.7"
+3 -1
View File
@@ -23,7 +23,7 @@ tracing = "0.1"
tracing-subscriber = { version = "0.3", features = ["env-filter"] }
chrono = { version = "0.4", features = ["serde"] }
mongodb = { version = "3", features = ["rustls-tls", "compat-3-0-0"] }
reqwest = { version = "0.12", features = ["json", "rustls-tls"], default-features = false }
reqwest = { version = "0.12", features = ["json", "rustls-tls", "multipart", "cookies"], default-features = false }
thiserror = "2"
sha2 = "0.10"
hex = "0.4"
@@ -34,3 +34,5 @@ zip = { version = "2", features = ["aes-crypto", "deflate"] }
dashmap = "6"
tokio-stream = { version = "0.1", features = ["sync"] }
aes-gcm = "0.10"
rand = "0.9"
base64 = "0.22"
+41 -2
View File
@@ -2,7 +2,22 @@ FROM rust:1.94-bookworm AS builder
WORKDIR /app
COPY . .
RUN cargo build --release -p compliance-agent
# compliance-agent depends on the private tramiton-core git repo. Authenticate
# the fetch with a PAT passed as a BuildKit secret (never baked into a layer).
# Build with: DOCKER_BUILDKIT=1 docker build --secret id=tramiton_token,env=TRAMITON_FETCH_TOKEN ...
RUN --mount=type=secret,id=tramiton_token \
if [ -s /run/secrets/tramiton_token ]; then \
git config --global \
url."https://sharang:$(cat /run/secrets/tramiton_token)@gitea.meghsakha.com/".insteadOf \
"ssh://git@gitea.meghsakha.com:22222/"; \
fi && \
CARGO_NET_GIT_FETCH_WITH_CLI=true cargo build --release -p compliance-agent
# A throwaway stage that packs a real nix store (store paths + the validity DB)
# into a compressed bootstrap tarball. Only the tarball is copied into the final
# image, so we don't carry a raw /nix copy layer.
FROM nixos/nix:latest AS nixseed
RUN tar -C / -czf /nix-bootstrap.tar.gz nix
FROM debian:bookworm-slim
RUN apt-get update && apt-get install -y ca-certificates libssl3 git curl python3 python3-pip npm golang-go php-cli && rm -rf /var/lib/apt/lists/*
@@ -31,7 +46,30 @@ RUN pip3 install --break-system-packages semgrep
# Install ruff for Python linting
RUN pip3 install --break-system-packages ruff
# Real nix for the tramiton reproducible-build firmware SBOM.
#
# nix-portable's proot fallback can't run here: user namespaces are blocked by
# the container's default seccomp/apparmor profile, and orca exposes no way to
# relax it. So ship a *real* nix and disable its build sandbox
# (`sandbox = false`) — a plain gcc/make firmware build needs no user namespace,
# so it runs fine under the locked-down profile with no proot involved.
#
# The store is shipped as a bootstrap tarball and seeded onto /nix at first
# start (see docker/agent-entrypoint.sh), so a persistent /nix volume survives
# redeploys. A missing/broken nix just falls back to the analysis-only SBOM.
COPY --from=nixseed /nix-bootstrap.tar.gz /opt/nix-bootstrap.tar.gz
ENV PATH="/nix/var/nix/profiles/default/bin:${PATH}"
RUN mkdir -p /etc/nix && printf '%s\n' \
'experimental-features = nix-command flakes' \
'sandbox = false' \
'build-users-group =' \
'substituters = https://cache.nixos.org' \
'trusted-public-keys = cache.nixos.org-1:6NCHdD59X431o0gWypbMrAURkbJ16ZPMQFGspcDShjY=' \
> /etc/nix/nix.conf
COPY --from=builder /app/target/release/compliance-agent /usr/local/bin/compliance-agent
COPY docker/agent-entrypoint.sh /usr/local/bin/agent-entrypoint.sh
RUN chmod +x /usr/local/bin/agent-entrypoint.sh
# Copy documentation for the help chat assistant
COPY --from=builder /app/README.md /app/README.md
@@ -43,5 +81,6 @@ RUN mkdir -p /data/compliance-scanner/ssh
EXPOSE 3001 3002
ENTRYPOINT ["compliance-agent"]
# Seeds /nix (fresh volume) from the bootstrap tarball, then runs the agent.
ENTRYPOINT ["/usr/local/bin/agent-entrypoint.sh"]
+10 -1
View File
@@ -7,7 +7,16 @@ ARG DOCS_URL=/docs
WORKDIR /app
COPY . .
ENV DOCS_URL=${DOCS_URL}
RUN dx build --release --package compliance-dashboard
# compliance-agent (a workspace member) depends on the private tramiton-core git
# repo, so the workspace resolve needs it even to build the dashboard.
# Authenticate the fetch with a PAT passed as a BuildKit secret.
RUN --mount=type=secret,id=tramiton_token \
if [ -s /run/secrets/tramiton_token ]; then \
git config --global \
url."https://sharang:$(cat /run/secrets/tramiton_token)@gitea.meghsakha.com/".insteadOf \
"ssh://git@gitea.meghsakha.com:22222/"; \
fi && \
CARGO_NET_GIT_FETCH_WITH_CLI=true dx build --release --package compliance-dashboard
FROM debian:bookworm-slim
RUN apt-get update && apt-get install -y ca-certificates libssl3 && rm -rf /var/lib/apt/lists/*
+10 -1
View File
@@ -2,7 +2,16 @@ FROM rust:1.94-bookworm AS builder
WORKDIR /app
COPY . .
RUN cargo build --release -p compliance-mcp
# compliance-agent (a workspace member) depends on the private tramiton-core git
# repo, so the workspace resolve needs it even to build the mcp binary.
# Authenticate the fetch with a PAT passed as a BuildKit secret.
RUN --mount=type=secret,id=tramiton_token \
if [ -s /run/secrets/tramiton_token ]; then \
git config --global \
url."https://sharang:$(cat /run/secrets/tramiton_token)@gitea.meghsakha.com/".insteadOf \
"ssh://git@gitea.meghsakha.com:22222/"; \
fi && \
CARGO_NET_GIT_FETCH_WITH_CLI=true cargo build --release -p compliance-mcp
FROM debian:bookworm-slim
RUN apt-get update && apt-get install -y ca-certificates libssl3 && rm -rf /var/lib/apt/lists/*
+15 -2
View File
@@ -10,6 +10,16 @@ workspace = true
compliance-core = { workspace = true, features = ["mongodb", "telemetry", "axum"] }
compliance-graph = { path = "../compliance-graph" }
compliance-dast = { path = "../compliance-dast" }
# Native firmware build/target detection for bare-metal & RTOS artifacts.
# Same-company IP, used directly (not via CLI) so the whole tramiton suite is
# available to the onboarding classifier. NOTE: CI must be able to fetch this
# private repo (see the git-auth step in .gitea/workflows/ci.yml).
tramiton-core = { git = "ssh://git@gitea.meghsakha.com:22222/sharang/tramiton.git", tag = "v0.4.1" }
# tramiton-repro drives the reproducible build (NixBackend seal_and_build) that
# yields a sealed lock; `libraries_from_inputs` is the analysis-only fallback.
tramiton-repro = { git = "ssh://git@gitea.meghsakha.com:22222/sharang/tramiton.git", tag = "v0.4.1" }
# tramiton-sbom renders the bill of materials from a sealed lock (+ binary SCA).
tramiton-sbom = { git = "ssh://git@gitea.meghsakha.com:22222/sharang/tramiton.git", tag = "v0.4.1" }
serde = { workspace = true }
serde_json = { workspace = true }
tokio = { workspace = true }
@@ -24,7 +34,7 @@ hex = { workspace = true }
uuid = { workspace = true }
secrecy = { workspace = true }
regex = { workspace = true }
axum = "0.8"
axum = { version = "0.8", features = ["multipart"] }
tower-http = { version = "0.6", features = ["cors", "trace", "set-header"] }
git2 = "0.20"
octocrab = "0.44"
@@ -32,6 +42,8 @@ tokio-cron-scheduler = "0.13"
dotenvy = "0.15"
hmac = "0.12"
walkdir = "2"
# Read-only XML tree parsing for PLCopen project files (POU extraction).
roxmltree = "0.20"
base64 = "0.22"
urlencoding = "2"
futures-util = "0.3"
@@ -42,6 +54,7 @@ tokio-tungstenite = { version = "0.26", features = ["rustls-tls-webpki-roots"] }
futures-core = "0.3"
dashmap = { workspace = true }
tokio-stream = { workspace = true }
rand = { workspace = true }
[dev-dependencies]
compliance-core = { workspace = true, features = ["mongodb", "axum"] }
@@ -52,5 +65,5 @@ tokio = { workspace = true }
mongodb = { workspace = true }
uuid = { workspace = true }
secrecy = { workspace = true }
axum = "0.8"
axum = { version = "0.8", features = ["multipart"] }
tower-http = { version = "0.6", features = ["cors"] }
+26 -8
View File
@@ -63,7 +63,22 @@ impl ComplianceAgent {
let db = self.db_pool.for_tenant_id(tenant_id).await?;
let orchestrator =
PipelineOrchestrator::new(self.config.clone(), db, self.llm.clone(), self.http.clone());
orchestrator.run(repo_id, trigger).await
orchestrator.run_target(repo_id, trigger).await
}
/// Alias for [`Self::run_scan`] — every scan runs the unified onboarded-target
/// pipeline. Kept as a distinct name for the `/targets/{id}/scan` endpoint's
/// intent.
pub async fn run_target_scan(
&self,
tenant_id: &str,
target_id: &str,
trigger: compliance_core::models::ScanTrigger,
) -> Result<(), crate::error::AgentError> {
let db = self.db_pool.for_tenant_id(tenant_id).await?;
let orchestrator =
PipelineOrchestrator::new(self.config.clone(), db, self.llm.clone(), self.http.clone());
orchestrator.run_target(target_id, trigger).await
}
/// Run a PR review: scan the diff and post review comments.
@@ -76,16 +91,19 @@ impl ComplianceAgent {
head_sha: &str,
) -> Result<(), crate::error::AgentError> {
let db = self.db_pool.for_tenant_id(tenant_id).await?;
let repo = db
.repositories()
.find_one(mongodb::bson::doc! {
"_id": mongodb::bson::oid::ObjectId::parse_str(repo_id)
.map_err(|e| crate::error::AgentError::Other(e.to_string()))?
})
let oid = mongodb::bson::oid::ObjectId::parse_str(repo_id)
.map_err(|e| crate::error::AgentError::Other(e.to_string()))?;
let target = db
.onboarded_targets()
.find_one(mongodb::bson::doc! { "_id": oid })
.await?
.ok_or_else(|| {
crate::error::AgentError::Other(format!("Repository {repo_id} not found"))
crate::error::AgentError::Other(format!("Target {repo_id} not found"))
})?;
let code = target.code_artifact().ok_or_else(|| {
crate::error::AgentError::Other(format!("Target {repo_id} has no code artifact"))
})?;
let repo = crate::pipeline::repo_view::RepoView::from_target(&target, code);
let orchestrator =
PipelineOrchestrator::new(self.config.clone(), db, self.llm.clone(), self.http.clone());
+12 -4
View File
@@ -146,7 +146,7 @@ pub async fn build_embeddings(
let agent_clone = (*agent).clone();
tokio::spawn(async move {
let repo = match db
.repositories()
.onboarded_targets()
.find_one(doc! { "_id": mongodb::bson::oid::ObjectId::parse_str(&repo_id).ok() })
.await
{
@@ -194,14 +194,22 @@ pub async fn build_embeddings(
}
};
let code = match repo.code_artifact() {
Some(c) => c,
None => {
tracing::error!("Target {repo_id} has no code artifact for embedding build");
return;
}
};
let view = crate::pipeline::repo_view::RepoView::from_target(&repo, code);
let creds = crate::pipeline::git::RepoCredentials {
ssh_key_path: Some(agent_clone.config.ssh_key_path.clone()),
auth_token: repo.auth_token.clone(),
auth_username: repo.auth_username.clone(),
auth_token: view.auth_token.clone(),
auth_username: view.auth_username.clone(),
};
let git_ops =
crate::pipeline::git::GitOps::new(&agent_clone.config.git_clone_base_path, creds);
let repo_path = match git_ops.clone_or_fetch(&repo.git_url, &repo.name) {
let repo_path = match git_ops.clone_or_fetch(&view.git_url, &view.name) {
Ok(p) => p,
Err(e) => {
tracing::error!("Failed to clone repo for embedding build: {e}");
+13 -5
View File
@@ -255,7 +255,7 @@ pub async fn get_file_content(
// Look up the repository to get repo name
let repo = db
.repositories()
.onboarded_targets()
.find_one(doc! { "_id": mongodb::bson::oid::ObjectId::parse_str(&repo_id).ok() })
.await
.map_err(|_| StatusCode::INTERNAL_SERVER_ERROR)?
@@ -317,7 +317,7 @@ pub async fn trigger_build(
let agent_clone = (*agent).clone();
tokio::spawn(async move {
let repo = match db
.repositories()
.onboarded_targets()
.find_one(doc! { "_id": mongodb::bson::oid::ObjectId::parse_str(&repo_id).ok() })
.await
{
@@ -328,14 +328,22 @@ pub async fn trigger_build(
}
};
let code = match repo.code_artifact() {
Some(c) => c,
None => {
tracing::error!("Target {repo_id} has no code artifact for graph build");
return;
}
};
let view = crate::pipeline::repo_view::RepoView::from_target(&repo, code);
let creds = crate::pipeline::git::RepoCredentials {
ssh_key_path: Some(agent_clone.config.ssh_key_path.clone()),
auth_token: repo.auth_token.clone(),
auth_username: repo.auth_username.clone(),
auth_token: view.auth_token.clone(),
auth_username: view.auth_username.clone(),
};
let git_ops =
crate::pipeline::git::GitOps::new(&agent_clone.config.git_clone_base_path, creds);
let repo_path = match git_ops.clone_or_fetch(&repo.git_url, &repo.name) {
let repo_path = match git_ops.clone_or_fetch(&view.git_url, &view.name) {
Ok(p) => p,
Err(e) => {
tracing::error!("Failed to clone repo for graph build: {e}");
+13 -1
View File
@@ -10,6 +10,18 @@ pub async fn health() -> Json<serde_json::Value> {
Json(serde_json::json!({ "status": "ok" }))
}
/// GET /api/v1/settings/ssh-public-key — the agent's SSH deploy public key,
/// for adding as a read-only deploy key on private git targets.
#[tracing::instrument(skip_all)]
pub async fn get_ssh_public_key(
axum::extract::Extension(agent): AgentExt,
) -> Result<Json<serde_json::Value>, axum::http::StatusCode> {
let public_path = format!("{}.pub", agent.config.ssh_key_path);
let public_key =
std::fs::read_to_string(&public_path).map_err(|_| axum::http::StatusCode::NOT_FOUND)?;
Ok(Json(serde_json::json!({ "public_key": public_key.trim() })))
}
#[tracing::instrument(skip_all)]
pub async fn stats_overview(
axum::extract::Extension(agent): AgentExt,
@@ -19,7 +31,7 @@ pub async fn stats_overview(
let db = &db;
let total_repositories = db
.repositories()
.onboarded_targets()
.count_documents(doc! {})
.await
.unwrap_or(0);
@@ -0,0 +1,186 @@
//! `/api/v1/mcp-tokens` — per-tenant API tokens for the MCP server.
//!
//! These are opaque static bearers issued via the dashboard (or a
//! direct curl with a KC JWT) and copied into LLM clients (Claude
//! Desktop / Cursor / ChatGPT). The MCP server hashes incoming bearers
//! and looks them up in the cross-tenant `<prefix>__admin.mcp_tokens`
//! collection to derive the tenant_id for routing.
//!
//! The raw token is shown to the caller exactly once at creation; the
//! database only ever stores the SHA-256 hash. Revocation is a soft
//! delete (sets `revoked: true`) so the audit log keeps the record.
use axum::extract::{Extension, Path};
use axum::http::StatusCode;
use axum::Json;
use base64::{engine::general_purpose::URL_SAFE_NO_PAD, Engine as _};
use compliance_core::models::{McpToken, McpTokenView};
use compliance_core::tenant_ctx::TenantCtx;
use mongodb::bson::doc;
use rand::RngCore;
use sha2::{Digest, Sha256};
use super::dto::{AgentExt, ApiResponse};
/// Mongo collection name inside the admin DB.
const COLLECTION: &str = "mcp_tokens";
/// Token prefix the MCP server expects on every bearer.
const TOKEN_PREFIX: &str = "mcpt_";
/// Bytes of randomness behind each token. 32 → ~256 bits.
/// Encoded as URL-safe base64 without padding → 43 chars.
/// Combined with `mcpt_` → 48-char tokens.
const TOKEN_RAND_BYTES: usize = 32;
#[derive(serde::Deserialize)]
pub struct CreateMcpTokenRequest {
pub name: String,
}
/// Returned exactly once at creation. The `token` field is gone from
/// the listing endpoint — the user must save it now.
#[derive(serde::Serialize)]
pub struct CreateMcpTokenResponse {
pub token: String,
pub view: McpTokenView,
}
/// `POST /api/v1/mcp-tokens` — mint a new token for the caller's tenant.
#[tracing::instrument(skip_all)]
pub async fn create_mcp_token(
Extension(agent): AgentExt,
tenant: TenantCtx,
Json(req): Json<CreateMcpTokenRequest>,
) -> Result<Json<CreateMcpTokenResponse>, StatusCode> {
if req.name.trim().is_empty() {
return Err(StatusCode::BAD_REQUEST);
}
let raw = generate_token();
let token_hash = sha256_hex(&raw);
let token_prefix: String = raw.chars().take(12).collect();
let mut token = McpToken {
id: None,
token_hash,
token_prefix,
tenant_id: tenant.0.tenant_id.clone(),
name: req.name.trim().to_string(),
created_by: tenant.0.user_id.clone(),
created_at: chrono::Utc::now(),
last_used_at: None,
revoked: false,
};
let col = agent.db_pool.admin_db().collection::<McpToken>(COLLECTION);
let res = col.insert_one(&token).await.map_err(|e| {
tracing::error!("Failed to insert MCP token: {e}");
StatusCode::INTERNAL_SERVER_ERROR
})?;
token.id = res.inserted_id.as_object_id();
Ok(Json(CreateMcpTokenResponse {
view: McpTokenView::from(&token),
token: raw,
}))
}
/// `GET /api/v1/mcp-tokens` — list tokens for the caller's tenant.
/// Hash is never returned; only metadata + the 12-char prefix so the
/// user can identify which row is which.
#[tracing::instrument(skip_all)]
pub async fn list_mcp_tokens(
Extension(agent): AgentExt,
tenant: TenantCtx,
) -> Result<Json<ApiResponse<Vec<McpTokenView>>>, StatusCode> {
let col = agent.db_pool.admin_db().collection::<McpToken>(COLLECTION);
let mut cursor = col
.find(doc! { "tenant_id": &tenant.0.tenant_id })
.sort(doc! { "created_at": -1 })
.await
.map_err(|e| {
tracing::error!("Failed to list MCP tokens: {e}");
StatusCode::INTERNAL_SERVER_ERROR
})?;
let mut out = Vec::new();
while cursor.advance().await.map_err(|e| {
tracing::warn!("MCP tokens cursor advance failed: {e}");
StatusCode::INTERNAL_SERVER_ERROR
})? {
match cursor.deserialize_current() {
Ok(t) => out.push(McpTokenView::from(&t)),
Err(e) => tracing::warn!("Failed to deserialize MCP token: {e}"),
}
}
Ok(Json(ApiResponse {
data: out,
total: None,
page: None,
}))
}
/// `DELETE /api/v1/mcp-tokens/{id}` — revoke (soft delete).
/// Scoped to the caller's tenant: a user can't revoke another tenant's
/// token even if they guess its id.
#[tracing::instrument(skip_all, fields(id = %id))]
pub async fn revoke_mcp_token(
Extension(agent): AgentExt,
tenant: TenantCtx,
Path(id): Path<String>,
) -> Result<Json<serde_json::Value>, StatusCode> {
let oid = mongodb::bson::oid::ObjectId::parse_str(&id).map_err(|_| StatusCode::BAD_REQUEST)?;
let col = agent.db_pool.admin_db().collection::<McpToken>(COLLECTION);
let result = col
.update_one(
doc! { "_id": oid, "tenant_id": &tenant.0.tenant_id },
doc! { "$set": { "revoked": true } },
)
.await
.map_err(|e| {
tracing::error!("Failed to revoke MCP token: {e}");
StatusCode::INTERNAL_SERVER_ERROR
})?;
if result.matched_count == 0 {
return Err(StatusCode::NOT_FOUND);
}
Ok(Json(serde_json::json!({ "status": "revoked" })))
}
/// 32 bytes random → URL-safe base64 → 43 chars, no padding.
/// Prefixed with `mcpt_` so the MCP server can sniff the format
/// before bothering with the DB lookup.
fn generate_token() -> String {
let mut bytes = [0u8; TOKEN_RAND_BYTES];
rand::rng().fill_bytes(&mut bytes);
format!("{TOKEN_PREFIX}{}", URL_SAFE_NO_PAD.encode(bytes))
}
fn sha256_hex(s: &str) -> String {
let mut h = Sha256::new();
h.update(s.as_bytes());
hex::encode(h.finalize())
}
#[cfg(test)]
mod tests {
use super::*;
#[test]
fn generated_tokens_are_unique_and_prefixed() {
let a = generate_token();
let b = generate_token();
assert_ne!(a, b);
assert!(a.starts_with(TOKEN_PREFIX));
assert!(b.starts_with(TOKEN_PREFIX));
// 5 + 43 = 48 chars
assert_eq!(a.len(), 5 + 43);
}
#[test]
fn sha256_is_stable_and_64_hex() {
let h = sha256_hex("mcpt_abc");
assert_eq!(h.len(), 64);
assert!(h.chars().all(|c| c.is_ascii_hexdigit()));
assert_eq!(sha256_hex("mcpt_abc"), h);
}
}
+2 -2
View File
@@ -7,10 +7,11 @@ pub mod graph;
pub mod health;
pub mod help_chat;
pub mod issues;
pub mod mcp_tokens;
pub mod notifications;
pub mod onboarding;
pub mod pentest_handlers;
pub use pentest_handlers as pentest;
pub mod repos;
pub mod sbom;
pub mod scans;
@@ -19,6 +20,5 @@ pub use dto::*;
pub use findings::*;
pub use health::*;
pub use issues::*;
pub use repos::*;
pub use sbom::*;
pub use scans::*;
@@ -0,0 +1,614 @@
//! Onboarding API — CRUD for unified targets, artifact add, classification, and
//! the scan-applicability matrix. The wizard (and future integrations) drive
//! onboarding through these endpoints.
use std::collections::HashMap;
use std::sync::Arc;
use axum::extract::{Extension, Multipart, Path, Query};
use axum::http::StatusCode;
use axum::Json;
use mongodb::bson::{doc, oid::ObjectId, to_bson};
use serde::{Deserialize, Serialize};
use compliance_core::models::{
Artifact, ArtifactKind, ComplianceProfile, OnboardedTarget, PlcFormat, TargetScanConfig,
TargetType,
};
use compliance_core::scan_matrix::{applicable_scans, supports_pentest};
use compliance_core::tenant_ctx::TenantCtx;
use crate::agent::ComplianceAgent;
use crate::classify::{classify_target, MockFirmwareDetector};
use super::dto::tenant_db;
use super::{collect_cursor_async, ApiResponse, PaginationParams};
type AgentExt = Extension<Arc<ComplianceAgent>>;
/// A client-supplied artifact spec. The server builds the [`Artifact`] (and its
/// id) from it, so clients never set internal fields.
#[derive(Deserialize)]
pub struct ArtifactInput {
pub kind: ArtifactKind,
pub source_ref: String,
#[serde(default)]
pub branch: Option<String>,
#[serde(default)]
pub plc_format: Option<PlcFormat>,
}
impl ArtifactInput {
fn build(&self) -> Artifact {
let s = self.source_ref.clone();
match self.kind {
ArtifactKind::GitRepo => {
Artifact::git_repo(s, self.branch.clone().unwrap_or_else(|| "main".to_string()))
}
ArtifactKind::LiveUrl => Artifact::live_url(s),
ArtifactKind::FirmwareImage => Artifact::firmware_image(s),
ArtifactKind::SourceArchive => Artifact::source_archive(s),
ArtifactKind::MobilePackage => Artifact::mobile_package(s),
ArtifactKind::ContainerImage => Artifact::container_image(s),
ArtifactKind::PlcProject => {
Artifact::plc_project(s, self.plc_format.unwrap_or(PlcFormat::PlcopenXml))
}
ArtifactKind::PlaintextDescription => Artifact::plaintext(s),
}
}
}
#[derive(Deserialize)]
pub struct CreateTargetRequest {
pub name: String,
pub target_type: TargetType,
#[serde(default)]
pub description: Option<String>,
#[serde(default)]
pub artifacts: Vec<ArtifactInput>,
}
#[derive(Deserialize)]
pub struct UpdateTargetRequest {
pub name: Option<String>,
pub target_type: Option<TargetType>,
pub scan_config: Option<TargetScanConfig>,
pub compliance_profile: Option<ComplianceProfile>,
pub scan_schedule: Option<String>,
/// Replace the target's artifacts wholesale (used by the dashboard editor).
#[serde(default)]
pub artifacts: Option<Vec<ArtifactInput>>,
}
/// One applicable-scan option, serialized for the wizard.
#[derive(Serialize)]
pub struct ScanOptionDto {
pub scan: String,
pub default_on: bool,
pub rationale: String,
pub required_artifact: Option<String>,
pub blocked_reason: Option<String>,
}
#[derive(Serialize)]
pub struct ApplicableScansResponse {
pub scans: Vec<ScanOptionDto>,
pub pentest_supported: bool,
}
fn parse_oid(id: &str) -> Result<ObjectId, StatusCode> {
ObjectId::parse_str(id).map_err(|_| StatusCode::BAD_REQUEST)
}
/// GET /api/v1/targets — list onboarded targets (paginated).
#[tracing::instrument(skip_all)]
pub async fn list_targets(
Extension(agent): AgentExt,
tenant: TenantCtx,
Query(params): Query<PaginationParams>,
) -> Result<Json<ApiResponse<Vec<OnboardedTarget>>>, StatusCode> {
let db = tenant_db(&agent, &tenant).await?;
let skip = (params.page.saturating_sub(1)) * params.limit as u64;
let total = db
.onboarded_targets()
.count_documents(doc! {})
.await
.unwrap_or(0);
let targets = match db
.onboarded_targets()
.find(doc! {})
.skip(skip)
.limit(params.limit)
.await
{
Ok(cursor) => collect_cursor_async(cursor).await,
Err(e) => {
tracing::warn!("Failed to fetch onboarded targets: {e}");
Vec::new()
}
};
Ok(Json(ApiResponse {
data: targets,
total: Some(total),
page: Some(params.page),
}))
}
/// POST /api/v1/targets — create an onboarded target.
#[tracing::instrument(skip_all)]
pub async fn create_target(
Extension(agent): AgentExt,
tenant: TenantCtx,
Json(req): Json<CreateTargetRequest>,
) -> Result<Json<ApiResponse<OnboardedTarget>>, StatusCode> {
let mut target = OnboardedTarget::new(req.name, req.target_type);
target.description = req.description;
target.artifacts = req.artifacts.iter().map(ArtifactInput::build).collect();
let db = tenant_db(&agent, &tenant).await?;
let res = db
.onboarded_targets()
.insert_one(&target)
.await
.map_err(|_| StatusCode::INTERNAL_SERVER_ERROR)?;
target.id = res.inserted_id.as_object_id();
Ok(Json(ApiResponse {
data: target,
total: None,
page: None,
}))
}
/// GET /api/v1/targets/{id} — fetch one target.
#[tracing::instrument(skip_all, fields(target_id = %id))]
pub async fn get_target(
Extension(agent): AgentExt,
tenant: TenantCtx,
Path(id): Path<String>,
) -> Result<Json<ApiResponse<OnboardedTarget>>, StatusCode> {
let oid = parse_oid(&id)?;
let db = tenant_db(&agent, &tenant).await?;
let target = db
.onboarded_targets()
.find_one(doc! { "_id": oid })
.await
.map_err(|_| StatusCode::INTERNAL_SERVER_ERROR)?
.ok_or(StatusCode::NOT_FOUND)?;
Ok(Json(ApiResponse {
data: target,
total: None,
page: None,
}))
}
/// PATCH /api/v1/targets/{id} — update mutable fields.
#[tracing::instrument(skip_all, fields(target_id = %id))]
pub async fn update_target(
Extension(agent): AgentExt,
tenant: TenantCtx,
Path(id): Path<String>,
Json(req): Json<UpdateTargetRequest>,
) -> Result<Json<ApiResponse<OnboardedTarget>>, StatusCode> {
let oid = parse_oid(&id)?;
let db = tenant_db(&agent, &tenant).await?;
let mut set = doc! { "updated_at": mongodb::bson::DateTime::now() };
if let Some(name) = req.name {
set.insert("name", name);
}
if let Some(tt) = req.target_type {
set.insert(
"target_type",
to_bson(&tt).map_err(|_| StatusCode::BAD_REQUEST)?,
);
}
if let Some(sc) = req.scan_config {
set.insert(
"scan_config",
to_bson(&sc).map_err(|_| StatusCode::BAD_REQUEST)?,
);
}
if let Some(cp) = req.compliance_profile {
set.insert(
"compliance_profile",
to_bson(&cp).map_err(|_| StatusCode::BAD_REQUEST)?,
);
}
if let Some(ss) = req.scan_schedule {
set.insert("scan_schedule", ss);
}
if let Some(arts) = req.artifacts {
let built: Vec<Artifact> = arts.iter().map(ArtifactInput::build).collect();
set.insert(
"artifacts",
to_bson(&built).map_err(|_| StatusCode::BAD_REQUEST)?,
);
}
db.onboarded_targets()
.update_one(doc! { "_id": oid }, doc! { "$set": set })
.await
.map_err(|_| StatusCode::INTERNAL_SERVER_ERROR)?;
get_target(Extension(agent), tenant, Path(id)).await
}
/// DELETE /api/v1/targets/{id} — remove the target and its findings/scans.
#[tracing::instrument(skip_all, fields(target_id = %id))]
pub async fn delete_target(
Extension(agent): AgentExt,
tenant: TenantCtx,
Path(id): Path<String>,
) -> Result<Json<serde_json::Value>, StatusCode> {
let oid = parse_oid(&id)?;
let db = tenant_db(&agent, &tenant).await?;
db.onboarded_targets()
.delete_one(doc! { "_id": oid })
.await
.map_err(|_| StatusCode::INTERNAL_SERVER_ERROR)?;
// Cascade all data keyed by repo_id == target id (best-effort).
let db = &db;
let _ = db.findings().delete_many(doc! { "repo_id": &id }).await;
let _ = db.sbom_entries().delete_many(doc! { "repo_id": &id }).await;
let _ = db.scan_runs().delete_many(doc! { "repo_id": &id }).await;
let _ = db.cve_alerts().delete_many(doc! { "repo_id": &id }).await;
let _ = db
.tracker_issues()
.delete_many(doc! { "repo_id": &id })
.await;
let _ = db.graph_nodes().delete_many(doc! { "repo_id": &id }).await;
let _ = db.graph_edges().delete_many(doc! { "repo_id": &id }).await;
let _ = db.graph_builds().delete_many(doc! { "repo_id": &id }).await;
let _ = db
.impact_analyses()
.delete_many(doc! { "repo_id": &id })
.await;
let _ = db
.code_embeddings()
.delete_many(doc! { "repo_id": &id })
.await;
let _ = db
.embedding_builds()
.delete_many(doc! { "repo_id": &id })
.await;
// DAST targets linked to this target, and all their downstream data.
if let Ok(mut cursor) = db.dast_targets().find(doc! { "repo_id": &id }).await {
use futures_util::StreamExt;
while let Some(Ok(dt)) = cursor.next().await {
let dast_target_id = dt.id.map(|oid| oid.to_hex()).unwrap_or_default();
if !dast_target_id.is_empty() {
cascade_delete_dast_target(db, &dast_target_id).await;
}
}
}
// Pentest sessions linked directly to this target (not via a DAST target).
if let Ok(mut cursor) = db.pentest_sessions().find(doc! { "repo_id": &id }).await {
use futures_util::StreamExt;
while let Some(Ok(session)) = cursor.next().await {
let session_id = session.id.map(|oid| oid.to_hex()).unwrap_or_default();
if !session_id.is_empty() {
let _ = db
.attack_chain_nodes()
.delete_many(doc! { "session_id": &session_id })
.await;
let _ = db
.pentest_messages()
.delete_many(doc! { "session_id": &session_id })
.await;
let _ = db
.dast_findings()
.delete_many(doc! { "session_id": &session_id })
.await;
}
}
}
let _ = db
.pentest_sessions()
.delete_many(doc! { "repo_id": &id })
.await;
Ok(Json(serde_json::json!({ "status": "deleted" })))
}
/// Delete a DAST target and everything downstream of it (pentest sessions +
/// their attack chains / messages / findings, DAST scan runs + findings).
async fn cascade_delete_dast_target(db: &crate::database::Database, target_id: &str) {
use futures_util::StreamExt;
if let Ok(mut cursor) = db
.pentest_sessions()
.find(doc! { "target_id": target_id })
.await
{
while let Some(Ok(session)) = cursor.next().await {
let session_id = session.id.map(|oid| oid.to_hex()).unwrap_or_default();
if !session_id.is_empty() {
let _ = db
.attack_chain_nodes()
.delete_many(doc! { "session_id": &session_id })
.await;
let _ = db
.pentest_messages()
.delete_many(doc! { "session_id": &session_id })
.await;
let _ = db
.dast_findings()
.delete_many(doc! { "session_id": &session_id })
.await;
}
}
}
let _ = db
.pentest_sessions()
.delete_many(doc! { "target_id": target_id })
.await;
let _ = db
.dast_findings()
.delete_many(doc! { "target_id": target_id })
.await;
let _ = db
.dast_scan_runs()
.delete_many(doc! { "target_id": target_id })
.await;
if let Ok(oid) = mongodb::bson::oid::ObjectId::parse_str(target_id) {
let _ = db.dast_targets().delete_one(doc! { "_id": oid }).await;
}
}
/// POST /api/v1/targets/{id}/artifacts — attach an artifact (by reference).
#[tracing::instrument(skip_all, fields(target_id = %id))]
pub async fn add_artifact(
Extension(agent): AgentExt,
tenant: TenantCtx,
Path(id): Path<String>,
Json(input): Json<ArtifactInput>,
) -> Result<Json<ApiResponse<OnboardedTarget>>, StatusCode> {
let oid = parse_oid(&id)?;
let db = tenant_db(&agent, &tenant).await?;
let artifact = to_bson(&input.build()).map_err(|_| StatusCode::BAD_REQUEST)?;
db.onboarded_targets()
.update_one(
doc! { "_id": oid },
doc! { "$push": { "artifacts": artifact }, "$set": { "updated_at": mongodb::bson::DateTime::now() } },
)
.await
.map_err(|_| StatusCode::INTERNAL_SERVER_ERROR)?;
get_target(Extension(agent), tenant, Path(id)).await
}
/// POST /api/v1/targets/{id}/artifacts/upload — attach an artifact by uploading
/// its file (PLC project, firmware image, source archive, mobile package). The
/// bytes are written to the artifact blob store and referenced by `stored_path`,
/// so ingest resolves them locally (no URL fetch).
///
/// Multipart fields: `file` (required), `kind` (required, snake_case
/// `ArtifactKind`), `plc_format` (optional, for PLC projects).
#[tracing::instrument(skip_all, fields(target_id = %id))]
pub async fn upload_artifact(
Extension(agent): AgentExt,
tenant: TenantCtx,
Path(id): Path<String>,
mut multipart: Multipart,
) -> Result<Json<ApiResponse<OnboardedTarget>>, StatusCode> {
let oid = parse_oid(&id)?;
let db = tenant_db(&agent, &tenant).await?;
if db
.onboarded_targets()
.find_one(doc! { "_id": oid })
.await
.map_err(|_| StatusCode::INTERNAL_SERVER_ERROR)?
.is_none()
{
return Err(StatusCode::NOT_FOUND);
}
let mut kind: Option<ArtifactKind> = None;
let mut plc_format: Option<PlcFormat> = None;
let mut filename = String::from("upload.bin");
let mut bytes: Option<axum::body::Bytes> = None;
while let Some(field) = multipart
.next_field()
.await
.map_err(|_| StatusCode::BAD_REQUEST)?
{
match field.name().unwrap_or("") {
"kind" => {
let v = field.text().await.map_err(|_| StatusCode::BAD_REQUEST)?;
kind = parse_enum(&v);
}
"plc_format" => {
let v = field.text().await.map_err(|_| StatusCode::BAD_REQUEST)?;
plc_format = parse_enum(&v);
}
"file" => {
if let Some(fname) = field.file_name() {
filename = fname.to_string();
}
bytes = Some(field.bytes().await.map_err(|_| StatusCode::BAD_REQUEST)?);
}
_ => {}
}
}
let (Some(kind), Some(bytes)) = (kind, bytes) else {
return Err(StatusCode::BAD_REQUEST);
};
// Store the uploaded bytes under the artifact blob store.
let safe_name: String = filename
.chars()
.map(|c| {
if c.is_ascii_alphanumeric() || matches!(c, '.' | '-' | '_') {
c
} else {
'_'
}
})
.collect();
let dir = std::path::Path::new(&agent.config.artifact_store_base_path)
.join("uploads")
.join(&id);
std::fs::create_dir_all(&dir).map_err(|_| StatusCode::INTERNAL_SERVER_ERROR)?;
let dest = dir.join(format!("{}_{safe_name}", uuid::Uuid::new_v4()));
std::fs::write(&dest, bytes.as_ref()).map_err(|_| StatusCode::INTERNAL_SERVER_ERROR)?;
// Build the artifact for this kind, referencing the stored file.
let mut artifact = match kind {
ArtifactKind::PlcProject => Artifact::plc_project(
filename.clone(),
plc_format.unwrap_or(PlcFormat::PlcopenXml),
),
ArtifactKind::FirmwareImage => Artifact::firmware_image(filename.clone()),
ArtifactKind::SourceArchive => Artifact::source_archive(filename.clone()),
ArtifactKind::MobilePackage => Artifact::mobile_package(filename.clone()),
// Non-file kinds (git repo, live URL, container ref, text) use the JSON
// add-artifact endpoint, not upload.
_ => return Err(StatusCode::BAD_REQUEST),
};
artifact.stored_path = Some(dest.to_string_lossy().to_string());
artifact.size_bytes = Some(bytes.len() as u64);
let artifact_bson = to_bson(&artifact).map_err(|_| StatusCode::INTERNAL_SERVER_ERROR)?;
db.onboarded_targets()
.update_one(
doc! { "_id": oid },
doc! { "$push": { "artifacts": artifact_bson }, "$set": { "updated_at": mongodb::bson::DateTime::now() } },
)
.await
.map_err(|_| StatusCode::INTERNAL_SERVER_ERROR)?;
get_target(Extension(agent), tenant, Path(id)).await
}
/// Deserialize a snake_case enum value from a plain string.
fn parse_enum<T: for<'de> Deserialize<'de>>(s: &str) -> Option<T> {
serde_json::from_value(serde_json::Value::String(s.to_string())).ok()
}
/// GET /api/v1/targets/{id}/applicable-scans — the scan-applicability matrix.
#[tracing::instrument(skip_all, fields(target_id = %id))]
pub async fn applicable_scans_for_target(
Extension(agent): AgentExt,
tenant: TenantCtx,
Path(id): Path<String>,
) -> Result<Json<ApiResponse<ApplicableScansResponse>>, StatusCode> {
let oid = parse_oid(&id)?;
let db = tenant_db(&agent, &tenant).await?;
let target = db
.onboarded_targets()
.find_one(doc! { "_id": oid })
.await
.map_err(|_| StatusCode::INTERNAL_SERVER_ERROR)?
.ok_or(StatusCode::NOT_FOUND)?;
let scans = applicable_scans(&target)
.into_iter()
.map(|o| ScanOptionDto {
scan: o.scan.to_string(),
default_on: o.default_on,
rationale: o.rationale,
required_artifact: o.required_artifact.map(|k| k.to_string()),
blocked_reason: o.blocked_reason,
})
.collect();
Ok(Json(ApiResponse {
data: ApplicableScansResponse {
scans,
pentest_supported: supports_pentest(target.target_type),
},
total: None,
page: None,
}))
}
/// POST /api/v1/targets/{id}/detect — classify the target from its artifacts.
///
/// This is the lightweight pass: it classifies from artifact kinds without
/// ingesting (cloning) sources, so it returns immediately. Deep detection (after
/// ingest, with tramiton firmware analysis) is a follow-up background step.
#[tracing::instrument(skip_all, fields(target_id = %id))]
pub async fn detect_target(
Extension(agent): AgentExt,
tenant: TenantCtx,
Path(id): Path<String>,
) -> Result<Json<ApiResponse<OnboardedTarget>>, StatusCode> {
let oid = parse_oid(&id)?;
let db = tenant_db(&agent, &tenant).await?;
let mut target = db
.onboarded_targets()
.find_one(doc! { "_id": oid })
.await
.map_err(|_| StatusCode::INTERNAL_SERVER_ERROR)?
.ok_or(StatusCode::NOT_FOUND)?;
// No ingested working paths here → kind-based classification only; the mock
// firmware detector is never invoked (no firmware working path present).
let empty = HashMap::new();
let detector = MockFirmwareDetector { detection: None };
let classification = classify_target(&target, &empty, &detector)
.await
.map_err(|_| StatusCode::INTERNAL_SERVER_ERROR)?;
let classification_bson =
to_bson(&classification).map_err(|_| StatusCode::INTERNAL_SERVER_ERROR)?;
db.onboarded_targets()
.update_one(
doc! { "_id": oid },
doc! { "$set": { "classification": classification_bson, "updated_at": mongodb::bson::DateTime::now() } },
)
.await
.map_err(|_| StatusCode::INTERNAL_SERVER_ERROR)?;
target.classification = Some(classification);
Ok(Json(ApiResponse {
data: target,
total: None,
page: None,
}))
}
/// POST /api/v1/targets/{id}/scan — trigger a scan for the target.
///
/// Dispatches to the unified pipeline when `UNIFIED_PIPELINE` is set (else the
/// legacy path). Runs in the background and returns immediately.
#[tracing::instrument(skip_all, fields(target_id = %id))]
pub async fn trigger_target_scan(
Extension(agent): AgentExt,
tenant: TenantCtx,
Path(id): Path<String>,
) -> Result<Json<serde_json::Value>, StatusCode> {
let oid = parse_oid(&id)?;
let db = tenant_db(&agent, &tenant).await?;
// 404 if the target doesn't exist for this tenant.
if db
.onboarded_targets()
.find_one(doc! { "_id": oid })
.await
.map_err(|_| StatusCode::INTERNAL_SERVER_ERROR)?
.is_none()
{
return Err(StatusCode::NOT_FOUND);
}
let agent_clone = (*agent).clone();
let tenant_id = tenant.0.tenant_id.clone();
tokio::spawn(async move {
// Always the unified target pipeline — this endpoint is about an
// onboarded target by construction, independent of the global
// `unified_pipeline` transition flag used by the legacy paths.
if let Err(e) = agent_clone
.run_target_scan(
&tenant_id,
&id,
compliance_core::models::ScanTrigger::Manual,
)
.await
{
tracing::error!("Manual target scan failed for {id}: {e}");
}
});
Ok(Json(serde_json::json!({ "status": "scan_triggered" })))
}
@@ -113,14 +113,14 @@ pub async fn create_session(
session.config = Some(config.clone());
session.repo_id = target.repo_id.clone();
// Resolve repo_id from git_repo_url if provided
// Resolve repo_id (target id) from git_repo_url if provided
if let Some(ref git_url) = config.git_repo_url {
if let Ok(Some(repo)) = db
.repositories()
.find_one(doc! { "git_url": git_url })
if let Ok(Some(target)) = db
.onboarded_targets()
.find_one(doc! { "artifacts.source_ref": git_url })
.await
{
session.repo_id = repo.id.map(|oid| oid.to_hex());
session.repo_id = target.id.map(|oid| oid.to_hex());
}
}
@@ -380,17 +380,20 @@ pub async fn lookup_repo(
) -> Result<Json<ApiResponse<serde_json::Value>>, StatusCode> {
let db = tenant_db(&agent, &tenant).await?;
let repo = db
.repositories()
.find_one(doc! { "git_url": &params.url })
.onboarded_targets()
.find_one(doc! { "artifacts.source_ref": &params.url })
.await
.map_err(|_| StatusCode::INTERNAL_SERVER_ERROR)?;
let data = match repo {
Some(r) => serde_json::json!({
Some(r) => {
let git = r.code_artifact().and_then(|c| c.git.as_ref());
serde_json::json!({
"name": r.name,
"default_branch": r.default_branch,
"last_scanned_commit": r.last_scanned_commit,
}),
"default_branch": git.map(|g| g.default_branch.clone()),
"last_scanned_commit": git.and_then(|g| g.last_scanned_commit.clone()),
})
}
None => serde_json::Value::Null,
};
-339
View File
@@ -1,339 +0,0 @@
use axum::extract::{Extension, Path, Query};
use axum::http::StatusCode;
use axum::Json;
use mongodb::bson::doc;
use super::dto::*;
use compliance_core::models::*;
use compliance_core::tenant_ctx::TenantCtx;
#[tracing::instrument(skip_all)]
pub async fn list_repositories(
Extension(agent): AgentExt,
tenant: TenantCtx,
Query(params): Query<PaginationParams>,
) -> ApiResult<Vec<TrackedRepository>> {
let db = tenant_db(&agent, &tenant).await?;
let db = &db;
let skip = (params.page.saturating_sub(1)) * params.limit as u64;
let total = db
.repositories()
.count_documents(doc! {})
.await
.unwrap_or(0);
let repos = match db
.repositories()
.find(doc! {})
.skip(skip)
.limit(params.limit)
.await
{
Ok(cursor) => collect_cursor_async(cursor).await,
Err(e) => {
tracing::warn!("Failed to fetch repositories: {e}");
Vec::new()
}
};
Ok(Json(ApiResponse {
data: repos,
total: Some(total),
page: Some(params.page),
}))
}
#[tracing::instrument(skip_all)]
pub async fn add_repository(
Extension(agent): AgentExt,
tenant: TenantCtx,
Json(req): Json<AddRepositoryRequest>,
) -> Result<Json<ApiResponse<TrackedRepository>>, (StatusCode, String)> {
// Validate repository access before saving
let creds = crate::pipeline::git::RepoCredentials {
ssh_key_path: Some(agent.config.ssh_key_path.clone()),
auth_token: req.auth_token.clone(),
auth_username: req.auth_username.clone(),
};
if let Err(e) = crate::pipeline::git::GitOps::test_access(&req.git_url, &creds) {
return Err((
StatusCode::BAD_REQUEST,
format!("Cannot access repository: {e}"),
));
}
let mut repo = TrackedRepository::new(req.name, req.git_url);
repo.default_branch = req.default_branch;
repo.auth_token = req.auth_token;
repo.auth_username = req.auth_username;
repo.tracker_type = req.tracker_type;
repo.tracker_owner = req.tracker_owner;
repo.tracker_repo = req.tracker_repo;
repo.tracker_token = req.tracker_token;
repo.scan_schedule = req.scan_schedule;
let db = tenant_db(&agent, &tenant)
.await
.map_err(|s| (s, "failed to acquire tenant database".to_string()))?;
db.repositories().insert_one(&repo).await.map_err(|_| {
(
StatusCode::CONFLICT,
"Repository already exists".to_string(),
)
})?;
Ok(Json(ApiResponse {
data: repo,
total: None,
page: None,
}))
}
#[tracing::instrument(skip_all, fields(repo_id = %id))]
pub async fn update_repository(
Extension(agent): AgentExt,
tenant: TenantCtx,
Path(id): Path<String>,
Json(req): Json<UpdateRepositoryRequest>,
) -> Result<Json<serde_json::Value>, StatusCode> {
let oid = mongodb::bson::oid::ObjectId::parse_str(&id).map_err(|_| StatusCode::BAD_REQUEST)?;
let db = tenant_db(&agent, &tenant).await?;
let mut set_doc = doc! { "updated_at": mongodb::bson::DateTime::now() };
if let Some(name) = &req.name {
set_doc.insert("name", name);
}
if let Some(branch) = &req.default_branch {
set_doc.insert("default_branch", branch);
}
if let Some(token) = &req.auth_token {
set_doc.insert("auth_token", token);
}
if let Some(username) = &req.auth_username {
set_doc.insert("auth_username", username);
}
if let Some(tracker_type) = &req.tracker_type {
set_doc.insert("tracker_type", tracker_type.to_string());
}
if let Some(owner) = &req.tracker_owner {
set_doc.insert("tracker_owner", owner);
}
if let Some(repo) = &req.tracker_repo {
set_doc.insert("tracker_repo", repo);
}
if let Some(token) = &req.tracker_token {
set_doc.insert("tracker_token", token);
}
if let Some(schedule) = &req.scan_schedule {
set_doc.insert("scan_schedule", schedule);
}
let result = db
.repositories()
.update_one(doc! { "_id": oid }, doc! { "$set": set_doc })
.await
.map_err(|e| {
tracing::warn!("Failed to update repository: {e}");
StatusCode::INTERNAL_SERVER_ERROR
})?;
if result.matched_count == 0 {
return Err(StatusCode::NOT_FOUND);
}
Ok(Json(serde_json::json!({ "status": "updated" })))
}
#[tracing::instrument(skip_all)]
pub async fn get_ssh_public_key(
Extension(agent): AgentExt,
) -> Result<Json<serde_json::Value>, StatusCode> {
let public_path = format!("{}.pub", agent.config.ssh_key_path);
let public_key = std::fs::read_to_string(&public_path).map_err(|_| StatusCode::NOT_FOUND)?;
Ok(Json(serde_json::json!({ "public_key": public_key.trim() })))
}
#[tracing::instrument(skip_all, fields(repo_id = %id))]
pub async fn trigger_scan(
Extension(agent): AgentExt,
tenant: TenantCtx,
Path(id): Path<String>,
) -> Result<Json<serde_json::Value>, StatusCode> {
let agent_clone = (*agent).clone();
let tenant_id = tenant.0.tenant_id.clone();
tokio::spawn(async move {
if let Err(e) = agent_clone
.run_scan(&tenant_id, &id, ScanTrigger::Manual)
.await
{
tracing::error!("Manual scan failed for {id}: {e}");
}
});
Ok(Json(serde_json::json!({ "status": "scan_triggered" })))
}
/// Return the webhook secret for a repository (used by dashboard to display it)
pub async fn get_webhook_config(
Extension(agent): AgentExt,
tenant: TenantCtx,
Path(id): Path<String>,
) -> Result<Json<serde_json::Value>, StatusCode> {
let oid = mongodb::bson::oid::ObjectId::parse_str(&id).map_err(|_| StatusCode::BAD_REQUEST)?;
let db = tenant_db(&agent, &tenant).await?;
let repo = db
.repositories()
.find_one(doc! { "_id": oid })
.await
.map_err(|_| StatusCode::INTERNAL_SERVER_ERROR)?
.ok_or(StatusCode::NOT_FOUND)?;
let tracker_type = repo
.tracker_type
.as_ref()
.map(|t| t.to_string())
.unwrap_or_else(|| "gitea".to_string());
Ok(Json(serde_json::json!({
"webhook_secret": repo.webhook_secret,
"tracker_type": tracker_type,
})))
}
#[tracing::instrument(skip_all, fields(repo_id = %id))]
pub async fn delete_repository(
Extension(agent): AgentExt,
tenant: TenantCtx,
Path(id): Path<String>,
) -> Result<Json<serde_json::Value>, StatusCode> {
let oid = mongodb::bson::oid::ObjectId::parse_str(&id).map_err(|_| StatusCode::BAD_REQUEST)?;
let db = tenant_db(&agent, &tenant).await?;
let db = &db;
// Delete the repository
let result = db
.repositories()
.delete_one(doc! { "_id": oid })
.await
.map_err(|_| StatusCode::INTERNAL_SERVER_ERROR)?;
if result.deleted_count == 0 {
return Err(StatusCode::NOT_FOUND);
}
// Cascade delete all related data
let _ = db.findings().delete_many(doc! { "repo_id": &id }).await;
let _ = db.sbom_entries().delete_many(doc! { "repo_id": &id }).await;
let _ = db.scan_runs().delete_many(doc! { "repo_id": &id }).await;
let _ = db.cve_alerts().delete_many(doc! { "repo_id": &id }).await;
let _ = db
.tracker_issues()
.delete_many(doc! { "repo_id": &id })
.await;
let _ = db.graph_nodes().delete_many(doc! { "repo_id": &id }).await;
let _ = db.graph_edges().delete_many(doc! { "repo_id": &id }).await;
let _ = db.graph_builds().delete_many(doc! { "repo_id": &id }).await;
let _ = db
.impact_analyses()
.delete_many(doc! { "repo_id": &id })
.await;
let _ = db
.code_embeddings()
.delete_many(doc! { "repo_id": &id })
.await;
let _ = db
.embedding_builds()
.delete_many(doc! { "repo_id": &id })
.await;
// Cascade delete DAST targets linked to this repo, and all their downstream data
// (scan runs, findings, pentest sessions, attack chains, messages)
if let Ok(mut cursor) = db.dast_targets().find(doc! { "repo_id": &id }).await {
use futures_util::StreamExt;
while let Some(Ok(target)) = cursor.next().await {
let target_id = target.id.map(|oid| oid.to_hex()).unwrap_or_default();
if !target_id.is_empty() {
cascade_delete_dast_target(db, &target_id).await;
}
}
}
// Also delete pentest sessions linked directly to this repo (not via target)
if let Ok(mut cursor) = db.pentest_sessions().find(doc! { "repo_id": &id }).await {
use futures_util::StreamExt;
while let Some(Ok(session)) = cursor.next().await {
let session_id = session.id.map(|oid| oid.to_hex()).unwrap_or_default();
if !session_id.is_empty() {
let _ = db
.attack_chain_nodes()
.delete_many(doc! { "session_id": &session_id })
.await;
let _ = db
.pentest_messages()
.delete_many(doc! { "session_id": &session_id })
.await;
// Delete DAST findings produced by this session
let _ = db
.dast_findings()
.delete_many(doc! { "session_id": &session_id })
.await;
}
}
}
let _ = db
.pentest_sessions()
.delete_many(doc! { "repo_id": &id })
.await;
Ok(Json(serde_json::json!({ "status": "deleted" })))
}
/// Cascade-delete a DAST target and all its downstream data.
async fn cascade_delete_dast_target(db: &crate::database::Database, target_id: &str) {
// Delete pentest sessions for this target (and their attack chains + messages)
if let Ok(mut cursor) = db
.pentest_sessions()
.find(doc! { "target_id": target_id })
.await
{
use futures_util::StreamExt;
while let Some(Ok(session)) = cursor.next().await {
let session_id = session.id.map(|oid| oid.to_hex()).unwrap_or_default();
if !session_id.is_empty() {
let _ = db
.attack_chain_nodes()
.delete_many(doc! { "session_id": &session_id })
.await;
let _ = db
.pentest_messages()
.delete_many(doc! { "session_id": &session_id })
.await;
let _ = db
.dast_findings()
.delete_many(doc! { "session_id": &session_id })
.await;
}
}
}
let _ = db
.pentest_sessions()
.delete_many(doc! { "target_id": target_id })
.await;
// Delete DAST scan runs and their findings
let _ = db
.dast_findings()
.delete_many(doc! { "target_id": target_id })
.await;
let _ = db
.dast_scan_runs()
.delete_many(doc! { "target_id": target_id })
.await;
// Delete the target itself
if let Ok(oid) = mongodb::bson::oid::ObjectId::parse_str(target_id) {
let _ = db.dast_targets().delete_one(doc! { "_id": oid }).await;
}
}
+1 -1
View File
@@ -282,7 +282,7 @@ pub async fn license_summary(
}
})
.collect();
summaries.sort_by(|a, b| b.count.cmp(&a.count));
summaries.sort_by_key(|s| std::cmp::Reverse(s.count));
Ok(Json(ApiResponse {
data: summaries,
+40 -22
View File
@@ -2,7 +2,6 @@ use axum::routing::{delete, get, patch, post};
use axum::Router;
use crate::api::handlers;
use crate::webhooks;
pub fn build_router() -> Router {
Router::new()
@@ -12,19 +11,36 @@ pub fn build_router() -> Router {
"/api/v1/settings/ssh-public-key",
get(handlers::get_ssh_public_key),
)
.route("/api/v1/repositories", get(handlers::list_repositories))
.route("/api/v1/repositories", post(handlers::add_repository))
// Unified onboarding targets (#131).
.route(
"/api/v1/repositories/{id}/scan",
post(handlers::trigger_scan),
"/api/v1/targets",
get(handlers::onboarding::list_targets).post(handlers::onboarding::create_target),
)
.route(
"/api/v1/repositories/{id}",
delete(handlers::delete_repository).patch(handlers::update_repository),
"/api/v1/targets/{id}",
get(handlers::onboarding::get_target)
.patch(handlers::onboarding::update_target)
.delete(handlers::onboarding::delete_target),
)
.route(
"/api/v1/repositories/{id}/webhook-config",
get(handlers::get_webhook_config),
"/api/v1/targets/{id}/artifacts",
post(handlers::onboarding::add_artifact),
)
.route(
"/api/v1/targets/{id}/artifacts/upload",
post(handlers::onboarding::upload_artifact),
)
.route(
"/api/v1/targets/{id}/applicable-scans",
get(handlers::onboarding::applicable_scans_for_target),
)
.route(
"/api/v1/targets/{id}/detect",
post(handlers::onboarding::detect_target),
)
.route(
"/api/v1/targets/{id}/scan",
post(handlers::onboarding::trigger_target_scan),
)
.route("/api/v1/findings", get(handlers::list_findings))
.route("/api/v1/findings/{id}", get(handlers::get_finding))
@@ -47,6 +63,15 @@ pub fn build_router() -> Router {
.route("/api/v1/sbom/diff", get(handlers::sbom_diff))
.route("/api/v1/issues", get(handlers::list_issues))
.route("/api/v1/scan-runs", get(handlers::list_scan_runs))
// MCP token management (per-tenant API tokens for the MCP server)
.route(
"/api/v1/mcp-tokens",
get(handlers::mcp_tokens::list_mcp_tokens).post(handlers::mcp_tokens::create_mcp_token),
)
.route(
"/api/v1/mcp-tokens/{id}",
delete(handlers::mcp_tokens::revoke_mcp_token),
)
// Graph API endpoints
.route("/api/v1/graph/{repo_id}", get(handlers::graph::get_graph))
.route(
@@ -175,17 +200,10 @@ pub fn build_router() -> Router {
"/api/v1/pentest/stats",
get(handlers::pentest::pentest_stats),
)
// Webhook endpoints (proxied through dashboard)
.route(
"/webhook/github/{repo_id}",
post(webhooks::github::handle_github_webhook),
)
.route(
"/webhook/gitlab/{repo_id}",
post(webhooks::gitlab::handle_gitlab_webhook),
)
.route(
"/webhook/gitea/{repo_id}",
post(webhooks::gitea::handle_gitea_webhook),
)
// Webhook routes live on the separate webhook server (port 3002,
// see crate::webhooks::server). The M7.2-C tenant-in-URL form is
// `/webhook/{tenant_id}/{platform}/{repo_id}` and the handlers
// expect a (tenant_id, repo_id) path tuple. Anything mounting
// them here on the API server would mismatch the handler
// signature, so the routes are not exported.
}
+4 -1
View File
@@ -1,6 +1,6 @@
use std::sync::Arc;
use axum::extract::Request;
use axum::extract::{DefaultBodyLimit, Request};
use axum::http::HeaderValue;
use axum::middleware::Next;
use axum::response::Response;
@@ -74,6 +74,9 @@ pub async fn start_api_server(agent: ComplianceAgent, port: u16) -> Result<(), A
let mut app = routes::build_router()
.merge(admin_router)
// Allow large artifact uploads (PLC .projectarchive, firmware images,
// mobile packages) — axum's default request-body limit is only 2 MiB.
.layer(DefaultBodyLimit::max(512 * 1024 * 1024))
.layer(Extension(Arc::new(agent.clone())))
.layer(CorsLayer::permissive())
.layer(TraceLayer::new_for_http())
+217
View File
@@ -0,0 +1,217 @@
//! Firmware classification via tramiton.
//!
//! tramiton is the company's firmware build/repro engine; we do not re-implement
//! its detection. We depend on `tramiton-core` directly (same-company IP) and run
//! its provider analysis in-process behind a [`FirmwareDetector`] port, mapping
//! tramiton's `BuildPlan` onto a [`TargetType`]. A deterministic
//! [`MockFirmwareDetector`] backs the tests so CI unit tests need neither the
//! tramiton sources nor a real firmware tree.
use std::path::Path;
use compliance_core::error::CoreError;
use compliance_core::models::{DetectedFact, TargetType};
use compliance_core::traits::ClassifierVerdict;
/// A minimal firmware-detection summary, mapped from tramiton's `BuildPlan`.
/// Kept small and tramiton-independent so the classifier and the test mock don't
/// need to construct a full tramiton plan.
#[derive(Debug, Clone, Default)]
pub struct FirmwareDetection {
/// The detecting provider (e.g. `zephyr`, `cmake`, `source-archaeology`).
pub provider: String,
/// Detection confidence: `low` | `medium` | `high`.
pub confidence: String,
/// Build-system label (e.g. `Zephyr`, `ESP-IDF`, `CMake`).
pub build_system: String,
/// Framework, when known (`zephyr`, `esp-idf`, `bare-metal`, ...).
pub framework: Option<String>,
/// Target board / MCU / arch.
pub target: FirmwareTarget,
/// Unresolved gaps in the plan.
pub gaps: Vec<String>,
}
/// The detected firmware target (board / MCU / arch).
#[derive(Debug, Clone, Default)]
pub struct FirmwareTarget {
/// Board name.
pub board: Option<String>,
/// MCU part.
pub mcu: Option<String>,
/// Architecture.
pub arch: Option<String>,
}
/// A source of tramiton firmware detection.
#[allow(async_fn_in_trait)]
pub trait FirmwareDetector: Send + Sync {
/// Run detection over a path, returning a firmware detection if tramiton
/// could form a build plan.
async fn detect(&self, path: &Path) -> Result<Option<FirmwareDetection>, CoreError>;
}
/// Uses `tramiton-core` in-process. The analysis is blocking (filesystem walk),
/// so it runs on a blocking thread to avoid stalling the async runtime. A path
/// with no recognizable build system yields `Ok(None)`.
pub struct TramitonNative;
impl FirmwareDetector for TramitonNative {
async fn detect(&self, path: &Path) -> Result<Option<FirmwareDetection>, CoreError> {
let path = path.to_path_buf();
let plan = tokio::task::spawn_blocking(move || {
let repo = tramiton_core::Repo::new(&path);
tramiton_core::provider::analyze(&repo)
})
.await
.map_err(|e| CoreError::Other(format!("tramiton detect task join error: {e}")))?
.map_err(|e| CoreError::Other(format!("tramiton analyze error: {e}")))?;
Ok(plan.map(|bp| detection_from_build_plan(&bp)))
}
}
/// Map tramiton's `BuildPlan` onto our minimal detection summary.
fn detection_from_build_plan(bp: &tramiton_core::BuildPlan) -> FirmwareDetection {
FirmwareDetection {
provider: bp.provider.clone(),
confidence: bp.confidence.to_string(),
build_system: bp.build_system.label().to_string(),
framework: bp.framework.clone(),
target: FirmwareTarget {
board: bp.target.board.clone(),
mcu: bp.target.mcu.clone(),
arch: bp.target.arch.clone(),
},
gaps: bp.gaps.clone(),
}
}
/// Map a firmware detection to a target type. Framework/build-system signals
/// distinguish RTOS from bare-metal from Yocto.
pub fn detection_to_target_type(det: &FirmwareDetection) -> TargetType {
let framework = det.framework.as_deref().unwrap_or("").to_lowercase();
let build_system = det.build_system.to_lowercase();
let signal = format!("{framework} {build_system} {}", det.provider.to_lowercase());
const RTOS: [&str; 6] = ["zephyr", "esp-idf", "freertos", "nuttx", "riot", "chibios"];
if signal.contains("bitbake") || signal.contains("yocto") || signal.contains("openembedded") {
TargetType::EmbeddedLinuxYocto
} else if RTOS.iter().any(|k| signal.contains(k)) {
TargetType::FirmwareRtos
} else {
TargetType::FirmwareBareMetal
}
}
/// Map tramiton's confidence label to a `[0,1]` score.
fn confidence_score(label: &str) -> f32 {
match label.to_lowercase().as_str() {
"high" => 0.9,
"medium" => 0.6,
"low" => 0.3,
_ => 0.4,
}
}
/// Turn a firmware detection into a classifier verdict, carrying the MCU / board
/// / build-system as facts.
pub fn detection_to_verdict(det: &FirmwareDetection) -> ClassifierVerdict {
let target_type = detection_to_target_type(det);
let mut facts = vec![DetectedFact::new(
"build_system",
det.build_system.clone(),
"tramiton",
)];
if let Some(fw) = &det.framework {
facts.push(DetectedFact::new("framework", fw.clone(), "tramiton"));
}
if let Some(mcu) = &det.target.mcu {
facts.push(DetectedFact::new("mcu", mcu.clone(), "tramiton"));
}
if let Some(board) = &det.target.board {
facts.push(DetectedFact::new("board", board.clone(), "tramiton"));
}
if let Some(arch) = &det.target.arch {
facts.push(DetectedFact::new("arch", arch.clone(), "tramiton"));
}
ClassifierVerdict {
target_type,
confidence: confidence_score(&det.confidence),
facts,
rationale: format!(
"tramiton detected build system '{}'{}",
det.build_system,
det.framework
.as_ref()
.map(|f| format!(" (framework {f})"))
.unwrap_or_default()
),
}
}
/// A deterministic [`FirmwareDetector`] for tests — returns a preset detection.
pub struct MockFirmwareDetector {
/// The detection to return (or `None` for "no detection").
pub detection: Option<FirmwareDetection>,
}
impl FirmwareDetector for MockFirmwareDetector {
async fn detect(&self, _path: &Path) -> Result<Option<FirmwareDetection>, CoreError> {
Ok(self.detection.clone())
}
}
#[cfg(test)]
#[allow(clippy::expect_used, clippy::unwrap_used)]
mod tests {
use super::*;
fn detection(build_system: &str, framework: Option<&str>) -> FirmwareDetection {
FirmwareDetection {
provider: build_system.to_string(),
confidence: "high".to_string(),
build_system: build_system.to_string(),
framework: framework.map(|s| s.to_string()),
target: FirmwareTarget {
mcu: Some("stm32f429".to_string()),
..Default::default()
},
gaps: Vec::new(),
}
}
#[test]
fn zephyr_maps_to_rtos() {
assert_eq!(
detection_to_target_type(&detection("zephyr", Some("zephyr"))),
TargetType::FirmwareRtos
);
}
#[test]
fn bare_cmake_maps_to_bare_metal() {
assert_eq!(
detection_to_target_type(&detection("cmake", Some("bare-metal"))),
TargetType::FirmwareBareMetal
);
}
#[test]
fn bitbake_maps_to_yocto() {
assert_eq!(
detection_to_target_type(&detection("bitbake", None)),
TargetType::EmbeddedLinuxYocto
);
}
#[test]
fn verdict_carries_mcu_fact_and_confidence() {
let v = detection_to_verdict(&detection("esp-idf", Some("esp-idf")));
assert_eq!(v.target_type, TargetType::FirmwareRtos);
assert!((v.confidence - 0.9).abs() < f32::EPSILON);
assert!(v
.facts
.iter()
.any(|f| f.key == "mcu" && f.value == "stm32f429"));
}
}
+357
View File
@@ -0,0 +1,357 @@
//! Heuristic target-type classification from artifact kinds and source markers.
//!
//! Complements the tramiton firmware detector: this handles web / backend /
//! mobile / desktop / PLC by sniffing manifest files and file extensions in the
//! ingested code trees, plus strong priors from the artifact kinds themselves
//! (a PLC-project artifact is a PLC target; an `.ipa` is an iOS app).
use std::collections::HashSet;
use std::fs;
use std::path::Path;
use compliance_core::error::CoreError;
use compliance_core::models::{ArtifactKind, DetectedFact, TargetType};
use compliance_core::traits::{ClassificationInput, ClassifierVerdict, TargetClassifier};
/// Max directory depth scanned for marker files.
const SCAN_DEPTH: usize = 2;
/// Markers collected from a code tree.
#[derive(Default)]
struct Markers {
files: HashSet<String>,
dirs: HashSet<String>,
exts: HashSet<String>,
}
impl Markers {
fn has_file(&self, name: &str) -> bool {
self.files.contains(name)
}
fn has_ext(&self, ext: &str) -> bool {
self.exts.contains(ext)
}
fn any_dir_ends_with(&self, suffix: &str) -> bool {
self.dirs.iter().any(|d| d.ends_with(suffix))
}
}
/// Recursively collect marker file/dir/extension names up to [`SCAN_DEPTH`].
fn collect_markers(root: &Path) -> Markers {
let mut m = Markers::default();
scan_dir(root, 0, &mut m);
m
}
fn scan_dir(dir: &Path, depth: usize, m: &mut Markers) {
let Ok(entries) = fs::read_dir(dir) else {
return;
};
for entry in entries.flatten() {
let path = entry.path();
let name = entry.file_name().to_string_lossy().to_lowercase();
if path.is_dir() {
m.dirs.insert(name);
if depth < SCAN_DEPTH {
scan_dir(&path, depth + 1, m);
}
} else {
if let Some(ext) = path.extension() {
m.exts.insert(ext.to_string_lossy().to_lowercase());
}
m.files.insert(name);
}
}
}
/// Whether a `package.json` at `root` looks like a front-end app.
fn package_json_is_frontend(root: &Path) -> bool {
let Ok(content) = fs::read_to_string(root.join("package.json")) else {
return false;
};
let c = content.to_lowercase();
["react", "next", "vue", "@angular", "svelte", "vite"]
.iter()
.any(|f| c.contains(f))
}
/// The heuristic classifier: artifact-kind priors + source-tree markers.
pub struct HeuristicClassifier;
impl HeuristicClassifier {
/// Verdicts from the artifact kinds alone (no filesystem needed).
fn kind_priors(&self, input: &ClassificationInput<'_>) -> Vec<ClassifierVerdict> {
let mut out = Vec::new();
for a in input.artifacts {
let lower = a.source_ref.to_lowercase();
match a.kind {
ArtifactKind::PlcProject => out.push(verdict(
TargetType::PlcSps,
0.85,
"PLC project artifact",
vec![],
)),
ArtifactKind::MobilePackage => {
let (tt, why) = if lower.ends_with(".ipa") {
(TargetType::IosApp, "iOS package (.ipa)")
} else {
(TargetType::AndroidApp, "Android package (.apk/.aab)")
};
out.push(verdict(tt, 0.85, why, vec![]));
}
ArtifactKind::ContainerImage => out.push(verdict(
TargetType::BackendService,
0.4,
"container image",
vec![],
)),
ArtifactKind::FirmwareImage => out.push(verdict(
TargetType::FirmwareBareMetal,
0.35,
"firmware image (pending tramiton detection)",
vec![],
)),
ArtifactKind::LiveUrl if input.artifacts.len() == 1 => {
out.push(verdict(TargetType::WebApp, 0.3, "live URL only", vec![]))
}
_ => {}
}
}
out
}
/// Verdicts from scanning the ingested code trees for manifest markers.
fn source_verdicts(&self, input: &ClassificationInput<'_>) -> Vec<ClassifierVerdict> {
let mut out = Vec::new();
for a in input.artifacts {
if !matches!(a.kind, ArtifactKind::GitRepo | ArtifactKind::SourceArchive) {
continue;
}
let Some(path) = input.working_paths.get(&a.id) else {
continue;
};
let m = collect_markers(path);
// Mobile (checked first — strongest signal).
if m.has_file("androidmanifest.xml") || m.has_ext("apk") || m.has_ext("aab") {
out.push(verdict(
TargetType::AndroidApp,
0.8,
"Android manifest / gradle",
facts_lang("kotlin/java"),
));
}
if m.any_dir_ends_with(".xcodeproj")
|| m.has_file("info.plist")
|| m.has_file("podfile")
|| m.has_ext("ipa")
{
out.push(verdict(
TargetType::IosApp,
0.8,
"Xcode project / Info.plist",
facts_lang("swift/objc"),
));
}
// Desktop.
if m.has_ext("sln")
|| m.has_ext("csproj")
|| m.has_ext("vcxproj")
|| m.has_ext("desktop")
{
out.push(verdict(
TargetType::DesktopApp,
0.7,
"desktop project files",
facts_lang("dotnet/native"),
));
}
// PLC.
if m.has_ext("st") {
out.push(verdict(
TargetType::PlcSps,
0.8,
"Structured Text sources",
facts_lang("iec-61131-3"),
));
}
// Web vs backend from package.json.
if m.has_file("package.json") {
if package_json_is_frontend(path) {
out.push(verdict(
TargetType::WebApp,
0.65,
"package.json with a front-end framework",
facts_lang("javascript"),
));
} else {
out.push(verdict(
TargetType::BackendService,
0.55,
"package.json (no front-end framework)",
facts_lang("javascript"),
));
}
}
// Backend languages.
for (file, lang) in [
("cargo.toml", "rust"),
("go.mod", "go"),
("pom.xml", "java"),
("requirements.txt", "python"),
("pyproject.toml", "python"),
] {
if m.has_file(file) {
out.push(verdict(
TargetType::BackendService,
0.6,
"backend build manifest",
facts_lang(lang),
));
}
}
// Container-only.
if m.has_file("dockerfile") && out.is_empty() {
out.push(verdict(
TargetType::BackendService,
0.4,
"Dockerfile",
facts_lang("container"),
));
}
}
out
}
}
impl TargetClassifier for HeuristicClassifier {
fn name(&self) -> &str {
"heuristic"
}
async fn classify(
&self,
input: &ClassificationInput<'_>,
) -> Result<Vec<ClassifierVerdict>, CoreError> {
let mut out = self.kind_priors(input);
out.extend(self.source_verdicts(input));
Ok(out)
}
}
fn verdict(
target_type: TargetType,
confidence: f32,
rationale: &str,
facts: Vec<DetectedFact>,
) -> ClassifierVerdict {
ClassifierVerdict {
target_type,
confidence,
facts,
rationale: rationale.to_string(),
}
}
fn facts_lang(lang: &str) -> Vec<DetectedFact> {
vec![DetectedFact::new("language", lang, "heuristic")]
}
#[cfg(test)]
#[allow(clippy::expect_used, clippy::unwrap_used)]
mod tests {
use super::*;
use compliance_core::models::Artifact;
use std::collections::HashMap;
use std::path::PathBuf;
struct Scratch(PathBuf);
impl Scratch {
fn new() -> Self {
let p = std::env::temp_dir().join(format!("cs-classify-{}", uuid::Uuid::new_v4()));
fs::create_dir_all(&p).expect("mkdir");
Self(p)
}
}
impl Drop for Scratch {
fn drop(&mut self) {
let _ = fs::remove_dir_all(&self.0);
}
}
async fn classify_tree(setup: impl FnOnce(&Path)) -> Vec<ClassifierVerdict> {
let scratch = Scratch::new();
setup(&scratch.0);
let artifact = Artifact::git_repo("https://git/x", "main");
let mut wp = HashMap::new();
wp.insert(artifact.id.clone(), scratch.0.clone());
let artifacts = vec![artifact];
let input = ClassificationInput {
artifacts: &artifacts,
working_paths: &wp,
description: None,
};
HeuristicClassifier
.classify(&input)
.await
.expect("classify")
}
#[tokio::test]
async fn frontend_package_json_is_webapp() {
let v = classify_tree(|root| {
fs::write(
root.join("package.json"),
r#"{"dependencies":{"react":"18"}}"#,
)
.unwrap();
})
.await;
assert!(v.iter().any(|x| x.target_type == TargetType::WebApp));
}
#[tokio::test]
async fn cargo_toml_is_backend() {
let v = classify_tree(|root| {
fs::write(root.join("Cargo.toml"), "[package]\nname='x'").unwrap();
})
.await;
assert!(v
.iter()
.any(|x| x.target_type == TargetType::BackendService));
}
#[tokio::test]
async fn android_manifest_is_android() {
let v = classify_tree(|root| {
fs::write(root.join("AndroidManifest.xml"), "<manifest/>").unwrap();
})
.await;
assert!(v.iter().any(|x| x.target_type == TargetType::AndroidApp));
}
#[tokio::test]
async fn structured_text_is_plc() {
let v = classify_tree(|root| {
fs::write(root.join("main.st"), "PROGRAM main END_PROGRAM").unwrap();
})
.await;
assert!(v.iter().any(|x| x.target_type == TargetType::PlcSps));
}
#[tokio::test]
async fn ipa_artifact_prior_is_ios() {
let artifacts = vec![Artifact::mobile_package("app.ipa")];
let wp = HashMap::new();
let input = ClassificationInput {
artifacts: &artifacts,
working_paths: &wp,
description: None,
};
let v = HeuristicClassifier
.classify(&input)
.await
.expect("classify");
assert!(v.iter().any(|x| x.target_type == TargetType::IosApp));
}
}
+226
View File
@@ -0,0 +1,226 @@
//! Target classification.
//!
//! Runs the classifier registry over a target's artifacts and their ingested
//! working paths, then merges and ranks the verdicts into a [`Classification`].
//! The registry is the heuristic classifier (artifact kinds + source markers)
//! plus the tramiton firmware detector (behind a [`FirmwareDetector`] port).
mod firmware;
mod language;
pub use firmware::{
FirmwareDetection, FirmwareDetector, FirmwareTarget, MockFirmwareDetector, TramitonNative,
};
pub use language::HeuristicClassifier;
use std::collections::HashMap;
use std::path::PathBuf;
use compliance_core::error::CoreError;
use compliance_core::models::{
ArtifactKind, Classification, DetectedFact, OnboardedTarget, TargetType, TargetTypeCandidate,
};
use compliance_core::traits::{ClassificationInput, ClassifierVerdict, TargetClassifier};
use firmware::detection_to_verdict;
/// Classify a target from its artifacts and their ingested working paths, using
/// the heuristic classifier plus the tramiton firmware detector. Verdicts are
/// merged (max confidence per target type) and ranked into a [`Classification`].
pub async fn classify_target<D: FirmwareDetector>(
target: &OnboardedTarget,
working_paths: &HashMap<String, PathBuf>,
firmware_detector: &D,
) -> Result<Classification, CoreError> {
let input = ClassificationInput {
artifacts: &target.artifacts,
working_paths,
description: target.description.as_deref(),
};
let mut verdicts = Vec::new();
let mut detected_by = Vec::new();
let heuristic = HeuristicClassifier.classify(&input).await?;
if !heuristic.is_empty() {
detected_by.push("heuristic".to_string());
}
verdicts.extend(heuristic);
// Tramiton firmware detection over firmware / code working paths.
let mut tramiton_used = false;
for artifact in &target.artifacts {
if !matches!(
artifact.kind,
ArtifactKind::FirmwareImage | ArtifactKind::GitRepo | ArtifactKind::SourceArchive
) {
continue;
}
let Some(path) = working_paths.get(&artifact.id) else {
continue;
};
if let Some(detection) = firmware_detector.detect(path).await? {
verdicts.push(detection_to_verdict(&detection));
tramiton_used = true;
}
}
if tramiton_used {
detected_by.push("tramiton".to_string());
}
Ok(rank(verdicts, detected_by, target.target_type))
}
/// Merge verdicts by target type (keeping the max confidence and its rationale),
/// dedupe facts, rank by descending confidence, and assemble a [`Classification`].
/// Falls back to the declared type when no verdict is produced.
fn rank(
verdicts: Vec<ClassifierVerdict>,
detected_by: Vec<String>,
fallback: TargetType,
) -> Classification {
let mut best: HashMap<TargetType, (f32, String)> = HashMap::new();
let mut facts: Vec<DetectedFact> = Vec::new();
for verdict in verdicts {
for fact in verdict.facts {
if !facts
.iter()
.any(|e| e.key == fact.key && e.value == fact.value)
{
facts.push(fact);
}
}
let entry = best
.entry(verdict.target_type)
.or_insert((0.0, String::new()));
if verdict.confidence > entry.0 {
*entry = (verdict.confidence, verdict.rationale);
}
}
let mut candidates: Vec<TargetTypeCandidate> = best
.into_iter()
.map(
|(target_type, (confidence, rationale))| TargetTypeCandidate {
target_type,
confidence,
rationale,
},
)
.collect();
// Descending confidence; ties broken by type name for deterministic ordering.
candidates.sort_by(|a, b| {
b.confidence
.partial_cmp(&a.confidence)
.unwrap_or(std::cmp::Ordering::Equal)
.then_with(|| a.target_type.to_string().cmp(&b.target_type.to_string()))
});
let suggested = candidates
.first()
.map(|c| c.target_type)
.unwrap_or(fallback);
Classification {
suggested,
candidates,
facts,
detected_by,
detected_at: chrono::Utc::now(),
confirmed: false,
}
}
#[cfg(test)]
#[allow(clippy::expect_used, clippy::unwrap_used)]
mod tests {
use super::*;
use compliance_core::models::Artifact;
use std::fs;
use std::path::Path;
struct Scratch(PathBuf);
impl Scratch {
fn new() -> Self {
let p = std::env::temp_dir().join(format!("cs-classify-mod-{}", uuid::Uuid::new_v4()));
fs::create_dir_all(&p).expect("mkdir");
Self(p)
}
}
impl Drop for Scratch {
fn drop(&mut self) {
let _ = fs::remove_dir_all(&self.0);
}
}
fn no_firmware() -> MockFirmwareDetector {
MockFirmwareDetector { detection: None }
}
#[tokio::test]
async fn backend_repo_classifies_as_backend() {
let scratch = Scratch::new();
fs::write(scratch.0.join("go.mod"), "module x").unwrap();
let artifact = Artifact::git_repo("https://git/x", "main");
let mut wp = HashMap::new();
wp.insert(artifact.id.clone(), scratch.0.clone());
let mut target = OnboardedTarget::new("x".to_string(), TargetType::WebApp);
target.artifacts.push(artifact);
let c = classify_target(&target, &wp, &no_firmware())
.await
.expect("classify");
assert_eq!(c.suggested, TargetType::BackendService);
assert!(c.detected_by.contains(&"heuristic".to_string()));
assert!(!c.confirmed);
}
#[tokio::test]
async fn firmware_detector_verdict_ranks_top() {
let scratch = Scratch::new();
fs::write(scratch.0.join("fw.bin"), b"x").unwrap();
let artifact =
Artifact::firmware_image(scratch.0.join("fw.bin").to_string_lossy().to_string());
let mut wp = HashMap::new();
wp.insert(artifact.id.clone(), scratch.0.clone());
let mut target = OnboardedTarget::new("fw".to_string(), TargetType::FirmwareBareMetal);
target.artifacts.push(artifact);
let detector = MockFirmwareDetector {
detection: Some(FirmwareDetection {
provider: "zephyr".to_string(),
confidence: "high".to_string(),
build_system: "zephyr".to_string(),
framework: Some("zephyr".to_string()),
target: FirmwareTarget {
mcu: Some("nrf52840".to_string()),
..Default::default()
},
gaps: vec![],
}),
};
let c = classify_target(&target, &wp, &detector)
.await
.expect("classify");
// tramiton's high-confidence RTOS verdict beats the weak firmware prior.
assert_eq!(c.suggested, TargetType::FirmwareRtos);
assert!(c.detected_by.contains(&"tramiton".to_string()));
assert!(c.facts.iter().any(|f| f.key == "mcu"));
}
#[tokio::test]
async fn no_signal_falls_back_to_declared_type() {
let scratch = Scratch::new();
let _ = Path::new(&scratch.0);
let target = OnboardedTarget::new("empty".to_string(), TargetType::DesktopApp);
let wp = HashMap::new();
let c = classify_target(&target, &wp, &no_firmware())
.await
.expect("classify");
assert_eq!(c.suggested, TargetType::DesktopApp);
assert!(c.candidates.is_empty());
}
}
+26
View File
@@ -1,3 +1,4 @@
use compliance_core::config::PlcRuntimeConfig;
use compliance_core::AgentConfig;
use secrecy::SecretString;
@@ -45,6 +46,8 @@ pub fn load_config() -> Result<AgentConfig, AgentError> {
.unwrap_or_else(|| "0 0 * * * *".to_string()),
git_clone_base_path: env_var_opt("GIT_CLONE_BASE_PATH")
.unwrap_or_else(|| "/tmp/compliance-scanner/repos".to_string()),
artifact_store_base_path: env_var_opt("ARTIFACT_STORE_BASE_PATH")
.unwrap_or_else(|| "/data/compliance-scanner/artifacts".to_string()),
ssh_key_path: env_var_opt("SSH_KEY_PATH")
.unwrap_or_else(|| "/data/compliance-scanner/ssh/id_ed25519".to_string()),
keycloak_url: env_var_opt("KEYCLOAK_URL"),
@@ -61,5 +64,28 @@ pub fn load_config() -> Result<AgentConfig, AgentError> {
pentest_imap_password: env_secret_opt("PENTEST_IMAP_PASSWORD"),
admin_api_token: env_secret_opt("ADMIN_API_TOKEN"),
tenant_registry_url: env_var_opt("TENANT_REGISTRY_URL"),
plc_runtime: load_plc_runtime_config(),
})
}
/// Build the ephemeral soft-PLC provisioning config from the environment,
/// falling back to [`PlcRuntimeConfig::default`] for any unset knob. Disabled
/// unless `PLC_RUNTIME_ENABLED` is truthy — it requires Docker access.
fn load_plc_runtime_config() -> PlcRuntimeConfig {
let d = PlcRuntimeConfig::default();
PlcRuntimeConfig {
enabled: env_var_opt("PLC_RUNTIME_ENABLED")
.map(|v| v == "1" || v.eq_ignore_ascii_case("true"))
.unwrap_or(d.enabled),
image: env_var_opt("PLC_RUNTIME_IMAGE").unwrap_or(d.image),
network: env_var_opt("PLC_RUNTIME_NETWORK").unwrap_or(d.network),
memory: env_var_opt("PLC_RUNTIME_MEMORY").unwrap_or(d.memory),
cpus: env_var_opt("PLC_RUNTIME_CPUS").unwrap_or(d.cpus),
max_lifetime_secs: env_var_opt("PLC_RUNTIME_MAX_LIFETIME_SECS")
.and_then(|v| v.parse().ok())
.unwrap_or(d.max_lifetime_secs),
openplc_user: env_var_opt("PLC_RUNTIME_OPENPLC_USER").unwrap_or(d.openplc_user),
openplc_password: env_secret_opt("PLC_RUNTIME_OPENPLC_PASSWORD")
.unwrap_or(d.openplc_password),
}
}
+80 -14
View File
@@ -141,6 +141,25 @@ impl DatabasePool {
&self.client
}
/// Cross-tenant admin database used by features that intentionally
/// span tenants (today: MCP bearer tokens — each token row carries
/// a `tenant_id` and the MCP server reads them to route requests).
///
/// The name `<db_prefix>__admin` (double underscore) is reserved —
/// the sanitizer never produces it for a normal tenant DB because
/// the natural format is `<db_prefix>_<sanitized_tenant_id>` (one
/// underscore) and tenant_ids would have to start with `_admin` to
/// collide. New tenant provisioning should reject such ids.
pub fn admin_db(&self) -> mongodb::Database {
self.client.database(&self.admin_db_name())
}
/// Name of the admin database — public so tests / operators can
/// drop it via the raw client.
pub fn admin_db_name(&self) -> String {
format!("{}__admin", self.db_prefix)
}
/// List every Mongo database currently belonging to this pool,
/// identified by the `<db_prefix>_` prefix. The result is the raw
/// database names — opening one for offboarding/cleanup goes
@@ -160,6 +179,23 @@ impl DatabasePool {
.collect())
}
/// Tenant ids for every provisioned tenant database, derived by stripping
/// the `<prefix>_` from the database names. Skips the admin database
/// (`<prefix>__admin`). Hash-fallback names (very long tenant_ids) are lost
/// at the cluster level and cannot be recovered here — in practice tenant
/// ids are UUIDs and never hit that path. Used by the migration CLI's
/// `--all` mode.
pub async fn list_tenant_ids(&self) -> Result<Vec<String>, AgentError> {
let prefix = format!("{}_", self.db_prefix);
Ok(self
.list_tenant_db_names()
.await?
.into_iter()
.filter_map(|n| n.strip_prefix(&prefix).map(str::to_string))
.filter(|id| !id.starts_with('_'))
.collect())
}
/// Drop the database for a specific tenant. Used by GDPR delete
/// and tenant offboarding. Idempotent — dropping a non-existent
/// database is a no-op at the driver level.
@@ -213,16 +249,6 @@ impl Database {
}
pub async fn ensure_indexes(&self) -> Result<(), AgentError> {
// repositories: unique git_url
self.repositories()
.create_index(
IndexModel::builder()
.keys(doc! { "git_url": 1 })
.options(IndexOptions::builder().unique(true).build())
.build(),
)
.await?;
// findings: unique fingerprint
self.findings()
.create_index(
@@ -409,14 +435,40 @@ impl Database {
)
.await?;
// onboarded_targets: multikey on artifact source ref (webhook + dedupe
// lookup). Non-unique — "one git URL per tenant" is enforced in the
// create handler, since a unique multikey index on an array field has
// null-collision caveats.
self.onboarded_targets()
.create_index(
IndexModel::builder()
.keys(doc! { "artifacts.source_ref": 1 })
.build(),
)
.await?;
// onboarded_targets: multikey on artifact kind
self.onboarded_targets()
.create_index(
IndexModel::builder()
.keys(doc! { "artifacts.kind": 1 })
.build(),
)
.await?;
// onboarded_targets: target_type filter
self.onboarded_targets()
.create_index(
IndexModel::builder()
.keys(doc! { "target_type": 1 })
.build(),
)
.await?;
tracing::info!("Database indexes ensured");
Ok(())
}
pub fn repositories(&self) -> Collection<TrackedRepository> {
self.inner.collection("repositories")
}
pub fn findings(&self) -> Collection<Finding> {
self.inner.collection("findings")
}
@@ -465,6 +517,20 @@ impl Database {
self.inner.collection("dast_targets")
}
/// The unified onboarding targets that replace `repositories` and
/// `dast_targets`. Ids are preserved from the legacy collections during
/// migration so downstream `repo_id` / `target_id` references keep resolving.
pub fn onboarded_targets(&self) -> Collection<OnboardedTarget> {
self.inner.collection("onboarded_targets")
}
/// A typed handle to an arbitrary collection by name. For bookkeeping
/// collections without a dedicated model (e.g. `schema_migrations`,
/// `onboarding_migration_log`).
pub fn collection_named<T: Send + Sync>(&self, name: &str) -> Collection<T> {
self.inner.collection(name)
}
pub fn dast_scan_runs(&self) -> Collection<DastScanRun> {
self.inner.collection("dast_scan_runs")
}
+154
View File
@@ -0,0 +1,154 @@
//! Content-addressed blob storage and archive extraction for ingest.
//!
//! Blobs are stored at `<base>/blobs/<sha[0:2]>/<sha>` and deduplicated by
//! digest; per-run working directories live under `<base>/work/`.
use std::fs::{self, File};
use std::io::{self, Read};
use std::path::{Path, PathBuf};
use sha2::{Digest, Sha256};
use crate::error::AgentError;
/// Read buffer size for streaming hashes/copies (64 KiB).
const BUF_LEN: usize = 64 * 1024;
/// Stream-hash a file with SHA-256, returning the lowercase-hex digest and the
/// byte length. Streams so large firmware images never load fully into memory.
pub fn hash_file(path: &Path) -> Result<(String, u64), AgentError> {
let mut file = File::open(path)?;
let mut hasher = Sha256::new();
let mut buf = [0u8; BUF_LEN];
let mut total: u64 = 0;
loop {
let n = file.read(&mut buf)?;
if n == 0 {
break;
}
hasher.update(&buf[..n]);
total += n as u64;
}
Ok((hex::encode(hasher.finalize()), total))
}
/// Copy `src` into the content-addressed blob store under `base`, returning the
/// stored path. Idempotent: an already-present blob is not rewritten.
pub fn store_file(base: &Path, src: &Path, sha: &str) -> Result<PathBuf, AgentError> {
if sha.len() < 2 {
return Err(AgentError::Other(format!("invalid content hash '{sha}'")));
}
let dir = base.join("blobs").join(&sha[0..2]);
fs::create_dir_all(&dir)?;
let dest = dir.join(sha);
if !dest.exists() {
fs::copy(src, &dest)?;
}
Ok(dest)
}
/// Extract a zip archive into `dest` (created if needed). `enclosed_name`
/// sanitizes each entry path, so this is safe against zip-slip traversal.
pub fn extract_zip(archive: &Path, dest: &Path) -> Result<(), AgentError> {
let file = File::open(archive)?;
let mut zip =
zip::ZipArchive::new(file).map_err(|e| AgentError::Other(format!("open zip: {e}")))?;
fs::create_dir_all(dest)?;
for i in 0..zip.len() {
let mut entry = zip
.by_index(i)
.map_err(|e| AgentError::Other(format!("read zip entry: {e}")))?;
// `enclosed_name` returns `None` for traversal-unsafe paths — skip them.
let Some(rel) = entry.enclosed_name() else {
continue;
};
let out = dest.join(rel);
if entry.is_dir() {
fs::create_dir_all(&out)?;
} else {
if let Some(parent) = out.parent() {
fs::create_dir_all(parent)?;
}
let mut outfile = File::create(&out)?;
io::copy(&mut entry, &mut outfile)?;
}
}
Ok(())
}
/// The working directory for one artifact of a target: `<base>/work/<target>/<artifact>`.
pub fn work_dir(base: &Path, target_id: &str, artifact_id: &str) -> PathBuf {
base.join("work").join(target_id).join(artifact_id)
}
#[cfg(test)]
#[allow(clippy::expect_used, clippy::unwrap_used)]
mod tests {
use super::*;
/// A unique scratch directory, removed on drop.
struct Scratch(PathBuf);
impl Scratch {
fn new() -> Self {
let p = std::env::temp_dir().join(format!("cs-ingest-{}", uuid::Uuid::new_v4()));
fs::create_dir_all(&p).expect("mkdir scratch");
Self(p)
}
fn path(&self) -> &Path {
&self.0
}
}
impl Drop for Scratch {
fn drop(&mut self) {
let _ = fs::remove_dir_all(&self.0);
}
}
#[test]
fn hash_is_stable_and_reports_size() {
let dir = Scratch::new();
let f = dir.path().join("a.bin");
fs::write(&f, b"hello world").expect("write");
let (sha, size) = hash_file(&f).expect("hash");
assert_eq!(size, 11);
// Known SHA-256 of "hello world".
assert_eq!(
sha,
"b94d27b9934d3e08a52e52d7da7dabfac484efe37a5380ee9088f7ace2efcde9"
);
}
#[test]
fn store_is_content_addressed_and_idempotent() {
let base = Scratch::new();
let src = base.path().join("src.bin");
fs::write(&src, b"payload").expect("write");
let (sha, _) = hash_file(&src).expect("hash");
let p1 = store_file(base.path(), &src, &sha).expect("store");
let p2 = store_file(base.path(), &src, &sha).expect("store again");
assert_eq!(p1, p2);
assert!(p1.ends_with(&sha));
assert!(p1.starts_with(base.path().join("blobs").join(&sha[0..2])));
assert_eq!(fs::read(&p1).expect("read"), b"payload");
}
#[test]
fn extract_zip_writes_entries() {
let base = Scratch::new();
let archive = base.path().join("a.zip");
{
let file = File::create(&archive).expect("create");
let mut w = zip::ZipWriter::new(file);
let opts: zip::write::SimpleFileOptions = Default::default();
w.start_file("dir/hello.txt", opts).expect("start");
io::Write::write_all(&mut w, b"hi").expect("write");
w.finish().expect("finish");
}
let dest = base.path().join("out");
extract_zip(&archive, &dest).expect("extract");
assert_eq!(
fs::read_to_string(dest.join("dir/hello.txt")).expect("read"),
"hi"
);
}
}
+416
View File
@@ -0,0 +1,416 @@
//! Artifact ingest.
//!
//! Normalizes each [`Artifact`] on an [`OnboardedTarget`] into a local working
//! path plus recorded metadata (content hash, size, discovered facts) that the
//! classifier and scanners consume. Every blob is SHA-256 hashed — that digest
//! is also the reconciliation key against sibling products (a firmware sha256
//! matches tramiton's `Artifact.sha256`).
mod blob;
use std::collections::HashMap;
use std::path::{Path, PathBuf};
use compliance_core::models::{Artifact, ArtifactKind, DetectedFact, OnboardedTarget};
use compliance_core::AgentConfig;
use crate::error::AgentError;
use crate::pipeline::git::{GitOps, RepoCredentials};
/// The paths and identifiers an ingest needs. Decoupled from the full
/// [`AgentConfig`] so ingest is testable without a complete config.
pub struct IngestContext<'a> {
/// Base directory for content-addressed blobs and working dirs.
pub artifact_store_base: &'a Path,
/// Base directory for git clones.
pub git_clone_base: &'a str,
/// Default SSH key path (used when an artifact provides none).
pub ssh_key_path: &'a str,
/// The id of the target these artifacts belong to (namespaces working dirs).
pub target_id: &'a str,
}
impl<'a> IngestContext<'a> {
/// Build an ingest context from the agent config for a given target.
pub fn from_config(config: &'a AgentConfig, target_id: &'a str) -> Self {
Self {
artifact_store_base: Path::new(&config.artifact_store_base_path),
git_clone_base: &config.git_clone_base_path,
ssh_key_path: &config.ssh_key_path,
target_id,
}
}
}
/// The result of ingesting one artifact.
pub struct IngestedArtifact {
/// The artifact this corresponds to ([`Artifact::id`]).
pub artifact_id: String,
/// The artifact kind.
pub kind: ArtifactKind,
/// Local working path (clone dir, extracted dir, or blob file). `None` for
/// artifacts with no on-disk form (live URL, plaintext, container ref).
pub working_path: Option<PathBuf>,
/// SHA-256 of the content (blobs) or git head SHA (git repos).
pub content_hash: Option<String>,
/// Stored blob size in bytes, when applicable.
pub size_bytes: Option<u64>,
/// Facts discovered during ingest.
pub facts: Vec<DetectedFact>,
}
/// All ingested artifacts for a target, keyed by artifact id.
pub struct IngestSet {
/// The ingested artifacts, keyed by [`Artifact::id`].
pub by_artifact: HashMap<String, IngestedArtifact>,
}
impl IngestSet {
/// The working paths of every ingested artifact that has one — the input the
/// classifier expects.
pub fn working_paths(&self) -> HashMap<String, PathBuf> {
self.by_artifact
.iter()
.filter_map(|(id, a)| a.working_path.clone().map(|p| (id.clone(), p)))
.collect()
}
/// The ingest result for a specific artifact.
pub fn get(&self, artifact_id: &str) -> Option<&IngestedArtifact> {
self.by_artifact.get(artifact_id)
}
}
/// Ingest every artifact on a target.
pub fn ingest_all(
target: &OnboardedTarget,
ctx: &IngestContext<'_>,
) -> Result<IngestSet, AgentError> {
let mut by_artifact = HashMap::new();
for artifact in &target.artifacts {
let ingested = ingest_artifact(artifact, ctx)?;
by_artifact.insert(artifact.id.clone(), ingested);
}
Ok(IngestSet { by_artifact })
}
/// Ingest a single artifact, dispatching on its kind.
pub fn ingest_artifact(
artifact: &Artifact,
ctx: &IngestContext<'_>,
) -> Result<IngestedArtifact, AgentError> {
match artifact.kind {
ArtifactKind::GitRepo => ingest_git(artifact, ctx),
ArtifactKind::SourceArchive | ArtifactKind::MobilePackage | ArtifactKind::PlcProject => {
ingest_blob(artifact, ctx, true)
}
ArtifactKind::FirmwareImage => ingest_blob(artifact, ctx, false),
ArtifactKind::ContainerImage => Ok(metadata_only(
artifact,
DetectedFact::new("container_ref", artifact.source_ref.as_str(), "ingest"),
)),
ArtifactKind::LiveUrl => Ok(metadata_only(
artifact,
DetectedFact::new("live_url", artifact.source_ref.as_str(), "ingest"),
)),
ArtifactKind::PlaintextDescription => Ok(metadata_only(
artifact,
DetectedFact::new(
"description_len",
artifact.source_ref.len().to_string(),
"ingest",
),
)),
}
}
/// Clone (or fetch) a git artifact, recording the head SHA as the content hash.
fn ingest_git(
artifact: &Artifact,
ctx: &IngestContext<'_>,
) -> Result<IngestedArtifact, AgentError> {
let creds = credentials_for(artifact, ctx.ssh_key_path);
let git_ops = GitOps::new(ctx.git_clone_base, creds);
let repo_path = git_ops.clone_or_fetch(&artifact.source_ref, &artifact.id)?;
let head = GitOps::get_head_sha(&repo_path).ok();
Ok(IngestedArtifact {
artifact_id: artifact.id.clone(),
kind: artifact.kind,
working_path: Some(repo_path),
content_hash: head,
size_bytes: None,
facts: Vec::new(),
})
}
/// Store a blob artifact content-addressed. When `extract` is set and the blob
/// is a zip container (source archive, APK/AAB/IPA), also unpack it into a
/// working directory; otherwise the working path is the stored blob.
fn ingest_blob(
artifact: &Artifact,
ctx: &IngestContext<'_>,
extract: bool,
) -> Result<IngestedArtifact, AgentError> {
let base = ctx.artifact_store_base;
let src = local_source(artifact)?;
let (sha, size) = blob::hash_file(&src)?;
let stored = blob::store_file(base, &src, &sha)?;
let mut facts = Vec::new();
let working_path = if extract {
let dest = blob::work_dir(base, ctx.target_id, &artifact.id);
match blob::extract_zip(&stored, &dest) {
Ok(()) => dest,
Err(e) => {
// Not a zip container — this is a single uploaded file (e.g. a
// `.st`/`.xml` PLC project or a `.tar.gz`). The content-addressed
// blob has no extension, so materialize it into a working dir
// under its original name; extension-based scanners (PLC) can then
// discover it and report a readable path.
facts.push(DetectedFact::new(
"archive_unextracted",
e.to_string(),
"ingest",
));
match materialize_single(&stored, &dest, &blob_file_name(artifact)) {
Ok(dir) => dir,
Err(copy_err) => {
facts.push(DetectedFact::new(
"materialize_failed",
copy_err.to_string(),
"ingest",
));
stored.clone()
}
}
}
}
} else {
stored.clone()
};
Ok(IngestedArtifact {
artifact_id: artifact.id.clone(),
kind: artifact.kind,
working_path: Some(working_path),
content_hash: Some(sha),
size_bytes: Some(size),
facts,
})
}
/// Copy a stored blob into `dest`/`name`, returning `dest`. Used when an
/// "extractable" artifact turns out to be a single file rather than an archive.
fn materialize_single(stored: &Path, dest: &Path, name: &str) -> Result<PathBuf, AgentError> {
std::fs::create_dir_all(dest)?;
std::fs::copy(stored, dest.join(name))?;
Ok(dest.to_path_buf())
}
/// A safe, single-segment file name for an artifact, preserving the original
/// extension so scanners can identify it. Derives from `source_ref` (the
/// uploaded/original file name); `file_name` strips any directory components,
/// so this is traversal-safe. Falls back to the artifact id.
fn blob_file_name(artifact: &Artifact) -> String {
Path::new(&artifact.source_ref)
.file_name()
.and_then(|n| n.to_str())
.map(str::to_string)
.filter(|s| !s.is_empty())
.unwrap_or_else(|| format!("artifact-{}", artifact.id))
}
/// An artifact with no on-disk form: record a single fact, no hash/path.
fn metadata_only(artifact: &Artifact, fact: DetectedFact) -> IngestedArtifact {
IngestedArtifact {
artifact_id: artifact.id.clone(),
kind: artifact.kind,
working_path: None,
content_hash: None,
size_bytes: None,
facts: vec![fact],
}
}
/// The local file backing a blob artifact: its `stored_path` if already
/// uploaded, else its `source_ref` interpreted as a filesystem path.
fn local_source(artifact: &Artifact) -> Result<PathBuf, AgentError> {
let path = artifact
.stored_path
.as_deref()
.unwrap_or(artifact.source_ref.as_str());
let path = PathBuf::from(path);
if !path.exists() {
return Err(AgentError::Other(format!(
"artifact {} source not found at {}",
artifact.id,
path.display()
)));
}
Ok(path)
}
/// Build git credentials from an artifact's auth plus a default SSH key path.
fn credentials_for(artifact: &Artifact, default_ssh_key_path: &str) -> RepoCredentials {
let auth = artifact.auth.as_ref();
RepoCredentials {
ssh_key_path: auth
.and_then(|a| a.ssh_key_path.clone())
.or_else(|| Some(default_ssh_key_path.to_string())),
auth_token: auth.and_then(|a| a.secret.clone()),
auth_username: auth.and_then(|a| a.username.clone()),
}
}
#[cfg(test)]
#[allow(clippy::expect_used, clippy::unwrap_used)]
mod tests {
use super::*;
use compliance_core::models::{ArtifactAuth, TargetType};
/// A unique scratch directory, removed on drop.
struct Scratch(PathBuf);
impl Scratch {
fn new() -> Self {
let p = std::env::temp_dir().join(format!("cs-ingest-mod-{}", uuid::Uuid::new_v4()));
std::fs::create_dir_all(&p).expect("mkdir scratch");
Self(p)
}
}
impl Drop for Scratch {
fn drop(&mut self) {
let _ = std::fs::remove_dir_all(&self.0);
}
}
fn ctx_for<'a>(store: &'a Path, target_id: &'a str) -> IngestContext<'a> {
IngestContext {
artifact_store_base: store,
git_clone_base: "/tmp/cs-ingest-test-repos",
ssh_key_path: "/tmp/cs-ingest-test-ssh",
target_id,
}
}
#[test]
fn firmware_blob_is_hashed_and_stored() {
let scratch = Scratch::new();
let store = scratch.0.join("store");
let fw = scratch.0.join("fw.bin");
std::fs::write(&fw, b"firmware-bytes").expect("write");
let ctx = ctx_for(&store, "t1");
let artifact = Artifact::firmware_image(fw.to_string_lossy().to_string());
let out = ingest_artifact(&artifact, &ctx).expect("ingest");
assert_eq!(out.kind, ArtifactKind::FirmwareImage);
assert_eq!(out.size_bytes, Some(14));
let sha = out.content_hash.expect("hash");
assert_eq!(sha.len(), 64);
// working path is the content-addressed blob
let wp = out.working_path.expect("working path");
assert!(wp.starts_with(store.join("blobs")));
}
#[test]
fn live_url_has_no_blob() {
let scratch = Scratch::new();
let store = scratch.0.join("store");
let ctx = ctx_for(&store, "t1");
let artifact = Artifact::live_url("https://example.com");
let out = ingest_artifact(&artifact, &ctx).expect("ingest");
assert!(out.working_path.is_none());
assert!(out.content_hash.is_none());
assert!(out.facts.iter().any(|f| f.key == "live_url"));
}
#[test]
fn ingest_all_collects_working_paths() {
let scratch = Scratch::new();
let store = scratch.0.join("store");
let fw = scratch.0.join("fw.bin");
std::fs::write(&fw, b"abc").expect("write");
let ctx = ctx_for(&store, "t1");
let mut target = OnboardedTarget::new("t".to_string(), TargetType::FirmwareBareMetal);
target
.artifacts
.push(Artifact::firmware_image(fw.to_string_lossy().to_string()));
target.artifacts.push(Artifact::live_url("https://x"));
let set = ingest_all(&target, &ctx).expect("ingest all");
assert_eq!(set.by_artifact.len(), 2);
// Only the firmware artifact yields a working path.
assert_eq!(set.working_paths().len(), 1);
}
#[test]
fn credentials_prefer_artifact_auth() {
let mut artifact = Artifact::git_repo("https://git/x", "main");
artifact.auth = Some(ArtifactAuth {
method: "token".to_string(),
username: Some("bob".to_string()),
secret: Some("pat".to_string()),
..Default::default()
});
let creds = credentials_for(&artifact, "/default/ssh/key");
assert_eq!(creds.auth_token.as_deref(), Some("pat"));
assert_eq!(creds.auth_username.as_deref(), Some("bob"));
}
#[test]
fn credentials_fall_back_to_default_ssh_key() {
let artifact = Artifact::git_repo("git@host:x.git", "main");
let creds = credentials_for(&artifact, "/default/ssh/key");
assert_eq!(creds.ssh_key_path.as_deref(), Some("/default/ssh/key"));
assert!(creds.auth_token.is_none());
}
/// A single uploaded PLC file (not an archive) must land in a working dir
/// under its original name so the PLC scanner can discover it by extension
/// and report a readable path — the demo's upload → scan path.
#[test]
fn single_uploaded_plc_file_is_materialized_and_scannable() {
use compliance_core::models::PlcFormat;
let scratch = Scratch::new();
let store = scratch.0.join("store");
// Simulate the upload handler: bytes written to an `uploads/` path,
// `source_ref` carrying the original (clean) file name.
let uploads = scratch.0.join("uploads");
std::fs::create_dir_all(&uploads).expect("mkdir uploads");
let uploaded = uploads.join("a1b2c3_pump_station.st");
std::fs::write(
&uploaded,
"PROGRAM P\nVAR\n ApiKey : STRING := 'sk-live-1234';\nEND_VAR\nEND_PROGRAM\n",
)
.expect("write st");
let mut artifact = Artifact::plc_project("pump_station.st", PlcFormat::StructuredText);
artifact.stored_path = Some(uploaded.to_string_lossy().to_string());
let ctx = ctx_for(&store, "t-plc");
let out = ingest_artifact(&artifact, &ctx).expect("ingest");
// Working path is a directory (not the extensionless blob) holding the
// file under its original name.
let wp = out.working_path.expect("working path");
assert!(wp.is_dir(), "expected a working dir, got {wp:?}");
assert!(wp.join("pump_station.st").is_file());
// The PLC scanner finds the hardcoded credential and reports a clean path.
let findings = crate::pipeline::plc::analyze_tree(&wp, "t-plc");
assert!(
!findings.is_empty(),
"scanner should flag the uploaded file"
);
assert!(findings
.iter()
.any(|f| f.rule_id.as_deref() == Some("plc-hardcoded-credential")));
assert_eq!(
findings[0].file_path.as_deref(),
Some("pump_station.st"),
"finding should reference the original file name"
);
}
}
+2
View File
@@ -2,9 +2,11 @@
pub mod agent;
pub mod api;
pub mod classify;
pub mod config;
pub mod database;
pub mod error;
pub mod ingest;
pub mod llm;
pub mod pentest;
pub mod pipeline;
+2
View File
@@ -328,6 +328,7 @@ mod tests {
scan_schedule: String::new(),
cve_monitor_schedule: String::new(),
git_clone_base_path: String::new(),
artifact_store_base_path: String::new(),
ssh_key_path: String::new(),
keycloak_url: None,
keycloak_realm: None,
@@ -341,6 +342,7 @@ mod tests {
pentest_imap_password: None,
admin_api_token: None,
tenant_registry_url: None,
plc_runtime: compliance_core::PlcRuntimeConfig::default(),
}
}
+283
View File
@@ -204,6 +204,202 @@ impl CveScanner {
Ok(results)
}
/// Match the CODESYS **runtime** component against NVD by CPE.
///
/// CODESYS advisories (the CoDe16 cluster and friends) are indexed in NVD by
/// CPE (`cpe:2.3:a:codesys:control*`) keyed off the *runtime* version — not by
/// the internal `Cmp*`/`Sys*` library names OSV-by-purl would look up. So we
/// find the runtime SBOM entry, pull every `cpe:2.3:a:codesys:*` CVE from NVD,
/// and keep the ones whose affected-version range covers our runtime version.
/// Best-effort: returns empty without an NVD key, on a network error, or when
/// no CODESYS runtime component is present.
pub async fn scan_codesys(&self, repo_id: &str, entries: &mut [SbomEntry]) -> Vec<CveAlert> {
let Some((name, version)) = codesys_runtime(entries) else {
return Vec::new();
};
let url = "https://services.nvd.nist.gov/rest/json/cves/2.0\
?virtualMatchString=cpe:2.3:a:codesys";
let mut req = self.http.get(url);
if let Some(key) = &self.nvd_api_key {
req = req.header("apiKey", key.as_str());
}
let body: serde_json::Value = match req.send().await {
Ok(r) if r.status().is_success() => match r.json().await {
Ok(b) => b,
Err(e) => {
tracing::warn!("CODESYS NVD parse failed: {e}");
return Vec::new();
}
},
Ok(r) => {
tracing::warn!("CODESYS NVD returned {}", r.status());
return Vec::new();
}
Err(e) => {
tracing::warn!("CODESYS NVD request failed: {e}");
return Vec::new();
}
};
let matched = parse_codesys_nvd(&body, &version);
let mut alerts = Vec::new();
for cve in matched {
if let Some(e) = entries
.iter_mut()
.find(|e| e.name == name && e.version == version)
{
e.known_vulnerabilities.push(VulnRef {
id: cve.id.clone(),
source: "nvd".to_string(),
severity: None,
url: Some(format!("https://nvd.nist.gov/vuln/detail/{}", cve.id)),
});
}
let mut alert = CveAlert::new(
cve.id,
repo_id.to_string(),
name.clone(),
version.clone(),
CveSource::Nvd,
);
alert.summary = cve.summary;
alert.cvss_score = cve.cvss;
alerts.push(alert);
}
tracing::info!(runtime = %name, version = %version, cves = alerts.len(), "CODESYS CVE match");
alerts
}
}
/// The CODESYS runtime component (name + version) from an SBOM, if present. The
/// runtime carries the version CODESYS advisories key off; the internal library
/// components do not.
fn codesys_runtime(entries: &[SbomEntry]) -> Option<(String, String)> {
entries
.iter()
.find(|e| e.package_manager == "codesys" && e.name.starts_with("CODESYS Control"))
.map(|e| (e.name.clone(), e.version.clone()))
}
/// A parsed NVD CVE that affects the CODESYS runtime.
struct CodesysCve {
id: String,
summary: Option<String>,
cvss: Option<f64>,
}
/// Version constraints from an NVD `cpeMatch` node.
#[derive(Default)]
struct CpeRange {
exact: Option<String>,
start_incl: Option<String>,
start_excl: Option<String>,
end_incl: Option<String>,
end_excl: Option<String>,
}
/// Parse an NVD CVE-list response and keep the CVEs whose CODESYS CPE match covers
/// `runtime_version`.
fn parse_codesys_nvd(body: &serde_json::Value, runtime_version: &str) -> Vec<CodesysCve> {
let mut out = Vec::new();
let Some(vulns) = body["vulnerabilities"].as_array() else {
return out;
};
for v in vulns {
let cve = &v["cve"];
let Some(id) = cve["id"].as_str() else {
continue;
};
let covered = cve["configurations"]
.as_array()
.into_iter()
.flatten()
.flat_map(|c| c["nodes"].as_array().into_iter().flatten())
.flat_map(|n| n["cpeMatch"].as_array().into_iter().flatten())
.any(|cm| {
cm["vulnerable"].as_bool() == Some(true)
&& cm["criteria"]
.as_str()
.is_some_and(|c| c.contains(":codesys:"))
&& version_matches(runtime_version, &cpe_range(cm))
});
if covered {
let summary = cve["descriptions"]
.as_array()
.and_then(|d| d.iter().find(|x| x["lang"].as_str() == Some("en")))
.and_then(|x| x["value"].as_str())
.map(String::from);
let cvss = cve["metrics"]["cvssMetricV31"]
.as_array()
.and_then(|m| m.first())
.and_then(|m| m["cvssData"]["baseScore"].as_f64());
out.push(CodesysCve {
id: id.to_string(),
summary,
cvss,
});
}
}
out
}
/// Build a [`CpeRange`] from an NVD `cpeMatch` object.
fn cpe_range(cm: &serde_json::Value) -> CpeRange {
let exact = cm["criteria"]
.as_str()
.and_then(cpe_version)
.filter(|v| v != "*" && v != "-" && !v.is_empty());
CpeRange {
exact,
start_incl: cm["versionStartIncluding"].as_str().map(String::from),
start_excl: cm["versionStartExcluding"].as_str().map(String::from),
end_incl: cm["versionEndIncluding"].as_str().map(String::from),
end_excl: cm["versionEndExcluding"].as_str().map(String::from),
}
}
/// The version field (6th component) of a CPE 2.3 string.
fn cpe_version(criteria: &str) -> Option<String> {
criteria.split(':').nth(5).map(String::from)
}
/// Whether `v` satisfies a CPE version range.
fn version_matches(v: &str, r: &CpeRange) -> bool {
use std::cmp::Ordering::{Equal, Greater, Less};
if let Some(exact) = &r.exact {
return cmp_dotted(v, exact) == Equal;
}
let mut ok = true;
if let Some(s) = &r.start_incl {
ok &= cmp_dotted(v, s) != Less;
}
if let Some(s) = &r.start_excl {
ok &= cmp_dotted(v, s) == Greater;
}
if let Some(e) = &r.end_incl {
ok &= cmp_dotted(v, e) != Greater;
}
if let Some(e) = &r.end_excl {
ok &= cmp_dotted(v, e) == Less;
}
ok
}
/// Compare two dotted numeric versions (`4.17.0.0` vs `4.9.0.0`); missing
/// components count as 0, non-numeric components as 0.
fn cmp_dotted(a: &str, b: &str) -> std::cmp::Ordering {
let pa: Vec<u64> = a.split('.').map(|x| x.parse().unwrap_or(0)).collect();
let pb: Vec<u64> = b.split('.').map(|x| x.parse().unwrap_or(0)).collect();
for i in 0..pa.len().max(pb.len()) {
let x = pa.get(i).copied().unwrap_or(0);
let y = pb.get(i).copied().unwrap_or(0);
match x.cmp(&y) {
std::cmp::Ordering::Equal => continue,
other => return other,
}
}
std::cmp::Ordering::Equal
}
#[derive(serde::Deserialize)]
@@ -228,3 +424,90 @@ struct OsvVuln {
summary: Option<String>,
severity: Option<String>,
}
#[cfg(test)]
mod tests {
use super::*;
use std::cmp::Ordering::{Equal, Greater, Less};
fn entry(name: &str, ver: &str, pm: &str) -> SbomEntry {
SbomEntry::new("t".into(), name.into(), ver.into(), pm.into())
}
#[test]
fn finds_the_codesys_runtime_component() {
let entries = vec![
entry("Standard", "3.5.18.0", "codesys"),
entry("CODESYS Control for Linux ARM SL", "4.17.0.0", "codesys"),
];
assert_eq!(
codesys_runtime(&entries),
Some(("CODESYS Control for Linux ARM SL".into(), "4.17.0.0".into()))
);
// Internal library components are not the runtime.
assert!(codesys_runtime(&[entry("Util", "3.5.21.0", "codesys")]).is_none());
}
#[test]
fn dotted_version_comparison() {
assert_eq!(cmp_dotted("4.17.0.0", "4.9.0.0"), Greater);
assert_eq!(cmp_dotted("4.9.0.0", "4.17.0.0"), Less);
assert_eq!(cmp_dotted("3.5.18.0", "3.5.18.0"), Equal);
assert_eq!(cmp_dotted("4.2", "4.2.0.0"), Equal); // missing components = 0
}
#[test]
fn version_range_matching() {
let end_excl = CpeRange {
end_excl: Some("4.9.0.0".into()),
..Default::default()
};
assert!(!version_matches("4.17.0.0", &end_excl)); // patched
assert!(version_matches("4.5.0.0", &end_excl)); // affected
let exact = CpeRange {
exact: Some("3.5.16.0".into()),
..Default::default()
};
assert!(version_matches("3.5.16.0", &exact));
assert!(!version_matches("3.5.17.0", &exact));
let span = CpeRange {
start_incl: Some("3.0.0.0".into()),
end_incl: Some("3.5.16.0".into()),
..Default::default()
};
assert!(version_matches("3.5.16.0", &span));
assert!(!version_matches("3.5.17.0", &span));
}
#[test]
fn parses_nvd_and_matches_by_runtime_version() {
// Two CODESYS CVEs: one affects < 4.9 (our 4.17 is patched), one affects
// <= 4.20 (our 4.17 is affected). Only the latter should match.
let body = serde_json::json!({
"vulnerabilities": [
{"cve": {"id":"CVE-2023-0001",
"descriptions":[{"lang":"en","value":"old CmpBlkDrvTcp bug"}],
"metrics":{"cvssMetricV31":[{"cvssData":{"baseScore":7.5}}]},
"configurations":[{"nodes":[{"cpeMatch":[
{"vulnerable":true,
"criteria":"cpe:2.3:a:codesys:control_for_linux_sl:*:*:*:*:*:*:*:*",
"versionEndExcluding":"4.9.0.0"}
]}]}]}},
{"cve": {"id":"CVE-2024-0002",
"descriptions":[{"lang":"en","value":"recent runtime bug"}],
"metrics":{"cvssMetricV31":[{"cvssData":{"baseScore":9.8}}]},
"configurations":[{"nodes":[{"cpeMatch":[
{"vulnerable":true,
"criteria":"cpe:2.3:a:codesys:control_for_linux_sl:*:*:*:*:*:*:*:*",
"versionEndIncluding":"4.20.0.0"}
]}]}]}}
]
});
let matched = parse_codesys_nvd(&body, "4.17.0.0");
let ids: Vec<&str> = matched.iter().map(|c| c.id.as_str()).collect();
assert_eq!(ids, vec!["CVE-2024-0002"]);
assert_eq!(matched[0].cvss, Some(9.8));
}
}
@@ -0,0 +1,152 @@
//! Firmware SBOM via tramiton.
//!
//! Phase 2 (full, the default): drive a **reproducible build** with tramiton's
//! `NixBackend` — `analyze` → `seal_and_build` → a sealed lock whose libraries
//! are pinned and whose firmware artifact carries a content hash — then render
//! the SBOM from the lock plus deep binary SCA of pre-compiled inputs. This is
//! the complete bill of materials (toolchain + every fetched library + the
//! firmware image), the same one `tramiton sbom` produces.
//!
//! Phase 1 fallback (analysis-only): when no nix backend is available or the
//! build fails, fall back to the resolvable libraries + toolchain from the build
//! plan alone (no build). A scan therefore always yields *something*, and a nix
//! that can't run in the deployment never breaks a scan.
use std::path::Path;
use compliance_core::models::{SbomEntry, TargetType};
use tramiton_repro::ReproBackend;
use tramiton_sbom::ComponentKind;
/// Whether firmware SBOM applies to this target family.
pub fn is_firmware_target(target_type: TargetType) -> bool {
matches!(
target_type,
TargetType::FirmwareBareMetal | TargetType::FirmwareRtos | TargetType::EmbeddedLinuxYocto
)
}
/// Build SBOM entries for a firmware target from its source tree. Prefers a full
/// reproducible build (sealed lock); falls back to analysis-only. Returns an
/// empty vector when tramiton cannot even form a build plan.
pub async fn firmware_sbom_entries(path: &Path, repo_id: &str) -> Vec<SbomEntry> {
let p = path.to_path_buf();
let repo = repo_id.to_string();
// The whole analyze → seal → build → render sequence is blocking (it shells
// out to nix), so keep it off the async runtime. Bound it: a firmware build
// that hangs must not wedge the scan (the orphaned task is abandoned).
let handle = tokio::task::spawn_blocking(move || build_sbom_blocking(&p, &repo));
match tokio::time::timeout(std::time::Duration::from_secs(900), handle).await {
Ok(Ok(entries)) => entries,
Ok(Err(e)) => {
tracing::warn!(repo_id, error = %e, "Firmware SBOM: task join error");
Vec::new()
}
Err(_) => {
tracing::warn!(repo_id, "Firmware SBOM: build exceeded 15m; skipping");
Vec::new()
}
}
}
fn build_sbom_blocking(path: &Path, repo_id: &str) -> Vec<SbomEntry> {
let repo = tramiton_core::Repo::new(path);
let plan = match tramiton_core::provider::analyze(&repo) {
Ok(Some(bp)) => bp,
Ok(None) => return Vec::new(),
Err(e) => {
tracing::warn!(repo_id, error = %e, "Firmware SBOM: tramiton analyze failed");
return Vec::new();
}
};
// Phase 2: reproducible build → sealed lock → complete SBOM.
if let Some(backend) = tramiton_repro::NixBackend::detect() {
match tramiton_repro::seal_and_build(&backend, &plan, path) {
Ok(lock) => {
let mut sbom = tramiton_sbom::Sbom::from_lock(&lock, repo_id);
// Deep binary SCA of any pre-compiled inputs in the tree.
sbom.components.extend(tramiton_sbom::binary::scan(path));
let entries = sbom_to_entries(&sbom, repo_id);
tracing::info!(
repo_id,
backend = backend.name(),
count = entries.len(),
"Firmware SBOM: sealed reproducible build"
);
return entries;
}
Err(e) => {
tracing::warn!(repo_id, error = %e, "Firmware SBOM: reproducible build failed; falling back to analysis-only")
}
}
} else {
tracing::info!(
repo_id,
"Firmware SBOM: no nix backend available; analysis-only SBOM"
);
}
// Phase 1 fallback: analysis-only (toolchain + resolvable libraries).
analysis_entries(&plan, repo_id)
}
/// Map a rendered [`tramiton_sbom::Sbom`] (primary firmware + components) into
/// our [`SbomEntry`] rows. Source-file (`File`) components are dropped — they are
/// build inputs, not a dependency inventory.
fn sbom_to_entries(sbom: &tramiton_sbom::Sbom, repo_id: &str) -> Vec<SbomEntry> {
let mut entries = Vec::new();
if let Some(primary) = &sbom.primary {
entries.push(component_to_entry(primary, repo_id));
}
for c in &sbom.components {
if matches!(c.kind, ComponentKind::File) {
continue;
}
entries.push(component_to_entry(c, repo_id));
}
entries
}
fn component_to_entry(c: &tramiton_sbom::Component, repo_id: &str) -> SbomEntry {
let manager = match c.kind {
ComponentKind::Firmware => "firmware",
ComponentKind::Library => "library",
ComponentKind::Toolchain => "toolchain",
ComponentKind::File => "file",
};
let mut entry = SbomEntry::new(
repo_id.to_string(),
c.name.clone(),
c.version.clone().unwrap_or_default(),
manager.to_string(),
);
entry.purl = c.source.clone();
entry
}
/// Analysis-only components from the build plan: the cross-toolchain plus the
/// resolvable fetched libraries, without a build.
fn analysis_entries(bp: &tramiton_core::BuildPlan, repo_id: &str) -> Vec<SbomEntry> {
let mut entries = Vec::new();
if let Some(id) = bp.toolchain.id.clone() {
let version = bp.toolchain.version.clone().unwrap_or_default();
entries.push(SbomEntry::new(
repo_id.to_string(),
id,
version,
"toolchain".to_string(),
));
}
for lib in tramiton_repro::lock::libraries_from_inputs(&bp.inputs) {
let mut entry = SbomEntry::new(
repo_id.to_string(),
lib.name,
lib.revision,
"library".to_string(),
);
entry.purl = lib.source;
entries.push(entry);
}
entries
}
+48 -2
View File
@@ -80,7 +80,10 @@ impl GitOps {
#[tracing::instrument(skip_all, fields(repo_name = %repo_name))]
pub fn clone_or_fetch(&self, git_url: &str, repo_name: &str) -> Result<PathBuf, AgentError> {
let repo_path = self.base_path.join(repo_name);
// Names can contain slashes or other path-hostile characters (a target
// named after a repo path, say); collapse to one safe directory segment
// so the clone path never nests or breaks.
let repo_path = self.base_path.join(sanitize_repo_dir(repo_name));
if repo_path.exists() {
tracing::info!("fetching updates for existing repo");
@@ -135,7 +138,7 @@ impl GitOps {
/// Build credentials from agent config + per-repo overrides
pub fn make_repo_credentials(
config: &compliance_core::AgentConfig,
repo: &compliance_core::models::TrackedRepository,
repo: &crate::pipeline::repo_view::RepoView,
) -> RepoCredentials {
RepoCredentials {
ssh_key_path: Some(config.ssh_key_path.clone()),
@@ -253,3 +256,46 @@ pub struct DiffFile {
pub path: String,
pub hunks: String,
}
/// Collapse a repository name into a single filesystem-safe directory segment.
/// Names may carry slashes or other path-hostile characters (a target named
/// after a repo path, for instance); those would otherwise nest or break the
/// clone path, so map anything outside `[A-Za-z0-9._-]` to `_`.
fn sanitize_repo_dir(name: &str) -> String {
let mapped: String = name
.chars()
.map(|c| {
if c.is_ascii_alphanumeric() || c == '-' || c == '_' || c == '.' {
c
} else {
'_'
}
})
.collect();
let trimmed = mapped.trim_matches(|c| c == '.' || c == '_');
if trimmed.is_empty() {
"repo".to_string()
} else {
trimmed.to_string()
}
}
#[cfg(test)]
mod tests {
use super::sanitize_repo_dir;
#[test]
fn sanitizes_path_hostile_names() {
assert_eq!(
sanitize_repo_dir("zephyr-example-app"),
"zephyr-example-app"
);
assert_eq!(
sanitize_repo_dir("ChristianRinn/bare_metal_stm32f411xe"),
"ChristianRinn_bare_metal_stm32f411xe"
);
assert_eq!(sanitize_repo_dir("../../etc/passwd"), "etc_passwd");
assert_eq!(sanitize_repo_dir("a b:c"), "a_b_c");
assert_eq!(sanitize_repo_dir("///"), "repo");
}
}
@@ -0,0 +1,95 @@
//! Minimal EtherNet/IP (CIP) reachability probe.
//!
//! Sends an EtherNet/IP encapsulation **ListIdentity** command (0x0063) over TCP
//! 44818 and checks for a valid encapsulation reply — confirming a CIP device
//! without opening a session or writing anything.
use std::time::Duration;
use tokio::io::{AsyncReadExt, AsyncWriteExt};
use tokio::net::TcpStream;
use tokio::time::timeout;
/// Outcome of an EtherNet/IP handshake probe.
#[derive(Debug, Default, PartialEq, Eq)]
pub struct EnipProbe {
/// A TCP connection to the port was established.
pub reachable: bool,
/// The endpoint returned a valid EtherNet/IP encapsulation reply.
pub is_enip: bool,
}
/// Probe an EtherNet/IP endpoint with a ListIdentity request. Read-only.
pub async fn probe(host: &str, port: u16, budget: Duration) -> EnipProbe {
let mut out = EnipProbe::default();
let Ok(Ok(mut stream)) = timeout(budget, TcpStream::connect((host, port))).await else {
return out;
};
out.reachable = true;
// Encapsulation header (24 bytes): command(2) length(2) session(4) status(4)
// context(8) options(4). ListIdentity = command 0x0063, everything else zero.
let mut req = vec![0u8; 24];
req[0..2].copy_from_slice(&0x0063u16.to_le_bytes());
if timeout(budget, stream.write_all(&req))
.await
.ok()
.and_then(Result::ok)
.is_none()
{
return out;
}
let mut hdr = [0u8; 24];
if timeout(budget, stream.read_exact(&mut hdr))
.await
.ok()
.and_then(Result::ok)
.is_none()
{
return out;
}
let command = u16::from_le_bytes([hdr[0], hdr[1]]);
let status = u32::from_le_bytes([hdr[8], hdr[9], hdr[10], hdr[11]]);
// Echoed command + success status = a valid EtherNet/IP encapsulation reply.
if command == 0x0063 && status == 0 {
out.is_enip = true;
}
out
}
#[cfg(test)]
mod tests {
use super::*;
use tokio::net::TcpListener;
async fn mock_server() -> std::net::SocketAddr {
let listener = TcpListener::bind("127.0.0.1:0").await.expect("bind");
let addr = listener.local_addr().expect("addr");
tokio::spawn(async move {
let (mut sock, _) = listener.accept().await.expect("accept");
let mut req = [0u8; 24];
if sock.read_exact(&mut req).await.is_err() {
return;
}
// Reply: echo command 0x0063, status 0, no data.
let mut hdr = vec![0u8; 24];
hdr[0..2].copy_from_slice(&0x0063u16.to_le_bytes());
let _ = sock.write_all(&hdr).await;
});
addr
}
#[tokio::test]
async fn probe_detects_an_ethernetip_device() {
let addr = mock_server().await;
let p = probe(&addr.ip().to_string(), addr.port(), Duration::from_secs(2)).await;
assert!(p.reachable && p.is_enip);
}
#[tokio::test]
async fn probe_reports_unreachable_for_a_closed_port() {
let p = probe("127.0.0.1", 1, Duration::from_millis(500)).await;
assert!(!p.reachable && !p.is_enip);
}
}
+306
View File
@@ -0,0 +1,306 @@
//! Dynamic ICS (industrial control system) probing for PLC/SPS targets.
//!
//! Where the control-logic scanner is static (over ST / PLCopen XML), this probes
//! the *running* device over industrial protocols and reports exposed /
//! unauthenticated control interfaces. It is read-only: it never writes to a live
//! process. Modbus/TCP and OPC UA are implemented; EtherNet-IP is a follow-on.
pub mod ethernetip;
pub mod modbus;
pub mod opcua;
pub mod portscan;
use std::time::Duration;
use compliance_core::models::{Finding, ScanType, Severity};
use crate::pipeline::dedup;
/// Well-known deep-probe ports (each independent of any WebVisu HTTP port).
const MODBUS_PORT: u16 = 502;
const OPCUA_PORT: u16 = 4840;
const ENIP_PORT: u16 = 44818;
/// Probe a PLC/SPS device's industrial-protocol surface and return findings.
/// Read-only. Deep-probes Modbus/TCP, OPC UA and EtherNet/IP, plus a service
/// discovery scan of the remaining OT / insecure-management ports. `endpoint` is
/// the target's live-URL / host reference.
pub async fn probe_target(endpoint: &str, repo_id: &str, budget: Duration) -> Vec<Finding> {
let (host, modbus_port) = parse_endpoint(endpoint);
let mut findings = modbus_findings(&host, modbus_port, repo_id, budget).await;
findings.extend(opcua_findings(&host, OPCUA_PORT, repo_id, budget).await);
findings.extend(enip_findings(&host, ENIP_PORT, repo_id, budget).await);
findings.extend(portscan_findings(&host, repo_id, budget).await);
findings
}
/// Findings from probing the Modbus/TCP surface.
async fn modbus_findings(host: &str, port: u16, repo_id: &str, budget: Duration) -> Vec<Finding> {
let probe = modbus::probe(host, port, budget).await;
let mut findings = Vec::new();
if !probe.speaks_modbus {
// Not reachable, or the port does not speak Modbus — nothing to report.
return findings;
}
let target = format!("{host}:{port}");
// Reachable Modbus/TCP = unauthenticated, cleartext control access by design.
let fp = dedup::compute_fingerprint(&[repo_id, "ics-modbus-exposed", &target]);
let mut f = Finding::new(
repo_id.to_string(),
fp,
"ics-probe".to_string(),
ScanType::IcsProbe,
"Modbus/TCP control interface exposed without authentication".to_string(),
format!(
"The device at {target} answers Modbus/TCP requests. Modbus/TCP has no \
authentication or encryption in the protocol, so any host that can reach this \
port can read and write process variables (coils/registers) and disrupt the \
controlled process."
),
Severity::Critical,
);
f.rule_id = Some("ics-modbus-exposed".to_string());
f.cwe = Some("CWE-306".to_string());
f.remediation = Some(
"Restrict the Modbus/TCP port to a trusted control network (segmentation / \
firewall / VPN), never expose it to IT or the internet, and prefer an authenticated \
transport (e.g. Modbus/TLS) or a secure protocol gateway where available."
.to_string(),
);
findings.push(f);
if let Some(dev) = &probe.device {
let details = [
dev.vendor.as_deref(),
dev.product.as_deref(),
dev.revision.as_deref(),
]
.into_iter()
.flatten()
.collect::<Vec<_>>()
.join(" / ");
let fp = dedup::compute_fingerprint(&[repo_id, "ics-device-disclosure", &target]);
let mut f = Finding::new(
repo_id.to_string(),
fp,
"ics-probe".to_string(),
ScanType::IcsProbe,
"PLC device identity disclosed over Modbus".to_string(),
format!(
"The device at {target} discloses its identity via Modbus Read Device \
Identification: {details}. This aids fingerprinting and targeting of \
known-vulnerable firmware/runtime versions."
),
Severity::Low,
);
f.rule_id = Some("ics-device-disclosure".to_string());
f.cwe = Some("CWE-200".to_string());
f.remediation = Some(
"Limit network reach to the device; Modbus device identification cannot be \
disabled, so exposure is bounded by network segmentation."
.to_string(),
);
findings.push(f);
}
// Exposed process points: coils / holding registers that a read enumerated
// and that, over unauthenticated Modbus/TCP, are also writable. This is the
// concrete attack surface behind the exposure — the live variables an
// attacker can overwrite. (Read-only to detect: we never write.)
let coils = probe.coils_readable.unwrap_or(0);
let registers = probe.holding_registers_readable.unwrap_or(0);
if coils > 0 || registers > 0 {
let fp = dedup::compute_fingerprint(&[repo_id, "ics-modbus-exposed-points", &target]);
let mut f = Finding::new(
repo_id.to_string(),
fp,
"ics-probe".to_string(),
ScanType::IcsProbe,
"Writable process points exposed over unauthenticated Modbus/TCP".to_string(),
format!(
"Reading the device at {target} enumerated {coils} coil(s) and {registers} \
holding register(s). Coils and holding registers are read/write process points \
in Modbus, so any host that can reach this port can not only read but overwrite \
live process state (force coils, change setpoints) without authentication."
),
Severity::High,
);
f.rule_id = Some("ics-modbus-exposed-points".to_string());
f.cwe = Some("CWE-306".to_string());
f.remediation = Some(
"Segment the Modbus/TCP port to a trusted control network; where the device \
supports it use Modbus/TLS or an authenticating protocol gateway; restrict which \
function codes and register ranges are reachable from outside the control zone."
.to_string(),
);
findings.push(f);
}
findings
}
/// Findings from probing the OPC UA surface (default port 4840). A reachability
/// probe only: it flags an exposed OPC UA server for review of its security
/// policy / authentication (deep SecurityPolicy analysis is a follow-on).
async fn opcua_findings(host: &str, port: u16, repo_id: &str, budget: Duration) -> Vec<Finding> {
let probe = opcua::probe(host, port, budget).await;
let mut findings = Vec::new();
if !probe.is_opcua {
return findings;
}
let target = format!("{host}:{port}");
let fp = dedup::compute_fingerprint(&[repo_id, "ics-opcua-exposed", &target]);
let mut f = Finding::new(
repo_id.to_string(),
fp,
"ics-probe".to_string(),
ScanType::IcsProbe,
"OPC UA server exposed on the network".to_string(),
format!(
"An OPC UA server answers at {target}. Verify it enforces message security \
(a SecurityPolicy other than None) and rejects anonymous sessions — the common \
default of SecurityPolicy None + an Anonymous user token allows unauthenticated, \
unencrypted read/write of the server's address space."
),
Severity::Medium,
);
f.rule_id = Some("ics-opcua-exposed".to_string());
f.cwe = Some("CWE-319".to_string());
f.remediation = Some(
"Restrict OPC UA (4840) to a trusted network; require a signed & encrypted \
SecurityPolicy (Basic256Sha256 or better) with certificate / username \
authentication, and disable the Anonymous user token."
.to_string(),
);
findings.push(f);
findings
}
/// Findings from probing the EtherNet/IP (CIP) surface (default port 44818).
async fn enip_findings(host: &str, port: u16, repo_id: &str, budget: Duration) -> Vec<Finding> {
let probe = ethernetip::probe(host, port, budget).await;
if !probe.is_enip {
return Vec::new();
}
let target = format!("{host}:{port}");
let fp = dedup::compute_fingerprint(&[repo_id, "ics-ethernetip-exposed", &target]);
let mut f = Finding::new(
repo_id.to_string(),
fp,
"ics-probe".to_string(),
ScanType::IcsProbe,
"EtherNet/IP (CIP) interface exposed on the network".to_string(),
format!(
"The device at {target} answers EtherNet/IP (CIP) requests. EtherNet/IP has no \
authentication in the base protocol, so a host that can reach it can enumerate \
and interact with the device's control objects."
),
Severity::High,
);
f.rule_id = Some("ics-ethernetip-exposed".to_string());
f.cwe = Some("CWE-306".to_string());
f.remediation = Some(
"Restrict EtherNet/IP (44818/2222) to a trusted control network; use CIP Security \
(encryption + authentication) on devices that support it."
.to_string(),
);
vec![f]
}
/// Findings from the service-discovery port scan of the remaining OT /
/// insecure-management surface.
async fn portscan_findings(host: &str, repo_id: &str, budget: Duration) -> Vec<Finding> {
let open = portscan::scan(host, portscan::KNOWN_PORTS, budget).await;
open.into_iter()
.map(|kp| {
let target = format!("{host}:{}", kp.port);
let (title, severity, cwe, description) = match kp.kind {
portscan::PortKind::Ics => (
format!("ICS service exposed: {}", kp.service),
Severity::High,
"CWE-306",
format!(
"{target} exposes {} ({}). Industrial protocols are typically \
unauthenticated, so network reach implies control access.",
kp.service, kp.note
),
),
portscan::PortKind::InsecureMgmt => (
format!("Cleartext service exposed: {}", kp.service),
Severity::Medium,
"CWE-319",
format!(
"{target} exposes {} ({}), which transmits credentials and data in \
cleartext.",
kp.service, kp.note
),
),
};
let fp = dedup::compute_fingerprint(&[repo_id, "ics-service-exposed", &target]);
let mut f = Finding::new(
repo_id.to_string(),
fp,
"ics-probe".to_string(),
ScanType::IcsProbe,
title,
description,
severity,
);
f.rule_id = Some("ics-service-exposed".to_string());
f.cwe = Some(cwe.to_string());
f.remediation = Some(
"Restrict the service to a trusted network segment; disable it if unused; \
replace cleartext protocols (Telnet/FTP) with SSH/SFTP."
.to_string(),
);
f
})
.collect()
}
/// Extract `(host, port)` from a target reference. Modbus lives on its own port
/// (502 by default), independent of any HTTP/WebVisu URL, so unless the reference
/// explicitly carries `modbus://host:port` or a bare `host:port`, we probe 502.
fn parse_endpoint(endpoint: &str) -> (String, u16) {
let s = endpoint.trim();
let (scheme, rest) = match s.split_once("://") {
Some((sch, r)) => (Some(sch.to_ascii_lowercase()), r),
None => (None, s),
};
let hostport = rest.split(['/', '?']).next().unwrap_or(rest);
let (host, port) = match hostport.rsplit_once(':') {
Some((h, p)) => (h.to_string(), p.parse::<u16>().ok()),
None => (hostport.to_string(), None),
};
let port = match (scheme.as_deref(), port) {
// Explicit Modbus port, or a bare host:port the user chose.
(Some("modbus"), Some(p)) | (None, Some(p)) => p,
// An http(s)/WebVisu URL (or no port): Modbus is on its own port.
_ => MODBUS_PORT,
};
(host, port)
}
#[cfg(test)]
mod tests {
use super::parse_endpoint;
#[test]
fn endpoint_parsing_picks_the_modbus_port() {
assert_eq!(parse_endpoint("10.0.0.5"), ("10.0.0.5".into(), 502));
assert_eq!(parse_endpoint("10.0.0.5:1502"), ("10.0.0.5".into(), 1502));
assert_eq!(
parse_endpoint("modbus://plc.local:5020"),
("plc.local".into(), 5020)
);
// A WebVisu URL: the http port is ignored; Modbus is on 502.
assert_eq!(
parse_endpoint("http://plc.local:8080/webvisu"),
("plc.local".into(), 502)
);
assert_eq!(
parse_endpoint("https://plc.local/"),
("plc.local".into(), 502)
);
}
}
+262
View File
@@ -0,0 +1,262 @@
//! Minimal Modbus/TCP client for dynamic ICS probing.
//!
//! Modbus/TCP (port 502) has no authentication or encryption in the protocol, so
//! an endpoint that answers requests is, by design, open to any host that can
//! reach it. The probe only *reads* — a Read Holding Registers request and a Read
//! Device Identification request — and never writes to the live process.
use std::time::Duration;
use tokio::io::{AsyncReadExt, AsyncWriteExt};
use tokio::net::TcpStream;
use tokio::time::timeout;
/// Outcome of probing a Modbus/TCP endpoint.
#[derive(Debug, Default, PartialEq, Eq)]
pub struct ModbusProbe {
/// A TCP connection to the port was established.
pub reachable: bool,
/// The endpoint answered a Modbus request (a normal reply or a Modbus
/// exception) — i.e. it speaks Modbus, unauthenticated.
pub speaks_modbus: bool,
/// Device identity, if disclosed via Read Device Identification (FC 43 / 14).
pub device: Option<DeviceId>,
/// Coils returned by a Read Coils of the first block, if that address range
/// exists. Coils are read/write process bits, so an exposed block is an
/// unauthenticated write surface on the live process.
pub coils_readable: Option<u16>,
/// Holding registers returned by a Read Holding Registers of the first block,
/// if that range exists. Holding registers are read/write process words.
pub holding_registers_readable: Option<u16>,
}
/// Vendor / product / revision from Read Device Identification.
#[derive(Debug, Default, PartialEq, Eq)]
pub struct DeviceId {
pub vendor: Option<String>,
pub product: Option<String>,
pub revision: Option<String>,
}
/// How many coils / holding registers to request when enumerating the exposed
/// process surface. Read-only: a normal reply means the block exists and is,
/// over unauthenticated Modbus/TCP, also writable.
const ENUM_QTY: u16 = 16;
/// Probe a Modbus/TCP endpoint. Read-only: issues Read Holding Registers, Read
/// Coils, and Read Device Identification requests; never writes to the device.
pub async fn probe(host: &str, port: u16, budget: Duration) -> ModbusProbe {
let mut out = ModbusProbe::default();
let Ok(Ok(mut stream)) = timeout(budget, TcpStream::connect((host, port))).await else {
return out; // unreachable
};
out.reachable = true;
// Read Holding Registers (FC 0x03), unit 1, addr 0 — a benign read that also
// enumerates the exposed register block.
let rhr = [0x03u8, 0x00, 0x00, (ENUM_QTY >> 8) as u8, ENUM_QTY as u8];
if let Some(resp) = txn(&mut stream, 1, &rhr, budget).await {
// A normal reply (0x03) or an exception (0x83) both prove it speaks Modbus.
if matches!(resp.first(), Some(0x03) | Some(0x83)) {
out.speaks_modbus = true;
}
if resp.first() == Some(&0x03) {
out.holding_registers_readable = Some(register_count_from_reply(&resp));
}
}
// Read Coils (FC 0x01), addr 0 — enumerates the exposed coil (bit) block.
let rc = [0x01u8, 0x00, 0x00, (ENUM_QTY >> 8) as u8, ENUM_QTY as u8];
if let Some(resp) = txn(&mut stream, 1, &rc, budget).await {
if matches!(resp.first(), Some(0x01) | Some(0x81)) {
out.speaks_modbus = true;
}
if resp.first() == Some(&0x01) {
out.coils_readable = Some(coil_count_from_reply(&resp));
}
}
// Read Device Identification (FC 0x2B / MEI 0x0E), basic (0x01), object 0.
let rdi = [0x2Bu8, 0x0E, 0x01, 0x00];
if let Some(resp) = txn(&mut stream, 1, &rdi, budget).await {
if resp.first() == Some(&0x2B) {
out.speaks_modbus = true;
out.device = parse_device_id(&resp);
}
}
out
}
/// Coils reported by a Read Coils reply `[0x01, byte_count, data…]` (8 per byte).
fn coil_count_from_reply(pdu: &[u8]) -> u16 {
pdu.get(1).map(|&b| u16::from(b) * 8).unwrap_or(0)
}
/// Registers reported by a Read Holding Registers reply `[0x03, byte_count,
/// data…]` (2 bytes per register).
fn register_count_from_reply(pdu: &[u8]) -> u16 {
pdu.get(1).map(|&b| u16::from(b) / 2).unwrap_or(0)
}
/// Send one Modbus PDU and return the response PDU (function code + data), or
/// `None` on timeout / malformed reply.
async fn txn(stream: &mut TcpStream, unit: u8, pdu: &[u8], budget: Duration) -> Option<Vec<u8>> {
// MBAP header: transaction id (2) + protocol id (2) = 0 + length (2) + unit (1),
// then the PDU. `length` counts the unit byte plus the PDU.
let len = (pdu.len() + 1) as u16;
let mut frame = Vec::with_capacity(7 + pdu.len());
frame.extend_from_slice(&[0x00, 0x01]); // transaction id
frame.extend_from_slice(&[0x00, 0x00]); // protocol id
frame.extend_from_slice(&len.to_be_bytes());
frame.push(unit);
frame.extend_from_slice(pdu);
timeout(budget, stream.write_all(&frame)).await.ok()?.ok()?;
let mut hdr = [0u8; 7];
timeout(budget, stream.read_exact(&mut hdr))
.await
.ok()?
.ok()?;
// Reject non-Modbus replies (protocol id must be 0).
if hdr[2] != 0 || hdr[3] != 0 {
return None;
}
let plen = u16::from_be_bytes([hdr[4], hdr[5]]) as usize;
if !(2..=260).contains(&plen) {
return None;
}
let mut body = vec![0u8; plen - 1]; // minus the unit id already in hdr[6]
timeout(budget, stream.read_exact(&mut body))
.await
.ok()?
.ok()?;
Some(body)
}
/// Parse vendor / product / revision from a Read Device Identification PDU:
/// `[0x2B, 0x0E, readDevIdCode, conformity, moreFollows, nextObjId, numObjects,
/// (objId, len, bytes…)…]`.
fn parse_device_id(pdu: &[u8]) -> Option<DeviceId> {
if pdu.len() < 7 {
return None;
}
let num = pdu[6] as usize;
let mut i = 7;
let mut dev = DeviceId::default();
for _ in 0..num {
if i + 2 > pdu.len() {
break;
}
let id = pdu[i];
let l = pdu[i + 1] as usize;
i += 2;
if i + l > pdu.len() {
break;
}
let val = String::from_utf8_lossy(&pdu[i..i + l]).trim().to_string();
i += l;
match id {
0x00 => dev.vendor = Some(val),
0x01 => dev.product = Some(val),
0x02 => dev.revision = Some(val),
_ => {}
}
}
if dev == DeviceId::default() {
None
} else {
Some(dev)
}
}
#[cfg(test)]
mod tests {
use super::*;
use tokio::net::TcpListener;
/// A one-shot mock Modbus/TCP server that answers a Read Holding Registers
/// request and a Read Device Identification request on one connection.
async fn mock_server(with_device: bool) -> std::net::SocketAddr {
let listener = TcpListener::bind("127.0.0.1:0").await.expect("bind");
let addr = listener.local_addr().expect("addr");
tokio::spawn(async move {
let (mut sock, _) = listener.accept().await.expect("accept");
loop {
let mut hdr = [0u8; 7];
if sock.read_exact(&mut hdr).await.is_err() {
break;
}
let plen = u16::from_be_bytes([hdr[4], hdr[5]]) as usize;
let mut pdu = vec![0u8; plen - 1];
if sock.read_exact(&mut pdu).await.is_err() {
break;
}
let reply_pdu: Vec<u8> = match pdu.first() {
Some(0x03) => vec![0x03, 0x02, 0x00, 0x00], // 1 register (byte_count 2)
Some(0x01) => vec![0x01, 0x02, 0xFF, 0xFF], // 16 coils (byte_count 2)
Some(0x2B) if with_device => vec![
0x2B, 0x0E, 0x01, 0x81, 0x00, 0x00, 0x02, // 2 objects
0x00, 0x04, b'A', b'C', b'M', b'E', // vendor
0x01, 0x03, b'P', b'L', b'C', // product
],
_ => vec![pdu[0] | 0x80, 0x01], // exception
};
let len = (reply_pdu.len() + 1) as u16;
let mut frame = vec![hdr[0], hdr[1], 0x00, 0x00];
frame.extend_from_slice(&len.to_be_bytes());
frame.push(hdr[6]);
frame.extend_from_slice(&reply_pdu);
if sock.write_all(&frame).await.is_err() {
break;
}
}
});
addr
}
#[tokio::test]
async fn probe_detects_a_modbus_endpoint_and_reads_device_id() {
let addr = mock_server(true).await;
let p = probe(&addr.ip().to_string(), addr.port(), Duration::from_secs(2)).await;
assert!(p.reachable && p.speaks_modbus);
let dev = p.device.expect("device id");
assert_eq!(dev.vendor.as_deref(), Some("ACME"));
assert_eq!(dev.product.as_deref(), Some("PLC"));
}
#[tokio::test]
async fn probe_enumerates_exposed_process_points() {
let addr = mock_server(false).await;
let p = probe(&addr.ip().to_string(), addr.port(), Duration::from_secs(2)).await;
assert!(p.speaks_modbus);
// The mock returns a 2-byte holding-register block (1 register) and a
// 2-byte coil block (16 coils).
assert_eq!(p.holding_registers_readable, Some(1));
assert_eq!(p.coils_readable, Some(16));
}
#[test]
fn reply_counts_decode_byte_counts() {
assert_eq!(register_count_from_reply(&[0x03, 0x08]), 4); // 8 bytes → 4 regs
assert_eq!(coil_count_from_reply(&[0x01, 0x03]), 24); // 3 bytes → 24 coils
assert_eq!(register_count_from_reply(&[0x03]), 0); // malformed → 0
}
#[tokio::test]
async fn probe_reports_unreachable_for_a_closed_port() {
// 127.0.0.1:1 is (almost certainly) closed.
let p = probe("127.0.0.1", 1, Duration::from_millis(500)).await;
assert!(!p.reachable && !p.speaks_modbus);
}
#[test]
fn parses_device_identification_objects() {
let pdu = [
0x2B, 0x0E, 0x01, 0x81, 0x00, 0x00, 0x01, // 1 object
0x02, 0x05, b'v', b'1', b'.', b'2', b'3', // revision
];
let dev = parse_device_id(&pdu).expect("device");
assert_eq!(dev.revision.as_deref(), Some("v1.23"));
assert!(dev.vendor.is_none());
}
}
+131
View File
@@ -0,0 +1,131 @@
//! Minimal OPC UA reachability probe.
//!
//! Speaks just the OPC UA Connection Protocol (UACP) handshake — a `HEL` (Hello)
//! message, expecting an `ACK` (or `ERR`) reply — to confirm an OPC UA server is
//! listening (default port 4840). It does **not** open a secure channel or make
//! service calls; deep analysis of the server's SecurityPolicy / user-token
//! policies (the common `None` + `Anonymous` misconfiguration) is a follow-on best
//! done with a full OPC UA stack.
use std::time::Duration;
use tokio::io::{AsyncReadExt, AsyncWriteExt};
use tokio::net::TcpStream;
use tokio::time::timeout;
/// Outcome of an OPC UA handshake probe.
#[derive(Debug, Default, PartialEq, Eq)]
pub struct OpcUaProbe {
/// A TCP connection to the port was established.
pub reachable: bool,
/// The endpoint replied to the UACP Hello (`ACK`) or rejected it (`ERR`) —
/// either way it speaks OPC UA.
pub is_opcua: bool,
}
/// Probe an OPC UA endpoint with a UACP Hello. Read-only handshake only.
pub async fn probe(host: &str, port: u16, budget: Duration) -> OpcUaProbe {
let mut out = OpcUaProbe::default();
let Ok(Ok(mut stream)) = timeout(budget, TcpStream::connect((host, port))).await else {
return out;
};
out.reachable = true;
let hello = hello_message(&format!("opc.tcp://{host}:{port}"));
if timeout(budget, stream.write_all(&hello))
.await
.ok()
.and_then(Result::ok)
.is_none()
{
return out;
}
// Read the 3-byte message type of the reply: ACK (accepted) or ERR (rejected
// our hello) both prove the peer speaks the OPC UA connection protocol.
let mut mt = [0u8; 3];
if timeout(budget, stream.read_exact(&mut mt))
.await
.ok()
.and_then(Result::ok)
.is_none()
{
return out;
}
if &mt == b"ACK" || &mt == b"ERR" {
out.is_opcua = true;
}
out
}
/// Build a UACP `HEL` (Hello) message advertising our buffer sizes + endpoint URL.
fn hello_message(endpoint_url: &str) -> Vec<u8> {
let url = endpoint_url.as_bytes();
let mut m = Vec::with_capacity(32 + url.len());
m.extend_from_slice(b"HELF");
m.extend_from_slice(&0u32.to_le_bytes()); // message size — patched below
m.extend_from_slice(&0u32.to_le_bytes()); // ProtocolVersion
m.extend_from_slice(&65536u32.to_le_bytes()); // ReceiveBufferSize
m.extend_from_slice(&65536u32.to_le_bytes()); // SendBufferSize
m.extend_from_slice(&0u32.to_le_bytes()); // MaxMessageSize (0 = no limit)
m.extend_from_slice(&0u32.to_le_bytes()); // MaxChunkCount
m.extend_from_slice(&(url.len() as i32).to_le_bytes()); // EndpointUrl length
m.extend_from_slice(url);
let size = m.len() as u32;
m[4..8].copy_from_slice(&size.to_le_bytes());
m
}
#[cfg(test)]
mod tests {
use super::*;
use tokio::net::TcpListener;
/// A mock OPC UA server that reads the Hello and replies with an `ACK` frame.
async fn mock_server() -> std::net::SocketAddr {
let listener = TcpListener::bind("127.0.0.1:0").await.expect("bind");
let addr = listener.local_addr().expect("addr");
tokio::spawn(async move {
let (mut sock, _) = listener.accept().await.expect("accept");
// Read the Hello header (8 bytes) to learn the size, then drain it.
let mut hdr = [0u8; 8];
if sock.read_exact(&mut hdr).await.is_err() {
return;
}
let size = u32::from_le_bytes([hdr[4], hdr[5], hdr[6], hdr[7]]) as usize;
let mut rest = vec![0u8; size.saturating_sub(8)];
let _ = sock.read_exact(&mut rest).await;
// Reply: ACK + size + 5 u32 fields.
let mut ack = Vec::new();
ack.extend_from_slice(b"ACKF");
ack.extend_from_slice(&28u32.to_le_bytes());
for _ in 0..5 {
ack.extend_from_slice(&0u32.to_le_bytes());
}
let _ = sock.write_all(&ack).await;
});
addr
}
#[tokio::test]
async fn probe_detects_an_opcua_server() {
let addr = mock_server().await;
let p = probe(&addr.ip().to_string(), addr.port(), Duration::from_secs(2)).await;
assert!(p.reachable && p.is_opcua);
}
#[tokio::test]
async fn probe_reports_unreachable_for_a_closed_port() {
let p = probe("127.0.0.1", 1, Duration::from_millis(500)).await;
assert!(!p.reachable && !p.is_opcua);
}
#[test]
fn hello_message_is_well_formed() {
let m = hello_message("opc.tcp://h:4840");
assert_eq!(&m[0..4], b"HELF");
// The embedded size equals the actual length.
let size = u32::from_le_bytes([m[4], m[5], m[6], m[7]]) as usize;
assert_eq!(size, m.len());
}
}
@@ -0,0 +1,137 @@
//! TCP service discovery for a device.
//!
//! Connect-scans a curated set of OT/ICS and insecure-management ports and reports
//! the ones that are open. The deep protocol probes own Modbus (502), OPC UA
//! (4840) and EtherNet/IP (44818); this surfaces the *rest* of the industrial and
//! cleartext-management surface (Siemens S7, DNP3, CODESYS programming, Telnet, …).
use std::time::Duration;
use futures_util::future::join_all;
use tokio::net::TcpStream;
use tokio::time::timeout;
/// Whether an open port is an industrial protocol or an insecure management service.
#[derive(Debug, Clone, Copy, PartialEq, Eq)]
pub enum PortKind {
/// An industrial control protocol (typically unauthenticated).
Ics,
/// A cleartext management service (credentials/data in the clear).
InsecureMgmt,
}
/// A well-known port worth flagging when open.
#[derive(Debug, Clone, Copy)]
pub struct KnownPort {
pub port: u16,
pub service: &'static str,
pub kind: PortKind,
pub note: &'static str,
}
/// The curated scan list. Excludes 502 / 4840 / 44818 — those have dedicated deep
/// probes (Modbus, OPC UA, EtherNet/IP) that report richer findings.
pub const KNOWN_PORTS: &[KnownPort] = &[
KnownPort {
port: 102,
service: "S7comm / ISO-TSAP",
kind: PortKind::Ics,
note: "Siemens S7 PLC communication",
},
KnownPort {
port: 20000,
service: "DNP3",
kind: PortKind::Ics,
note: "SCADA / DNP3",
},
KnownPort {
port: 1911,
service: "Niagara Fox",
kind: PortKind::Ics,
note: "Tridium Niagara building automation",
},
KnownPort {
port: 11740,
service: "CODESYS",
kind: PortKind::Ics,
note: "CODESYS programming protocol",
},
KnownPort {
port: 1962,
service: "PCWorx",
kind: PortKind::Ics,
note: "Phoenix Contact PCWorx",
},
KnownPort {
port: 9600,
service: "OMRON FINS",
kind: PortKind::Ics,
note: "Omron FINS",
},
KnownPort {
port: 789,
service: "Red Lion Crimson",
kind: PortKind::Ics,
note: "Red Lion controllers",
},
KnownPort {
port: 23,
service: "Telnet",
kind: PortKind::InsecureMgmt,
note: "cleartext remote shell",
},
KnownPort {
port: 21,
service: "FTP",
kind: PortKind::InsecureMgmt,
note: "cleartext file transfer",
},
];
/// Connect-scan `ports` on `host` (concurrently) and return those that accept a
/// TCP connection.
pub async fn scan<'a>(host: &str, ports: &'a [KnownPort], budget: Duration) -> Vec<&'a KnownPort> {
let checks = ports.iter().map(|kp| async move {
let open = timeout(budget, TcpStream::connect((host, kp.port)))
.await
.map(|r| r.is_ok())
.unwrap_or(false);
(kp, open)
});
join_all(checks)
.await
.into_iter()
.filter_map(|(kp, open)| open.then_some(kp))
.collect()
}
#[cfg(test)]
mod tests {
use super::*;
use tokio::net::TcpListener;
#[tokio::test]
async fn scan_reports_only_open_ports() {
// Bind one port (open) and pick another that is closed.
let listener = TcpListener::bind("127.0.0.1:0").await.expect("bind");
let open_port = listener.local_addr().expect("addr").port();
let ports = [
KnownPort {
port: open_port,
service: "test-open",
kind: PortKind::Ics,
note: "",
},
KnownPort {
port: 1,
service: "test-closed",
kind: PortKind::InsecureMgmt,
note: "",
},
];
let found = scan("127.0.0.1", &ports, Duration::from_millis(500)).await;
let services: Vec<&str> = found.iter().map(|p| p.service).collect();
assert_eq!(services, vec!["test-open"]);
}
}
@@ -1,5 +1,6 @@
use mongodb::bson::doc;
use crate::pipeline::repo_view::RepoView;
use compliance_core::models::*;
use super::orchestrator::{extract_base_url, PipelineOrchestrator};
@@ -10,7 +11,7 @@ use crate::trackers;
impl PipelineOrchestrator {
/// Build an issue tracker client from a repository's tracker configuration.
/// Returns `None` if the repo has no tracker configured.
pub(super) fn build_tracker(&self, repo: &TrackedRepository) -> Option<TrackerDispatch> {
pub(super) fn build_tracker(&self, repo: &RepoView) -> Option<TrackerDispatch> {
let tracker_type = repo.tracker_type.as_ref()?;
// Per-repo token takes precedence, fall back to global config
match tracker_type {
@@ -81,7 +82,7 @@ impl PipelineOrchestrator {
#[tracing::instrument(skip_all, fields(repo_id = %repo_id))]
pub(super) async fn create_tracker_issues(
&self,
repo: &TrackedRepository,
repo: &RepoView,
repo_id: &str,
new_findings: &[Finding],
) -> Result<(), AgentError> {
+5
View File
@@ -1,14 +1,19 @@
pub mod code_review;
pub mod cve;
pub mod dedup;
pub mod firmware_sbom;
pub mod git;
pub mod gitleaks;
mod graph_build;
pub mod ics;
mod issue_creation;
pub mod lint;
pub mod orchestrator;
pub mod patterns;
pub mod plan;
pub mod plc;
mod pr_review;
pub mod repo_view;
pub mod sbom;
pub mod semgrep;
mod tracker_dispatch;
+778 -138
View File
@@ -15,6 +15,8 @@ use crate::pipeline::git::GitOps;
use crate::pipeline::gitleaks::GitleaksScanner;
use crate::pipeline::lint::LintScanner;
use crate::pipeline::patterns::{GdprPatternScanner, OAuthPatternScanner};
use crate::pipeline::plan::build_scan_plan;
use crate::pipeline::repo_view::RepoView;
use crate::pipeline::sbom::SbomScanner;
use crate::pipeline::semgrep::SemgrepScanner;
@@ -50,72 +52,8 @@ impl PipelineOrchestrator {
}
}
#[tracing::instrument(skip_all, fields(repo_id = %repo_id, trigger = ?trigger))]
pub async fn run(&self, repo_id: &str, trigger: ScanTrigger) -> Result<(), AgentError> {
// Look up the repository
let repo = self
.db
.repositories()
.find_one(doc! { "_id": mongodb::bson::oid::ObjectId::parse_str(repo_id).map_err(|e| AgentError::Other(e.to_string()))? })
.await?
.ok_or_else(|| AgentError::Other(format!("Repository {repo_id} not found")))?;
// Create scan run
let scan_run = ScanRun::new(repo_id.to_string(), trigger);
let insert = self.db.scan_runs().insert_one(&scan_run).await?;
let scan_run_id = insert
.inserted_id
.as_object_id()
.map(|id| id.to_hex())
.unwrap_or_default();
let result = self.run_pipeline(&repo, &scan_run_id).await;
// Update scan run status
match &result {
Ok(count) => {
self.db
.scan_runs()
.update_one(
doc! { "_id": &insert.inserted_id },
doc! {
"$set": {
"status": "completed",
"current_phase": "completed",
"new_findings_count": *count as i64,
"completed_at": mongodb::bson::DateTime::now(),
}
},
)
.await?;
}
Err(e) => {
tracing::error!(repo_id, error = %e, "Scan pipeline failed");
self.db
.scan_runs()
.update_one(
doc! { "_id": &insert.inserted_id },
doc! {
"$set": {
"status": "failed",
"error_message": e.to_string(),
"completed_at": mongodb::bson::DateTime::now(),
}
},
)
.await?;
}
}
result.map(|_| ())
}
#[tracing::instrument(skip_all, fields(repo_id = repo.name.as_str()))]
async fn run_pipeline(
&self,
repo: &TrackedRepository,
scan_run_id: &str,
) -> Result<u32, AgentError> {
async fn run_pipeline(&self, repo: &RepoView, scan_run_id: &str) -> Result<u32, AgentError> {
let repo_id = repo.id.as_ref().map(|id| id.to_hex()).unwrap_or_default();
// Stage 0: Change detection
@@ -129,7 +67,6 @@ impl PipelineOrchestrator {
return Ok(0);
}
let current_sha = GitOps::get_head_sha(&repo_path)?;
let mut all_findings: Vec<Finding> = Vec::new();
// Stage 1: Semgrep SAST
@@ -322,68 +259,13 @@ impl PipelineOrchestrator {
.await?;
}
// Persist CVE alerts and create notifications
{
use compliance_core::models::notification::{parse_severity, CveNotification};
let repo_name = repo.name.clone();
let mut new_notif_count = 0u32;
for alert in &cve_alerts {
// Upsert the alert
let filter = doc! {
"cve_id": &alert.cve_id,
"repo_id": &alert.repo_id,
};
let update = mongodb::bson::to_document(alert)
.map(|d| doc! { "$set": d })
.unwrap_or_else(|_| doc! {});
self.db
.cve_alerts()
.update_one(filter, update)
.upsert(true)
// Persist CVE alerts and create notifications (shared with the PLC path).
let new_notif_count = self
.persist_cve_alerts(&repo_id, &repo.name, &cve_alerts)
.await?;
// Create notification (dedup by cve_id + repo + package + version)
let notif_filter = doc! {
"cve_id": &alert.cve_id,
"repo_id": &alert.repo_id,
"package_name": &alert.affected_package,
"package_version": &alert.affected_version,
};
let severity = parse_severity(alert.severity.as_deref(), alert.cvss_score);
let mut notification = CveNotification::new(
alert.cve_id.clone(),
repo_id.clone(),
repo_name.clone(),
alert.affected_package.clone(),
alert.affected_version.clone(),
severity,
);
notification.cvss_score = alert.cvss_score;
notification.summary = alert.summary.clone();
notification.url = Some(format!("https://osv.dev/vulnerability/{}", alert.cve_id));
let notif_update = doc! {
"$setOnInsert": mongodb::bson::to_bson(&notification).unwrap_or_default()
};
if let Ok(result) = self
.db
.cve_notifications()
.update_one(notif_filter, notif_update)
.upsert(true)
.await
{
if result.upserted_id.is_some() {
new_notif_count += 1;
}
}
}
if new_notif_count > 0 {
tracing::info!("[{repo_id}] Created {new_notif_count} CVE notification(s)");
}
}
// Stage 6: Issue Creation
tracing::info!("[{repo_id}] Stage 6: Issue Creation");
@@ -395,20 +277,9 @@ impl PipelineOrchestrator {
tracing::warn!("[{repo_id}] Issue creation failed: {e}");
}
// Stage 7: Update repository
self.db
.repositories()
.update_one(
doc! { "_id": repo.id },
doc! {
"$set": {
"last_scanned_commit": &current_sha,
"updated_at": mongodb::bson::DateTime::now(),
},
"$inc": { "findings_count": new_count as i64 },
},
)
.await?;
// The onboarded target's findings_count and the git artifact's
// last_scanned_commit watermark are persisted by `finalize_target` after
// `run_pipeline` returns.
// Stage 8: DAST (async, optional — only if a DastTarget is configured)
tracing::info!("[{repo_id}] Stage 8: Checking for DAST targets");
@@ -419,6 +290,728 @@ impl PipelineOrchestrator {
Ok(new_count)
}
/// Unified entry point (behind `UNIFIED_PIPELINE`): run a scan for an
/// `OnboardedTarget`. Mirrors [`Self::run`] but sources the target from
/// `onboarded_targets` and dispatches by the scan plan.
#[tracing::instrument(skip_all, fields(target_id = %target_id, trigger = ?trigger))]
pub async fn run_target(
&self,
target_id: &str,
trigger: ScanTrigger,
) -> Result<(), AgentError> {
let oid = mongodb::bson::oid::ObjectId::parse_str(target_id)
.map_err(|e| AgentError::Other(e.to_string()))?;
let target = self
.db
.onboarded_targets()
.find_one(doc! { "_id": oid })
.await?
.ok_or_else(|| AgentError::Other(format!("Onboarded target {target_id} not found")))?;
let scan_run = ScanRun::new(target_id.to_string(), trigger);
let insert = self.db.scan_runs().insert_one(&scan_run).await?;
let scan_run_id = insert
.inserted_id
.as_object_id()
.map(|id| id.to_hex())
.unwrap_or_default();
let result = self.run_target_pipeline(&target, &scan_run_id).await;
match &result {
Ok(count) => {
self.db
.scan_runs()
.update_one(
doc! { "_id": &insert.inserted_id },
doc! { "$set": {
"status": "completed",
"current_phase": "completed",
"new_findings_count": *count as i64,
"completed_at": mongodb::bson::DateTime::now(),
} },
)
.await?;
// Refresh the target's cached findings count. The shared pipeline
// (Stage 7) increments `repositories`, which the unified path does
// not use, so set the accurate total on the target itself.
let total = self
.db
.findings()
.count_documents(doc! { "repo_id": target_id })
.await
.unwrap_or(*count as u64);
self.db
.onboarded_targets()
.update_one(
doc! { "_id": oid },
doc! { "$set": {
"findings_count": total as i64,
"updated_at": mongodb::bson::DateTime::now(),
} },
)
.await?;
}
Err(e) => {
tracing::error!(target_id, error = %e, "Unified scan pipeline failed");
self.db
.scan_runs()
.update_one(
doc! { "_id": &insert.inserted_id },
doc! { "$set": {
"status": "failed",
"error_message": e.to_string(),
"completed_at": mongodb::bson::DateTime::now(),
} },
)
.await?;
}
}
result.map(|_| ())
}
/// Run the applicable scans for a target. For a code target this reuses the
/// full legacy pipeline over the code artifact (clone → SAST umbrella →
/// triage → persist → issues → DAST); firmware/PLC/mobile scanners are
/// follow-ups (#128/#129/#130). Returns the number of new findings.
async fn run_target_pipeline(
&self,
target: &OnboardedTarget,
scan_run_id: &str,
) -> Result<u32, AgentError> {
let target_id = target.id.map(|id| id.to_hex()).unwrap_or_default();
let plan = build_scan_plan(target);
tracing::info!(
target_id = %target_id,
target_type = %target.target_type,
planned_steps = plan.steps.len(),
"Unified pipeline: scan plan built"
);
// Ingest + classify (tramiton for firmware) and store the detected type.
self.classify_and_store(target, &target_id, scan_run_id)
.await;
// Provision a DAST target from a LiveUrl artifact so DAST fires for
// wizard-created targets, not just migrated ones.
self.ensure_dast_target(target, &plan).await;
// PLC/SPS targets: the control-logic scan consumes the PLC source (an
// uploaded PlcProject *or* a git repo / source archive of PLCopen XML / ST
// exports), so it takes over the code artifact — we don't also run the
// SAST pipeline over it. A PLC device is reachable, so DAST still runs
// against a WebVisu / exposed endpoint when one is provisioned.
let mut new_count = 0u32;
let plc = plan.has(ScanType::PlcControlLogic);
let ics = plan.has(ScanType::IcsProbe);
if plc {
new_count += self.run_plc_scan(target, &target_id, scan_run_id).await?;
// Provision-and-test (#183): with the control logic but no reachable
// device, instantiate it on an ephemeral soft-PLC and probe that
// instead of the customer's OT network. Opt-in (needs Docker) and only
// when there is no live URL to probe directly. Never fails the scan.
if self.config.plc_runtime.enabled && target.live_url().is_none() {
match self
.run_provisioned_plc_test(target, &target_id, scan_run_id)
.await
{
Ok(n) => new_count += n,
Err(e) => {
tracing::warn!(target_id = %target_id, error = %e, "provision-and-test failed")
}
}
}
}
if ics {
new_count += self.run_ics_probe(target, &target_id, scan_run_id).await?;
}
if plc || ics {
// PLC/SPS device: also DAST against a WebVisu / exposed endpoint, but
// only when DAST is actually planned — a device reachable only over an
// industrial protocol (e.g. modbus://) has no web surface to crawl, and
// running DAST there just fails at reconnaissance. Gating here (not only
// at provisioning) also stops a DAST target left over from an earlier
// run from re-triggering. The control-logic scan already consumed the
// code artifact, so the SAST pipeline is not re-run.
if plan.has(ScanType::Dast) {
self.update_phase(scan_run_id, "dast_scanning").await;
self.maybe_trigger_dast(&target_id, scan_run_id).await;
}
return Ok(new_count);
}
match target.code_artifact() {
Some(code) if code.kind == ArtifactKind::GitRepo => {
let repo = RepoView::from_target(target, code);
let n = self.run_pipeline(&repo, scan_run_id).await?;
self.finalize_target(target, &repo, n).await?;
new_count += n;
}
Some(_) => {
tracing::warn!(
target_id = %target_id,
"Unified pipeline: source-archive scanning not yet wired; skipping"
);
}
None => {
// No code to scan (a migrated DAST target). Firmware/mobile static
// scanners land in #128/#129; DAST for a running URL works when a
// DastTarget row exists (provisioned above from a LiveUrl, or from
// a migrated target).
tracing::info!(
target_id = %target_id,
"Unified pipeline: no code artifact; attempting DAST"
);
self.update_phase(scan_run_id, "dast_scanning").await;
self.maybe_trigger_dast(&target_id, scan_run_id).await;
}
}
Ok(new_count)
}
/// Analyze a PLC/SPS project (Structured Text / PLCopen XML) for
/// control-logic security issues and persist the new findings.
async fn run_plc_scan(
&self,
target: &OnboardedTarget,
target_id: &str,
scan_run_id: &str,
) -> Result<u32, AgentError> {
tracing::info!(target_id, "[{target_id}] PLC control-logic analysis");
self.update_phase(scan_run_id, "plc_analysis").await;
let ctx = crate::ingest::IngestContext::from_config(&self.config, target_id);
let ingest_set = crate::ingest::ingest_all(target, &ctx)?;
// Every PLC-source artifact on the target: dedicated PLC projects plus any
// code artifacts (git repo / source archive) holding PLCopen XML / ST
// exports. A target can carry several (e.g. one POU export per file).
let sources: Vec<&Artifact> = target
.artifacts
.iter()
.filter(|a| {
matches!(
a.kind,
ArtifactKind::PlcProject | ArtifactKind::GitRepo | ArtifactKind::SourceArchive
)
})
.collect();
if sources.is_empty() {
tracing::warn!(target_id, "PLC scan: no PLC source artifact");
return Ok(0);
}
let mut all_findings = Vec::new();
let mut all_sbom: Vec<SbomEntry> = Vec::new();
let mut sbom_seen = std::collections::BTreeSet::new();
for a in &sources {
let Some(path) = ingest_set.get(&a.id).and_then(|ia| ia.working_path.clone()) else {
continue;
};
all_findings.extend(crate::pipeline::plc::analyze_tree(&path, target_id));
// Control-application SBOM: CODESYS libraries + runtime from a
// `.projectarchive` (uploaded, or committed in the working tree).
let archive = a
.stored_path
.clone()
.unwrap_or_else(|| a.source_ref.clone());
for e in crate::pipeline::plc::sbom::collect_sbom(
std::path::Path::new(&archive),
&path,
target_id,
) {
if sbom_seen.insert((e.name.clone(), e.version.clone())) {
all_sbom.push(e);
}
}
}
tracing::info!(
target_id,
artifacts = sources.len(),
found = all_findings.len(),
"PLC control-logic analysis complete"
);
let mut new_count = 0u32;
for mut finding in all_findings {
finding.scan_run_id = Some(scan_run_id.to_string());
if self
.db
.findings()
.find_one(doc! { "fingerprint": &finding.fingerprint })
.await?
.is_none()
{
self.db.findings().insert_one(&finding).await?;
new_count += 1;
}
}
if !all_sbom.is_empty() {
if let Err(e) = self
.persist_control_app_sbom(target_id, &target.name, all_sbom)
.await
{
tracing::warn!(target_id, error = %e, "control-app SBOM persist failed");
}
}
Ok(new_count)
}
/// Provision-and-test (#183): instantiate the target's control logic on an
/// ephemeral soft-PLC (OpenPLC), start it, probe the provisioned Modbus
/// endpoint, and tear the instance down. Used when a PLC/SPS target has the
/// control logic but no reachable live device to probe directly. Guarded by
/// `plc_runtime.enabled` (needs Docker); persists the same [`ScanType::IcsProbe`]
/// findings as a live probe.
async fn run_provisioned_plc_test(
&self,
target: &OnboardedTarget,
target_id: &str,
scan_run_id: &str,
) -> Result<u32, AgentError> {
self.update_phase(scan_run_id, "plc_provision").await;
// Locate a loadable control-logic program among the PLC-source artifacts
// (same selection as the static PLC scan: dedicated PLC projects plus code
// artifacts holding PLCopen XML / ST exports).
let ctx = crate::ingest::IngestContext::from_config(&self.config, target_id);
let ingest_set = crate::ingest::ingest_all(target, &ctx)?;
let program = target
.artifacts
.iter()
.filter(|a| {
matches!(
a.kind,
ArtifactKind::PlcProject | ArtifactKind::GitRepo | ArtifactKind::SourceArchive
)
})
.find_map(|a| {
let path = ingest_set
.get(&a.id)
.and_then(|ia| ia.working_path.clone())?;
crate::pipeline::plc::runtime::extract_program(&path)
});
let Some(program) = program else {
tracing::info!(
target_id,
"provision-and-test: no loadable control-logic program"
);
return Ok(0);
};
let http = crate::pipeline::plc::runtime::http_client()?;
let provisioner =
crate::pipeline::plc::runtime::DockerSoftPlc::new(self.config.plc_runtime.clone());
let outcome = crate::pipeline::plc::runtime::provision_and_test(
&provisioner,
&http,
&self.config.plc_runtime,
&program,
target_id,
)
.await?;
tracing::info!(
target_id,
found = outcome.findings.len(),
dast = outcome.dast.is_some(),
"provision-and-test complete"
);
let mut new_count = 0u32;
for mut finding in outcome.findings {
finding.scan_run_id = Some(scan_run_id.to_string());
if self
.db
.findings()
.find_one(doc! { "fingerprint": &finding.fingerprint })
.await?
.is_none()
{
self.db.findings().insert_one(&finding).await?;
new_count += 1;
}
}
// Persist the DAST scan of the provisioned web endpoint, linked to this
// scan run (mirrors `maybe_trigger_dast`).
if let Some(dast) = outcome.dast {
let mut scan_run = dast.scan_run;
scan_run.sast_scan_run_id = Some(scan_run_id.to_string());
if let Err(e) = self.db.dast_scan_runs().insert_one(&scan_run).await {
tracing::warn!(target_id, error = %e, "failed to store provisioned DAST scan run");
}
for finding in &dast.findings {
if let Err(e) = self.db.dast_findings().insert_one(finding).await {
tracing::warn!(target_id, error = %e, "failed to store provisioned DAST finding");
}
}
}
Ok(new_count)
}
/// Probe a running PLC/SPS device over industrial protocols (Modbus/TCP, …)
/// and persist findings for exposed / unauthenticated control access. The
/// probe is read-only; it targets the Modbus port of the target's live URL.
async fn run_ics_probe(
&self,
target: &OnboardedTarget,
target_id: &str,
scan_run_id: &str,
) -> Result<u32, AgentError> {
self.update_phase(scan_run_id, "ics_probe").await;
let Some(endpoint) = target.live_url().map(|a| a.source_ref.clone()) else {
tracing::warn!(target_id, "ICS probe: no live URL");
return Ok(0);
};
// Short per-request budget so an unreachable device doesn't stall the scan.
let budget = std::time::Duration::from_secs(5);
let findings = crate::pipeline::ics::probe_target(&endpoint, target_id, budget).await;
tracing::info!(
target_id,
endpoint = %endpoint,
found = findings.len(),
"ICS probe complete"
);
let mut new_count = 0u32;
for mut finding in findings {
finding.scan_run_id = Some(scan_run_id.to_string());
if self
.db
.findings()
.find_one(doc! { "fingerprint": &finding.fingerprint })
.await?
.is_none()
{
self.db.findings().insert_one(&finding).await?;
new_count += 1;
}
}
Ok(new_count)
}
/// Store a control-application SBOM (CODESYS libraries + runtime) for a target
/// and match it against known CVEs. Scoped to `package_manager = "codesys"` so
/// it refreshes on re-scan and coexists with any firmware/source SBOM. The
/// runtime `Cmp*` / `3SLicense` components carry real CODESYS advisories, so
/// this is where PLC-device CVE coverage comes from.
async fn persist_control_app_sbom(
&self,
target_id: &str,
target_name: &str,
mut entries: Vec<SbomEntry>,
) -> Result<(), AgentError> {
if entries.is_empty() {
return Ok(());
}
self.db
.sbom_entries()
.delete_many(doc! { "repo_id": target_id, "package_manager": "codesys" })
.await?;
let cve_scanner = CveScanner::new(
self.http.clone(),
self.config.searxng_url.clone(),
self.config.nvd_api_key.as_ref().map(|k| {
use secrecy::ExposeSecret;
k.expose_secret().to_string()
}),
);
let mut alerts = match tokio::time::timeout(
std::time::Duration::from_secs(600),
cve_scanner.scan_dependencies(target_id, &mut entries),
)
.await
{
Ok(Ok(a)) => a,
Ok(Err(e)) => {
tracing::warn!(target_id, error = %e, "control-app CVE scan failed");
Vec::new()
}
Err(_) => {
tracing::warn!(target_id, "control-app CVE scan timed out");
Vec::new()
}
};
// OSV can't match `pkg:codesys/*` (no such ecosystem); CODESYS advisories
// live in NVD keyed by CPE + runtime version. Add those (best-effort).
if let Ok(codesys) = tokio::time::timeout(
std::time::Duration::from_secs(120),
cve_scanner.scan_codesys(target_id, &mut entries),
)
.await
{
alerts.extend(codesys);
} else {
tracing::warn!(target_id, "CODESYS CVE match timed out");
}
for entry in &entries {
let filter = doc! {
"repo_id": &entry.repo_id,
"name": &entry.name,
"version": &entry.version,
};
if let Ok(d) = mongodb::bson::to_document(entry) {
self.db
.sbom_entries()
.update_one(filter, doc! { "$set": d })
.upsert(true)
.await?;
}
}
let new_notifs = self
.persist_cve_alerts(target_id, target_name, &alerts)
.await?;
tracing::info!(
target_id,
components = entries.len(),
alerts = alerts.len(),
notifications = new_notifs,
"control-app SBOM stored"
);
Ok(())
}
/// Upsert CVE alerts for a target and create dedup'd CVE notifications;
/// returns the number of newly-created notifications. Shared by the SAST
/// pipeline and the PLC control-app SBOM path, so every SBOM source (source,
/// firmware, CODESYS libraries/runtime) raises the same notifications.
async fn persist_cve_alerts(
&self,
repo_id: &str,
repo_name: &str,
alerts: &[CveAlert],
) -> Result<u32, AgentError> {
use compliance_core::models::notification::{parse_severity, CveNotification};
let mut new_notif = 0u32;
for alert in alerts {
let filter = doc! { "cve_id": &alert.cve_id, "repo_id": &alert.repo_id };
let update = mongodb::bson::to_document(alert)
.map(|d| doc! { "$set": d })
.unwrap_or_else(|_| doc! {});
self.db
.cve_alerts()
.update_one(filter, update)
.upsert(true)
.await?;
// Dedup notifications by cve + repo + package + version.
let notif_filter = doc! {
"cve_id": &alert.cve_id,
"repo_id": &alert.repo_id,
"package_name": &alert.affected_package,
"package_version": &alert.affected_version,
};
let severity = parse_severity(alert.severity.as_deref(), alert.cvss_score);
let mut notification = CveNotification::new(
alert.cve_id.clone(),
repo_id.to_string(),
repo_name.to_string(),
alert.affected_package.clone(),
alert.affected_version.clone(),
severity,
);
notification.cvss_score = alert.cvss_score;
notification.summary = alert.summary.clone();
notification.url = Some(format!("https://osv.dev/vulnerability/{}", alert.cve_id));
let notif_update = doc! {
"$setOnInsert": mongodb::bson::to_bson(&notification).unwrap_or_default()
};
if let Ok(result) = self
.db
.cve_notifications()
.update_one(notif_filter, notif_update)
.upsert(true)
.await
{
if result.upserted_id.is_some() {
new_notif += 1;
}
}
}
Ok(new_notif)
}
/// Ingest the target's artifacts, classify (tramiton for firmware/RTOS/Yocto,
/// heuristics otherwise), and store the detected classification on the target.
/// Best-effort — never fails the scan.
async fn classify_and_store(
&self,
target: &OnboardedTarget,
target_id: &str,
scan_run_id: &str,
) {
self.update_phase(scan_run_id, "classification").await;
let ctx = crate::ingest::IngestContext::from_config(&self.config, target_id);
let ingest_set = match crate::ingest::ingest_all(target, &ctx) {
Ok(set) => set,
Err(e) => {
tracing::warn!(target_id, error = %e, "Unified pipeline: ingest for classification failed");
return;
}
};
let working_paths = ingest_set.working_paths();
match crate::classify::classify_target(
target,
&working_paths,
&crate::classify::TramitonNative,
)
.await
{
Ok(classification) => {
tracing::info!(
target_id,
suggested = %classification.suggested,
"Unified pipeline: classified target"
);
if let (Some(oid), Ok(bson)) = (target.id, mongodb::bson::to_bson(&classification))
{
let _ = self
.db
.onboarded_targets()
.update_one(
doc! { "_id": oid },
doc! { "$set": { "classification": bson } },
)
.await;
}
}
Err(e) => {
tracing::warn!(target_id, error = %e, "Unified pipeline: classification failed")
}
}
// Analysis-based firmware SBOM: for embedded targets, derive components
// (resolved libraries + cross-toolchain) from tramiton's build-plan
// analysis over the already-ingested source — no build, no binary
// upload. Best-effort; empty when no build plan forms.
if crate::pipeline::firmware_sbom::is_firmware_target(target.target_type) {
if let Some(code) = target.code_artifact() {
if let Some(path) = working_paths.get(&code.id) {
let entries =
crate::pipeline::firmware_sbom::firmware_sbom_entries(path, target_id)
.await;
if !entries.is_empty() {
let _ = self
.db
.sbom_entries()
.delete_many(doc! { "repo_id": target_id })
.await;
for entry in &entries {
let filter = doc! {
"repo_id": &entry.repo_id,
"name": &entry.name,
"version": &entry.version,
};
if let Ok(d) = mongodb::bson::to_document(entry) {
let _ = self
.db
.sbom_entries()
.update_one(filter, doc! { "$set": d })
.upsert(true)
.await;
}
}
tracing::info!(
target_id,
count = entries.len(),
"Firmware SBOM: stored components from tramiton analysis"
);
}
}
}
}
}
/// If the target has a `LiveUrl` artifact and DAST is planned, provision a
/// `DastTarget` (keyed by `repo_id` = target id) so the existing DAST trigger
/// fires for wizard-created targets. Idempotent.
async fn ensure_dast_target(
&self,
target: &OnboardedTarget,
plan: &crate::pipeline::plan::ScanPlan,
) {
if !plan.has(ScanType::Dast) {
return;
}
let (Some(url), Some(oid)) = (target.live_url(), target.id) else {
return;
};
let target_id = oid.to_hex();
if self
.db
.dast_targets()
.find_one(doc! { "repo_id": &target_id })
.await
.ok()
.flatten()
.is_some()
{
return; // already provisioned
}
let kind = url
.web
.as_ref()
.map(|w| w.target_kind.clone())
.unwrap_or(DastTargetType::WebApp);
let mut dast = DastTarget::new(target.name.clone(), url.source_ref.clone(), kind);
dast.repo_id = Some(target_id);
if let Some(web) = &url.web {
dast.excluded_paths = web.excluded_paths.clone();
dast.max_crawl_depth = web.max_crawl_depth;
dast.rate_limit = web.rate_limit;
dast.allow_destructive = web.allow_destructive;
}
if let Some(auth) = &url.auth {
dast.auth_config = Some(DastAuthConfig {
method: auth.method.clone(),
login_url: auth.login_url.clone(),
username: auth.username.clone(),
password: None,
token: auth.secret.clone(),
headers: auth.headers.clone(),
});
}
if let Err(e) = self.db.dast_targets().insert_one(&dast).await {
tracing::warn!(error = %e, "Unified pipeline: failed to provision DAST target");
}
}
/// Sync the onboarded-target document after a scan: bump `findings_count`
/// and advance the git artifact's `last_scanned_commit` watermark.
async fn finalize_target(
&self,
target: &OnboardedTarget,
repo: &RepoView,
new_count: u32,
) -> Result<(), AgentError> {
let oid = match target.id {
Some(id) => id,
None => return Ok(()),
};
self.db
.onboarded_targets()
.update_one(
doc! { "_id": oid },
doc! {
"$inc": { "findings_count": new_count as i64 },
"$set": { "updated_at": mongodb::bson::DateTime::now() },
},
)
.await?;
let repo_path = std::path::Path::new(&self.config.git_clone_base_path).join(&repo.name);
if let (Ok(sha), Some(code)) = (GitOps::get_head_sha(&repo_path), target.code_artifact()) {
self.db
.onboarded_targets()
.update_one(
doc! { "_id": oid, "artifacts.id": &code.id },
doc! { "$set": { "artifacts.$.git.last_scanned_commit": sha } },
)
.await?;
}
Ok(())
}
pub(super) async fn update_phase(&self, scan_run_id: &str, phase: &str) {
if let Ok(oid) = mongodb::bson::oid::ObjectId::parse_str(scan_run_id) {
let _ = self
@@ -460,3 +1053,50 @@ pub(super) fn extract_base_url(git_url: &str) -> Option<String> {
None
}
}
#[cfg(test)]
#[allow(clippy::expect_used, clippy::unwrap_used)]
mod tests {
use super::*;
use compliance_core::models::{
Artifact, ArtifactAuth, IssueTrackerConfig, TargetType, TrackerType,
};
#[test]
fn repo_view_preserves_id_git_auth_and_tracker() {
let mut target = OnboardedTarget::new("acme".to_string(), TargetType::WebApp);
target.id = Some(mongodb::bson::oid::ObjectId::new());
target.findings_count = 3;
target.scan_config.issue_tracker = Some(IssueTrackerConfig {
tracker_type: Some(TrackerType::Gitea),
owner: Some("acme".to_string()),
repo: Some("web".to_string()),
token: Some("tt".to_string()),
});
let mut artifact = Artifact::git_repo("https://git/acme.git", "develop");
if let Some(git) = artifact.git.as_mut() {
git.last_scanned_commit = Some("abc123".to_string());
}
artifact.auth = Some(ArtifactAuth {
method: "token".to_string(),
username: Some("bob".to_string()),
secret: Some("pat".to_string()),
..Default::default()
});
target.artifacts.push(artifact);
let code = target.code_artifact().expect("code artifact");
let repo = RepoView::from_target(&target, code);
assert_eq!(repo.id, target.id); // preserved
assert_eq!(repo.git_url, "https://git/acme.git");
assert_eq!(repo.default_branch, "develop");
assert_eq!(repo.last_scanned_commit.as_deref(), Some("abc123"));
assert_eq!(repo.auth_token.as_deref(), Some("pat"));
assert_eq!(repo.auth_username.as_deref(), Some("bob"));
assert_eq!(repo.tracker_type, Some(TrackerType::Gitea));
assert_eq!(repo.tracker_owner.as_deref(), Some("acme"));
assert_eq!(repo.findings_count, 3);
}
}
+1 -1
View File
@@ -215,7 +215,7 @@ fn scan_with_patterns(
repo_id.to_string(),
fingerprint,
scanner_name.to_string(),
scan_type.clone(),
scan_type,
pattern.title.clone(),
pattern.description.clone(),
pattern.severity.clone(),
+214
View File
@@ -0,0 +1,214 @@
//! The scan plan.
//!
//! [`build_scan_plan`] turns an [`OnboardedTarget`] into the concrete ordered
//! list of scans to run, each bound to the artifact it consumes. It intersects
//! the scan-applicability matrix ([`applicable_scans`]) with the target's
//! `scan_config` overrides: a scan runs when its required artifact is present and
//! it is either on by default or explicitly enabled, and is not explicitly
//! disabled. This is the decision engine the unified pipeline (`run_target`)
//! executes.
use compliance_core::models::{Artifact, ArtifactKind, OnboardedTarget, ScanPhase, ScanType};
use compliance_core::scan_matrix::applicable_scans;
/// One scan to run, bound to the artifact it operates on.
#[derive(Debug, Clone, PartialEq)]
pub struct ScanStep {
/// The scan to run.
pub scan_type: ScanType,
/// The pipeline phase to report while it runs.
pub phase: ScanPhase,
/// The id of the artifact this scan consumes ([`Artifact::id`]).
pub artifact_id: String,
}
/// The ordered set of scans to run for a target.
#[derive(Debug, Clone, Default, PartialEq)]
pub struct ScanPlan {
/// The scans, in matrix order.
pub steps: Vec<ScanStep>,
}
impl ScanPlan {
/// Whether the plan contains a step for the given scan type.
pub fn has(&self, scan: ScanType) -> bool {
self.steps.iter().any(|s| s.scan_type == scan)
}
/// Whether the plan is empty (nothing to run).
pub fn is_empty(&self) -> bool {
self.steps.is_empty()
}
}
/// Build the scan plan for a target: matrix defaults ∩ `scan_config`, each scan
/// bound to the artifact it consumes. Scans whose required artifact is absent, or
/// that are disabled, or off-by-default and not explicitly enabled, are dropped.
pub fn build_scan_plan(target: &OnboardedTarget) -> ScanPlan {
let enabled = &target.scan_config.enabled_scans;
let disabled = &target.scan_config.disabled_scans;
let mut steps = Vec::new();
for option in applicable_scans(target) {
// Required artifact missing → not runnable.
if option.blocked_reason.is_some() {
continue;
}
// Explicit opt-out wins.
if disabled.contains(&option.scan) {
continue;
}
// Run if on by default, or explicitly enabled.
if !option.default_on && !enabled.contains(&option.scan) {
continue;
}
let Some(artifact) = resolve_artifact(target, option.required_artifact) else {
continue;
};
steps.push(ScanStep {
scan_type: option.scan,
phase: phase_for(option.scan),
artifact_id: artifact.id.clone(),
});
}
ScanPlan { steps }
}
/// Resolve the artifact a scan consumes. A "code" requirement (represented by
/// `GitRepo`) is satisfied by a git repo *or* a source archive. The PLC
/// control-logic requirement (represented by `PlcProject`) prefers an uploaded
/// PLC project but also accepts a code artifact — a git repo / source archive
/// holding PLCopen XML / ST exports.
fn resolve_artifact(target: &OnboardedTarget, required: Option<ArtifactKind>) -> Option<&Artifact> {
match required {
Some(ArtifactKind::GitRepo) => target.code_artifact(),
Some(ArtifactKind::PlcProject) => target
.first_of(ArtifactKind::PlcProject)
.or_else(|| target.code_artifact()),
Some(kind) => target.first_of(kind),
None => target.code_artifact().or_else(|| target.artifacts.first()),
}
}
/// The pipeline phase reported while a given scan runs.
fn phase_for(scan: ScanType) -> ScanPhase {
match scan {
ScanType::Sast => ScanPhase::Sast,
ScanType::Sbom => ScanPhase::SbomGeneration,
ScanType::Cve => ScanPhase::CveScanning,
ScanType::Gdpr | ScanType::OAuth => ScanPhase::PatternScanning,
ScanType::SecretDetection => ScanPhase::SecretDetection,
ScanType::Lint => ScanPhase::LintScanning,
ScanType::CodeReview => ScanPhase::CodeReview,
ScanType::Graph => ScanPhase::GraphBuilding,
ScanType::Dast => ScanPhase::DastScanning,
ScanType::FirmwareStatic => ScanPhase::FirmwareStatic,
ScanType::PlcControlLogic => ScanPhase::PlcAnalysis,
ScanType::MobileStatic => ScanPhase::MobileStatic,
ScanType::ContainerScan => ScanPhase::ContainerScan,
ScanType::IcsProbe => ScanPhase::IcsProbe,
}
}
#[cfg(test)]
#[allow(clippy::expect_used, clippy::unwrap_used)]
mod tests {
use super::*;
use compliance_core::models::{PlcFormat, TargetType};
fn target(target_type: TargetType, artifacts: Vec<Artifact>) -> OnboardedTarget {
let mut t = OnboardedTarget::new("t".to_string(), target_type);
t.artifacts = artifacts;
t
}
fn step_for<'a>(plan: &'a ScanPlan, scan: ScanType) -> Option<&'a ScanStep> {
plan.steps.iter().find(|s| s.scan_type == scan)
}
#[test]
fn webapp_with_code_and_url_runs_sast_and_dast_bound_to_the_right_artifacts() {
let code = Artifact::git_repo("https://git/x", "main");
let url = Artifact::live_url("https://x");
let (code_id, url_id) = (code.id.clone(), url.id.clone());
let t = target(TargetType::WebApp, vec![code, url]);
let plan = build_scan_plan(&t);
let sast = step_for(&plan, ScanType::Sast).expect("sast planned");
assert_eq!(sast.artifact_id, code_id);
assert_eq!(sast.phase, ScanPhase::Sast);
let dast = step_for(&plan, ScanType::Dast).expect("dast planned");
assert_eq!(dast.artifact_id, url_id);
}
#[test]
fn webapp_without_url_omits_dast() {
let t = target(TargetType::WebApp, vec![Artifact::git_repo("u", "main")]);
let plan = build_scan_plan(&t);
assert!(plan.has(ScanType::Sast));
assert!(!plan.has(ScanType::Dast));
}
#[test]
fn code_scan_binds_to_source_archive_when_no_git_repo() {
let arc = Artifact::source_archive("src.zip");
let arc_id = arc.id.clone();
let t = target(TargetType::BackendService, vec![arc]);
let plan = build_scan_plan(&t);
let sast = step_for(&plan, ScanType::Sast).expect("sast planned");
assert_eq!(sast.artifact_id, arc_id);
}
#[test]
fn firmware_sbom_and_cve_bind_to_the_firmware_image() {
let fw = Artifact::firmware_image("fw.bin");
let fw_id = fw.id.clone();
let t = target(TargetType::FirmwareBareMetal, vec![fw]);
let plan = build_scan_plan(&t);
let sbom = step_for(&plan, ScanType::Sbom).expect("sbom planned");
assert_eq!(sbom.artifact_id, fw_id);
assert!(step_for(&plan, ScanType::FirmwareStatic).is_some());
assert!(!plan.has(ScanType::Dast));
}
#[test]
fn plc_plans_only_control_logic() {
let plc = Artifact::plc_project("p.xml", PlcFormat::PlcopenXml);
let t = target(TargetType::PlcSps, vec![plc]);
let plan = build_scan_plan(&t);
assert_eq!(plan.steps.len(), 1);
assert_eq!(plan.steps[0].scan_type, ScanType::PlcControlLogic);
assert_eq!(plan.steps[0].phase, ScanPhase::PlcAnalysis);
}
#[test]
fn plc_control_logic_binds_to_a_git_repo() {
// A CODESYS project in git (PLCopen XML / ST exports) with no uploaded
// PlcProject: control-logic still plans, bound to the git artifact.
let git = Artifact::git_repo("https://git/plc", "main");
let git_id = git.id.clone();
let t = target(TargetType::PlcSps, vec![git]);
let plan = build_scan_plan(&t);
let step = step_for(&plan, ScanType::PlcControlLogic).expect("control-logic planned");
assert_eq!(step.artifact_id, git_id, "PLC scan binds to the git repo");
}
#[test]
fn disabled_scan_is_dropped_and_off_by_default_can_be_enabled() {
let mut t = target(TargetType::WebApp, vec![Artifact::git_repo("u", "main")]);
t.scan_config.disabled_scans = vec![ScanType::Lint];
// CodeReview is off by default for web; enable it explicitly.
t.scan_config.enabled_scans = vec![ScanType::CodeReview];
let plan = build_scan_plan(&t);
assert!(!plan.has(ScanType::Lint));
assert!(plan.has(ScanType::CodeReview));
assert!(plan.has(ScanType::Sast));
}
#[test]
fn no_code_artifact_yields_empty_plan_for_web() {
let t = target(TargetType::WebApp, vec![]);
let plan = build_scan_plan(&t);
assert!(plan.is_empty());
}
}
+226
View File
@@ -0,0 +1,226 @@
//! Abstract syntax tree for IEC 61131-3 Structured Text (ST).
//!
//! This is the security-relevant subset: POUs with their variable declarations
//! and statement bodies, enough to run semantic control-logic rules over. It is
//! deliberately not a full language model — declarations we don't reason about
//! (e.g. exotic type definitions) are parsed loosely and kept as raw text.
/// A Program Organization Unit: a PROGRAM, FUNCTION, or FUNCTION_BLOCK.
#[derive(Debug, Clone)]
pub struct Pou {
pub name: String,
pub kind: PouKind,
/// The declared variables, across all VAR_* sections.
pub vars: Vec<VarDecl>,
/// The statement body.
pub body: Vec<Stmt>,
/// 1-based line where the POU header appears (in the source that was parsed).
pub line: u32,
}
#[derive(Debug, Clone, Copy, PartialEq, Eq)]
pub enum PouKind {
Program,
Function,
FunctionBlock,
}
impl PouKind {
pub fn label(self) -> &'static str {
match self {
PouKind::Program => "PROGRAM",
PouKind::Function => "FUNCTION",
PouKind::FunctionBlock => "FUNCTION_BLOCK",
}
}
}
/// A single declared variable.
#[derive(Debug, Clone)]
pub struct VarDecl {
pub name: String,
pub section: VarSection,
/// The declared type as written (e.g. `BOOL`, `INT`, `ARRAY[0..9] OF INT`).
pub type_name: String,
/// Whether the type is an ARRAY, and its declared bounds `(lo, hi)` when
/// they are literal integers — used by the array-bounds rule.
pub array_bounds: Option<(i64, i64)>,
/// The initializer expression, if any (`:= <expr>`).
pub init: Option<Expr>,
pub line: u32,
}
#[derive(Debug, Clone, Copy, PartialEq, Eq)]
pub enum VarSection {
Var,
Input,
Output,
InOut,
Global,
Temp,
External,
}
/// A statement.
#[derive(Debug, Clone)]
pub enum Stmt {
Assign {
target: Expr,
value: Expr,
line: u32,
},
If {
/// (condition, body) for IF and each ELSIF, in order.
branches: Vec<(Expr, Vec<Stmt>)>,
else_body: Option<Vec<Stmt>>,
line: u32,
},
Case {
selector: Expr,
/// (label expressions, body) per CASE arm.
arms: Vec<(Vec<Expr>, Vec<Stmt>)>,
else_body: Option<Vec<Stmt>>,
line: u32,
},
For {
var: String,
from: Expr,
to: Expr,
by: Option<Expr>,
body: Vec<Stmt>,
line: u32,
},
While {
cond: Expr,
body: Vec<Stmt>,
line: u32,
},
Repeat {
body: Vec<Stmt>,
until: Expr,
line: u32,
},
/// A bare call statement, e.g. `TON1(IN := x, PT := T#5s);`.
Call {
callee: String,
args: Vec<CallArg>,
line: u32,
},
Return {
line: u32,
},
Exit {
line: u32,
},
/// `JMP label;` — an unstructured jump.
Jump {
label: String,
line: u32,
},
/// `label:` — a jump target.
Label {
name: String,
line: u32,
},
}
/// One argument in a call: positional (`name: None`) or named (`X := expr`).
#[derive(Debug, Clone)]
pub struct CallArg {
pub name: Option<String>,
pub value: Expr,
}
/// An expression.
#[derive(Debug, Clone)]
pub enum Expr {
Int(i64, u32),
Real(f64, u32),
Bool(bool, u32),
/// A string literal, with the unquoted contents.
Str(String, u32),
/// A duration / date / time literal, kept as raw text (`T#5s`, `DT#...`).
Time(String, u32),
Ident(String, u32),
/// `base[index]`.
Index {
base: Box<Expr>,
index: Box<Expr>,
line: u32,
},
/// `base.field`.
Member {
base: Box<Expr>,
field: String,
line: u32,
},
Unary {
op: UnOp,
expr: Box<Expr>,
line: u32,
},
Binary {
op: BinOp,
lhs: Box<Expr>,
rhs: Box<Expr>,
line: u32,
},
/// A function call used as an expression, e.g. `LIMIT(a, b, c)`.
Call {
callee: String,
args: Vec<CallArg>,
line: u32,
},
}
impl Expr {
/// The 1-based source line this expression starts on.
pub fn line(&self) -> u32 {
match self {
Expr::Int(_, l)
| Expr::Real(_, l)
| Expr::Bool(_, l)
| Expr::Str(_, l)
| Expr::Time(_, l)
| Expr::Ident(_, l)
| Expr::Index { line: l, .. }
| Expr::Member { line: l, .. }
| Expr::Unary { line: l, .. }
| Expr::Binary { line: l, .. }
| Expr::Call { line: l, .. } => *l,
}
}
/// If this expression is a plain identifier, its name.
pub fn as_ident(&self) -> Option<&str> {
match self {
Expr::Ident(name, _) => Some(name.as_str()),
_ => None,
}
}
}
#[derive(Debug, Clone, Copy, PartialEq, Eq)]
pub enum UnOp {
Not,
Neg,
}
#[derive(Debug, Clone, Copy, PartialEq, Eq)]
pub enum BinOp {
Add,
Sub,
Mul,
Div,
Mod,
Pow,
Eq,
Ne,
Lt,
Le,
Gt,
Ge,
And,
Or,
Xor,
}
+372
View File
@@ -0,0 +1,372 @@
//! Lexer for IEC 61131-3 Structured Text.
//!
//! Tokenizes ST source into a flat token stream with 1-based line numbers.
//! Keywords are case-insensitive. Handles `(* *)` and `//` comments, `'..'` and
//! `".."` strings (with `''`/`""` escapes), based integers (`16#FF`, `2#1010`),
//! and duration/date literals (`T#5s`, `DT#...`) kept as raw text.
/// A lexed token with its source line.
#[derive(Debug, Clone)]
pub struct Token {
pub kind: Tok,
pub line: u32,
}
#[derive(Debug, Clone, PartialEq)]
pub enum Tok {
Int(i64),
Real(f64),
Str(String),
Time(String),
Bool(bool),
Ident(String),
Kw(Keyword),
Assign, // :=
Plus, // +
Minus, // -
Star, // *
Slash, // /
Power, // **
LParen, // (
RParen, // )
LBrack, // [
RBrack, // ]
Dot, // .
DotDot, // ..
Comma, // ,
Semi, // ;
Colon, // :
Lt, // <
Le, // <=
Gt, // >
Ge, // >=
Eq, // =
Ne, // <>
Amp, // &
Eof,
}
#[derive(Debug, Clone, Copy, PartialEq, Eq)]
pub enum Keyword {
Program,
EndProgram,
Function,
EndFunction,
FunctionBlock,
EndFunctionBlock,
Var,
VarInput,
VarOutput,
VarInOut,
VarGlobal,
VarTemp,
VarExternal,
Constant,
EndVar,
Array,
Of,
If,
Then,
Elsif,
Else,
EndIf,
Case,
EndCase,
For,
To,
By,
Do,
EndFor,
While,
EndWhile,
Repeat,
Until,
EndRepeat,
Return,
Exit,
Jmp,
Not,
And,
Or,
Xor,
Mod,
Type,
EndType,
Struct,
EndStruct,
}
fn keyword_from(word: &str) -> Option<Keyword> {
use Keyword::*;
Some(match word.to_ascii_uppercase().as_str() {
"PROGRAM" => Program,
"END_PROGRAM" => EndProgram,
"FUNCTION" => Function,
"END_FUNCTION" => EndFunction,
"FUNCTION_BLOCK" => FunctionBlock,
"END_FUNCTION_BLOCK" => EndFunctionBlock,
"VAR" => Var,
"VAR_INPUT" => VarInput,
"VAR_OUTPUT" => VarOutput,
"VAR_IN_OUT" => VarInOut,
"VAR_GLOBAL" => VarGlobal,
"VAR_TEMP" => VarTemp,
"VAR_EXTERNAL" => VarExternal,
"CONSTANT" => Constant,
"END_VAR" => EndVar,
"ARRAY" => Array,
"OF" => Of,
"IF" => If,
"THEN" => Then,
"ELSIF" => Elsif,
"ELSE" => Else,
"END_IF" => EndIf,
"CASE" => Case,
"END_CASE" => EndCase,
"FOR" => For,
"TO" => To,
"BY" => By,
"DO" => Do,
"END_FOR" => EndFor,
"WHILE" => While,
"END_WHILE" => EndWhile,
"REPEAT" => Repeat,
"UNTIL" => Until,
"END_REPEAT" => EndRepeat,
"RETURN" => Return,
"EXIT" => Exit,
"JMP" => Jmp,
"NOT" => Not,
"AND" => And,
"OR" => Or,
"XOR" => Xor,
"MOD" => Mod,
"TYPE" => Type,
"END_TYPE" => EndType,
"STRUCT" => Struct,
"END_STRUCT" => EndStruct,
_ => return None,
})
}
/// Tokenize `src`. Unknown characters are skipped (best-effort — a scanner must
/// not die on odd input).
pub fn lex(src: &str) -> Vec<Token> {
let chars: Vec<char> = src.chars().collect();
let mut i = 0usize;
let mut line = 1u32;
let mut out = Vec::new();
let bump_line = |c: char, line: &mut u32| {
if c == '\n' {
*line += 1;
}
};
while i < chars.len() {
let c = chars[i];
// Whitespace.
if c.is_whitespace() {
bump_line(c, &mut line);
i += 1;
continue;
}
// Line comment: //
if c == '/' && i + 1 < chars.len() && chars[i + 1] == '/' {
while i < chars.len() && chars[i] != '\n' {
i += 1;
}
continue;
}
// Block comment: (* ... *)
if c == '(' && i + 1 < chars.len() && chars[i + 1] == '*' {
i += 2;
while i + 1 < chars.len() && !(chars[i] == '*' && chars[i + 1] == ')') {
bump_line(chars[i], &mut line);
i += 1;
}
i = (i + 2).min(chars.len());
continue;
}
let tok_line = line;
// String literal: '...' or "..."
if c == '\'' || c == '"' {
let quote = c;
i += 1;
let mut s = String::new();
while i < chars.len() {
let ch = chars[i];
if ch == quote {
// Doubled quote is an escaped quote.
if i + 1 < chars.len() && chars[i + 1] == quote {
s.push(quote);
i += 2;
continue;
}
i += 1;
break;
}
bump_line(ch, &mut line);
s.push(ch);
i += 1;
}
out.push(Token {
kind: Tok::Str(s),
line: tok_line,
});
continue;
}
// Identifier / keyword / time literal / boolean.
if c.is_ascii_alphabetic() || c == '_' {
let start = i;
while i < chars.len() && (chars[i].is_ascii_alphanumeric() || chars[i] == '_') {
i += 1;
}
let word: String = chars[start..i].iter().collect();
// Duration/date/time literal prefix: T#, TIME#, DT#, D#, TOD#, LT# ...
if i < chars.len() && chars[i] == '#' {
let up = word.to_ascii_uppercase();
if matches!(
up.as_str(),
"T" | "TIME" | "DT" | "D" | "TOD" | "LT" | "DATE"
) {
let lit_start = start;
i += 1; // consume '#'
while i < chars.len()
&& (chars[i].is_ascii_alphanumeric()
|| chars[i] == '.'
|| chars[i] == '_'
|| chars[i] == ':')
{
i += 1;
}
let lit: String = chars[lit_start..i].iter().collect();
out.push(Token {
kind: Tok::Time(lit),
line: tok_line,
});
continue;
}
}
let kind = match word.to_ascii_uppercase().as_str() {
"TRUE" => Tok::Bool(true),
"FALSE" => Tok::Bool(false),
_ => match keyword_from(&word) {
Some(kw) => Tok::Kw(kw),
None => Tok::Ident(word),
},
};
out.push(Token {
kind,
line: tok_line,
});
continue;
}
// Number: decimal, real, or based (16#..., 2#...).
if c.is_ascii_digit() {
let start = i;
while i < chars.len() && (chars[i].is_ascii_digit() || chars[i] == '_') {
i += 1;
}
// Based literal: <base>#<digits>
if i < chars.len() && chars[i] == '#' {
let base_str: String = chars[start..i].iter().filter(|c| **c != '_').collect();
i += 1;
let dstart = i;
while i < chars.len() && (chars[i].is_ascii_alphanumeric() || chars[i] == '_') {
i += 1;
}
let digits: String = chars[dstart..i].iter().filter(|c| **c != '_').collect();
let radix = base_str.parse::<u32>().unwrap_or(10);
let val = i64::from_str_radix(&digits, radix.clamp(2, 36)).unwrap_or(0);
out.push(Token {
kind: Tok::Int(val),
line: tok_line,
});
continue;
}
// Real: has a '.' (not '..') or exponent.
let is_real =
i < chars.len() && chars[i] == '.' && !(i + 1 < chars.len() && chars[i + 1] == '.');
if is_real {
i += 1;
while i < chars.len() && (chars[i].is_ascii_digit() || chars[i] == '_') {
i += 1;
}
let raw: String = chars[start..i].iter().filter(|c| **c != '_').collect();
out.push(Token {
kind: Tok::Real(raw.parse().unwrap_or(0.0)),
line: tok_line,
});
continue;
}
let raw: String = chars[start..i].iter().filter(|c| **c != '_').collect();
out.push(Token {
kind: Tok::Int(raw.parse().unwrap_or(0)),
line: tok_line,
});
continue;
}
// Operators / punctuation (longest match first).
let two: String = chars[i..(i + 2).min(chars.len())].iter().collect();
let kind = match two.as_str() {
":=" => Some(Tok::Assign),
"<=" => Some(Tok::Le),
">=" => Some(Tok::Ge),
"<>" => Some(Tok::Ne),
".." => Some(Tok::DotDot),
"**" => Some(Tok::Power),
_ => None,
};
if let Some(k) = kind {
out.push(Token {
kind: k,
line: tok_line,
});
i += 2;
continue;
}
let one = match c {
'+' => Some(Tok::Plus),
'-' => Some(Tok::Minus),
'*' => Some(Tok::Star),
'/' => Some(Tok::Slash),
'(' => Some(Tok::LParen),
')' => Some(Tok::RParen),
'[' => Some(Tok::LBrack),
']' => Some(Tok::RBrack),
'.' => Some(Tok::Dot),
',' => Some(Tok::Comma),
';' => Some(Tok::Semi),
':' => Some(Tok::Colon),
'<' => Some(Tok::Lt),
'>' => Some(Tok::Gt),
'=' => Some(Tok::Eq),
'&' => Some(Tok::Amp),
_ => None,
};
if let Some(k) = one {
out.push(Token {
kind: k,
line: tok_line,
});
}
i += 1;
}
out.push(Token {
kind: Tok::Eof,
line,
});
out
}
+235
View File
@@ -0,0 +1,235 @@
//! PLC control-logic security scanner for IEC 61131-3 targets.
//!
//! Parses Structured Text (raw `.st`/`.scl`/`.exp` files and PLCopen-XML
//! projects) into an AST and runs semantic control-logic security rules over it.
//! Implements [`ScanType::PlcControlLogic`].
pub mod ast;
pub mod lexer;
pub mod parser;
pub mod plcopen;
pub mod rules;
pub mod runtime;
pub mod sbom;
use std::path::Path;
use compliance_core::error::CoreError;
use compliance_core::models::{Finding, ScanType};
use compliance_core::traits::{ScanOutput, Scanner};
use crate::pipeline::dedup;
/// Scanner for `ScanType::PlcControlLogic`.
pub struct PlcControlLogicScanner;
impl Scanner for PlcControlLogicScanner {
fn name(&self) -> &str {
"plc-control-logic"
}
fn scan_type(&self) -> ScanType {
ScanType::PlcControlLogic
}
#[tracing::instrument(skip_all)]
async fn scan(&self, repo_path: &Path, repo_id: &str) -> Result<ScanOutput, CoreError> {
let findings = analyze_tree(repo_path, repo_id);
Ok(ScanOutput {
findings,
sbom_entries: Vec::new(),
})
}
}
/// Walk a PLC project tree and produce findings.
pub(crate) fn analyze_tree(root: &Path, repo_id: &str) -> Vec<Finding> {
let mut findings = Vec::new();
for entry in walkdir::WalkDir::new(root)
.into_iter()
.filter_map(|e| e.ok())
{
if !entry.file_type().is_file() {
continue;
}
let path = entry.path();
let ext = path
.extension()
.and_then(|e| e.to_str())
.unwrap_or("")
.to_ascii_lowercase();
let is_st = matches!(ext.as_str(), "st" | "iecst" | "scl" | "exp" | "il");
let is_xml = matches!(ext.as_str(), "xml" | "plcopen" | "project");
if !is_st && !is_xml {
continue;
}
let Ok(content) = std::fs::read_to_string(path) else {
continue;
};
let pous = if is_xml {
plcopen::parse_plcopen(&content)
} else {
parser::parse(&content)
};
if pous.is_empty() {
continue;
}
let rel = path
.strip_prefix(root)
.unwrap_or(path)
.to_string_lossy()
.to_string();
for pou in &pous {
for hit in rules::analyze(pou) {
let line_s = hit.line.to_string();
let fingerprint =
dedup::compute_fingerprint(&[repo_id, &rel, hit.rule_id, &pou.name, &line_s]);
let mut f = Finding::new(
repo_id.to_string(),
fingerprint,
"plc-control-logic".to_string(),
ScanType::PlcControlLogic,
hit.title,
hit.description,
hit.severity,
);
f.file_path = Some(rel.clone());
f.line_number = Some(hit.line);
f.rule_id = Some(hit.rule_id.to_string());
f.cwe = hit.cwe.map(String::from);
f.remediation = Some(hit.remediation.to_string());
findings.push(f);
}
}
}
findings
}
#[cfg(test)]
mod tests {
use super::*;
use std::collections::HashSet;
use std::path::PathBuf;
fn demo_dir() -> PathBuf {
PathBuf::from(env!("CARGO_MANIFEST_DIR"))
.parent()
.expect("workspace root")
.join("examples/plc-demo")
}
#[test]
fn scans_demo_project_end_to_end() {
let findings = analyze_tree(&demo_dir(), "demo-target");
assert!(!findings.is_empty(), "demo project should produce findings");
let rules: HashSet<&str> = findings
.iter()
.filter_map(|f| f.rule_id.as_deref())
.collect();
for r in [
"plc-hardcoded-credential",
"plc-default-password",
"plc-safety-bypass",
"plc-array-unchecked-index",
"plc-insecure-comm",
"plc-insecure-protocol-port",
"plc-unstructured-jump",
"plc-division-by-zero",
] {
assert!(rules.contains(r), "expected rule {r}; got {rules:?}");
}
// Every finding is well-formed for storage.
for f in &findings {
assert_eq!(f.repo_id, "demo-target");
assert!(f.file_path.is_some(), "finding needs a file");
assert!(f.line_number.is_some(), "finding needs a line");
}
// The guarded division (IF ScaleFactor <> 0.0) must not be double-counted:
// exactly one division-by-zero (the unguarded MeasuredFlow divide).
let div0 = findings
.iter()
.filter(|f| f.rule_id.as_deref() == Some("plc-division-by-zero"))
.count();
assert_eq!(div0, 1, "only the unguarded division should be flagged");
}
/// The realistic OpenPLC-style traffic-light sample is mostly sound control
/// logic: the scanner must surface its few genuine defects and stay quiet on
/// the timed state machine and the guarded duty-cycle division.
#[test]
fn realistic_sample_flags_only_real_issues() {
let all = analyze_tree(&demo_dir(), "demo-target");
let tl: Vec<_> = all
.iter()
.filter(|f| {
f.file_path
.as_deref()
.is_some_and(|p| p.ends_with("traffic_light.st"))
})
.collect();
assert!(!tl.is_empty(), "traffic_light.st should produce findings");
let rules: HashSet<&str> = tl.iter().filter_map(|f| f.rule_id.as_deref()).collect();
// The three planted defects: hardcoded SCADA password, cleartext Modbus
// master (no auth), and a maintenance mode that drops the PedPermit.
for r in [
"plc-hardcoded-credential",
"plc-insecure-comm",
"plc-safety-bypass",
] {
assert!(rules.contains(r), "expected rule {r}; got {rules:?}");
}
// Modbus/TCP on 502 is also an insecure-protocol port.
assert!(rules.contains("plc-insecure-protocol-port"));
// Low false positives: the guarded `IF LampCount <> 0` division and the
// JMP-free state machine must not trip anything.
assert_eq!(
tl.iter()
.filter(|f| f.rule_id.as_deref() == Some("plc-division-by-zero"))
.count(),
0,
"the guarded duty-cycle division must not be flagged"
);
assert!(
!rules.contains("plc-unstructured-jump"),
"the CASE state machine uses no JMP"
);
}
/// Graphical logic must be analysed too: an FBD POU (blocks + in/out
/// variables) is translated to synthetic ST, so the same rules fire on the
/// cleartext Modbus block, the hardcoded HMI password and the safety write.
#[test]
fn fbd_graphical_body_is_analysed() {
let all = analyze_tree(&demo_dir(), "demo-target");
let fbd: Vec<_> = all
.iter()
.filter(|f| {
f.file_path
.as_deref()
.is_some_and(|p| p.ends_with("pump_fbd.xml"))
})
.collect();
assert!(
!fbd.is_empty(),
"pump_fbd.xml (FBD) should produce findings"
);
let rules: HashSet<&str> = fbd.iter().filter_map(|f| f.rule_id.as_deref()).collect();
for r in [
"plc-insecure-comm", // Modbus_TCP_Master(AUTH := FALSE)
"plc-insecure-protocol-port", // PORT := 502
"plc-hardcoded-credential", // HmiPassword := 'admin123'
"plc-safety-bypass", // Safety_Enable := FALSE
] {
assert!(
rules.contains(r),
"expected rule {r} from FBD; got {rules:?}"
);
}
}
}
+766
View File
@@ -0,0 +1,766 @@
//! Recursive-descent parser for the security-relevant subset of Structured Text.
//!
//! Tolerant by design: it parses the POUs, variable sections, and statement
//! bodies it understands, and skips (with statement/POU-level recovery) anything
//! it does not, so a single odd construct never sinks the whole file.
use super::ast::*;
use super::lexer::{Keyword as K, Tok, Token};
pub struct Parser {
toks: Vec<Token>,
pos: usize,
}
impl Parser {
pub fn new(toks: Vec<Token>) -> Self {
Self { toks, pos: 0 }
}
// ── token helpers ──────────────────────────────────────────────
fn peek(&self) -> &Tok {
&self.toks[self.pos.min(self.toks.len() - 1)].kind
}
fn line(&self) -> u32 {
self.toks[self.pos.min(self.toks.len() - 1)].line
}
fn at_end(&self) -> bool {
matches!(self.peek(), Tok::Eof)
}
fn advance(&mut self) -> Tok {
let t = self.toks[self.pos.min(self.toks.len() - 1)].kind.clone();
if self.pos < self.toks.len() - 1 {
self.pos += 1;
}
t
}
fn eat(&mut self, t: &Tok) -> bool {
if self.peek() == t {
self.advance();
true
} else {
false
}
}
fn eat_kw(&mut self, k: K) -> bool {
if matches!(self.peek(), Tok::Kw(x) if *x == k) {
self.advance();
true
} else {
false
}
}
fn at_kw(&self, k: K) -> bool {
matches!(self.peek(), Tok::Kw(x) if *x == k)
}
fn ident(&mut self) -> Option<String> {
if let Tok::Ident(s) = self.peek() {
let s = s.clone();
self.advance();
Some(s)
} else {
None
}
}
// ── top level ──────────────────────────────────────────────────
/// Parse every POU in the token stream.
pub fn parse_units(&mut self) -> Vec<Pou> {
let mut pous = Vec::new();
while !self.at_end() {
match self.peek() {
Tok::Kw(K::Program) => {
self.advance();
if let Some(p) = self.parse_pou(PouKind::Program, K::EndProgram) {
pous.push(p);
}
}
Tok::Kw(K::Function) => {
self.advance();
if let Some(p) = self.parse_pou(PouKind::Function, K::EndFunction) {
pous.push(p);
}
}
Tok::Kw(K::FunctionBlock) => {
self.advance();
if let Some(p) = self.parse_pou(PouKind::FunctionBlock, K::EndFunctionBlock) {
pous.push(p);
}
}
// Skip TYPE...END_TYPE and anything else at top level.
_ => {
self.advance();
}
}
}
pous
}
fn parse_pou(&mut self, kind: PouKind, end: K) -> Option<Pou> {
let line = self.line();
let name = self.ident().unwrap_or_else(|| "<anonymous>".to_string());
// Optional `: return_type` for functions.
if self.eat(&Tok::Colon) {
let _ = self.advance(); // return type token
}
let mut vars = Vec::new();
// Variable sections precede the body.
while let Some(section) = self.var_section_kw() {
self.advance();
let _ = self.eat_kw(K::Constant); // CONSTANT is informational for our rules
self.parse_var_decls(section, &mut vars);
}
// Body statements until END_<kind>.
let mut body = Vec::new();
while !self.at_end() && !self.at_kw(end) {
if let Some(s) = self.parse_stmt() {
body.push(s);
}
}
self.eat_kw(end);
Some(Pou {
name,
kind,
vars,
body,
line,
})
}
fn var_section_kw(&self) -> Option<VarSection> {
match self.peek() {
Tok::Kw(K::Var) => Some(VarSection::Var),
Tok::Kw(K::VarInput) => Some(VarSection::Input),
Tok::Kw(K::VarOutput) => Some(VarSection::Output),
Tok::Kw(K::VarInOut) => Some(VarSection::InOut),
Tok::Kw(K::VarGlobal) => Some(VarSection::Global),
Tok::Kw(K::VarTemp) => Some(VarSection::Temp),
Tok::Kw(K::VarExternal) => Some(VarSection::External),
_ => None,
}
}
fn parse_var_decls(&mut self, section: VarSection, out: &mut Vec<VarDecl>) {
while !self.at_end() && !self.at_kw(K::EndVar) {
let line = self.line();
// names: a, b, c
let mut names = Vec::new();
match self.ident() {
Some(n) => names.push(n),
None => {
// Not a declaration we understand — skip to next ; or END_VAR.
self.sync_decl();
continue;
}
}
while self.eat(&Tok::Comma) {
if let Some(n) = self.ident() {
names.push(n);
}
}
if !self.eat(&Tok::Colon) {
self.sync_decl();
continue;
}
let (type_name, array_bounds) = self.parse_type();
let init = if self.eat(&Tok::Assign) {
Some(self.parse_expr())
} else {
None
};
self.eat(&Tok::Semi);
for n in names {
out.push(VarDecl {
name: n,
section,
type_name: type_name.clone(),
array_bounds,
init: init.clone(),
line,
});
}
}
self.eat_kw(K::EndVar);
}
/// Parse a (possibly ARRAY) type, returning its rendered name and literal
/// bounds when present.
fn parse_type(&mut self) -> (String, Option<(i64, i64)>) {
if self.eat_kw(K::Array) {
let mut bounds = None;
if self.eat(&Tok::LBrack) {
let lo = self.int_lit();
self.eat(&Tok::DotDot);
let hi = self.int_lit();
if let (Some(lo), Some(hi)) = (lo, hi) {
bounds = Some((lo, hi));
}
// Skip any further dimensions / tokens to the closing bracket.
while !self.at_end() && !self.eat(&Tok::RBrack) {
self.advance();
}
}
self.eat_kw(K::Of);
let elem = self.type_ident();
(format!("ARRAY OF {elem}"), bounds)
} else {
(self.type_ident(), None)
}
}
fn type_ident(&mut self) -> String {
// Types can be qualified idents; keep it simple: one token, plus any
// string-length suffix like STRING[80].
let base = match self.advance() {
Tok::Ident(s) => s,
Tok::Kw(_) => "TYPE".to_string(),
other => format!("{other:?}"),
};
if self.eat(&Tok::LBrack) {
while !self.at_end() && !self.eat(&Tok::RBrack) {
self.advance();
}
}
base
}
fn int_lit(&mut self) -> Option<i64> {
match self.peek() {
Tok::Int(n) => {
let n = *n;
self.advance();
Some(n)
}
Tok::Minus => {
self.advance();
if let Tok::Int(n) = self.peek() {
let n = -*n;
self.advance();
Some(n)
} else {
None
}
}
_ => None,
}
}
fn sync_decl(&mut self) {
while !self.at_end() && !self.eat(&Tok::Semi) && !self.at_kw(K::EndVar) {
self.advance();
}
}
fn sync_stmt(&mut self) {
while !self.at_end() && !self.eat(&Tok::Semi) {
// Stop at block terminators so recovery doesn't swallow structure.
if matches!(
self.peek(),
Tok::Kw(
K::EndIf
| K::EndFor
| K::EndWhile
| K::EndCase
| K::EndRepeat
| K::EndProgram
| K::EndFunction
| K::EndFunctionBlock
| K::Else
| K::Elsif
)
) {
return;
}
self.advance();
}
}
// ── statements ─────────────────────────────────────────────────
fn parse_stmt(&mut self) -> Option<Stmt> {
let line = self.line();
match self.peek().clone() {
Tok::Semi => {
self.advance();
None
}
Tok::Kw(K::If) => self.parse_if(),
Tok::Kw(K::Case) => self.parse_case(),
Tok::Kw(K::For) => self.parse_for(),
Tok::Kw(K::While) => self.parse_while(),
Tok::Kw(K::Repeat) => self.parse_repeat(),
Tok::Kw(K::Return) => {
self.advance();
self.eat(&Tok::Semi);
Some(Stmt::Return { line })
}
Tok::Kw(K::Exit) => {
self.advance();
self.eat(&Tok::Semi);
Some(Stmt::Exit { line })
}
Tok::Kw(K::Jmp) => {
self.advance();
let label = self.ident().unwrap_or_default();
self.eat(&Tok::Semi);
Some(Stmt::Jump { label, line })
}
Tok::Ident(name) => {
// Could be `label:`, `call(...)`, or an assignment.
// Lookahead: ident ':' (not ':=') → label.
if matches!(
self.toks.get(self.pos + 1).map(|t| &t.kind),
Some(Tok::Colon)
) && !matches!(self.toks.get(self.pos + 2).map(|t| &t.kind), Some(Tok::Eq))
{
self.advance(); // ident
self.advance(); // ':'
return Some(Stmt::Label { name, line });
}
let lhs = self.parse_expr();
if self.eat(&Tok::Assign) {
let value = self.parse_expr();
self.eat(&Tok::Semi);
Some(Stmt::Assign {
target: lhs,
value,
line,
})
} else if let Expr::Call { callee, args, .. } = lhs {
self.eat(&Tok::Semi);
Some(Stmt::Call { callee, args, line })
} else {
// Bare expression / FB invocation without args recognized —
// skip to the terminator.
self.sync_stmt();
None
}
}
_ => {
self.sync_stmt();
None
}
}
}
fn parse_block_until(&mut self, terms: &[K]) -> Vec<Stmt> {
let mut body = Vec::new();
while !self.at_end() && !terms.iter().any(|k| self.at_kw(*k)) {
if let Some(s) = self.parse_stmt() {
body.push(s);
}
}
body
}
fn parse_if(&mut self) -> Option<Stmt> {
let line = self.line();
self.eat_kw(K::If);
let mut branches = Vec::new();
let cond = self.parse_expr();
self.eat_kw(K::Then);
let body = self.parse_block_until(&[K::Elsif, K::Else, K::EndIf]);
branches.push((cond, body));
while self.eat_kw(K::Elsif) {
let c = self.parse_expr();
self.eat_kw(K::Then);
let b = self.parse_block_until(&[K::Elsif, K::Else, K::EndIf]);
branches.push((c, b));
}
let else_body = if self.eat_kw(K::Else) {
Some(self.parse_block_until(&[K::EndIf]))
} else {
None
};
self.eat_kw(K::EndIf);
self.eat(&Tok::Semi);
Some(Stmt::If {
branches,
else_body,
line,
})
}
fn parse_case(&mut self) -> Option<Stmt> {
let line = self.line();
self.eat_kw(K::Case);
let selector = self.parse_expr();
self.eat_kw(K::Of);
let mut arms = Vec::new();
let mut else_body = None;
while !self.at_end() && !self.at_kw(K::EndCase) {
if self.eat_kw(K::Else) {
else_body = Some(self.parse_block_until(&[K::EndCase]));
break;
}
// labels: expr {, expr} :
let mut labels = vec![self.parse_expr()];
while self.eat(&Tok::Comma) {
labels.push(self.parse_expr());
}
self.eat(&Tok::Colon);
let body = self.parse_block_until(&[K::EndCase, K::Else]);
arms.push((labels, body));
}
self.eat_kw(K::EndCase);
self.eat(&Tok::Semi);
Some(Stmt::Case {
selector,
arms,
else_body,
line,
})
}
fn parse_for(&mut self) -> Option<Stmt> {
let line = self.line();
self.eat_kw(K::For);
let var = self.ident().unwrap_or_default();
self.eat(&Tok::Assign);
let from = self.parse_expr();
self.eat_kw(K::To);
let to = self.parse_expr();
let by = if self.eat_kw(K::By) {
Some(self.parse_expr())
} else {
None
};
self.eat_kw(K::Do);
let body = self.parse_block_until(&[K::EndFor]);
self.eat_kw(K::EndFor);
self.eat(&Tok::Semi);
Some(Stmt::For {
var,
from,
to,
by,
body,
line,
})
}
fn parse_while(&mut self) -> Option<Stmt> {
let line = self.line();
self.eat_kw(K::While);
let cond = self.parse_expr();
self.eat_kw(K::Do);
let body = self.parse_block_until(&[K::EndWhile]);
self.eat_kw(K::EndWhile);
self.eat(&Tok::Semi);
Some(Stmt::While { cond, body, line })
}
fn parse_repeat(&mut self) -> Option<Stmt> {
let line = self.line();
self.eat_kw(K::Repeat);
let body = self.parse_block_until(&[K::Until, K::EndRepeat]);
self.eat_kw(K::Until);
let until = self.parse_expr();
self.eat_kw(K::EndRepeat);
self.eat(&Tok::Semi);
Some(Stmt::Repeat { body, until, line })
}
// ── expressions (precedence climbing) ──────────────────────────
pub fn parse_expr(&mut self) -> Expr {
self.parse_or()
}
fn parse_or(&mut self) -> Expr {
let mut lhs = self.parse_and();
loop {
let op = match self.peek() {
Tok::Kw(K::Or) => BinOp::Or,
Tok::Kw(K::Xor) => BinOp::Xor,
_ => break,
};
let line = self.line();
self.advance();
let rhs = self.parse_and();
lhs = Expr::Binary {
op,
lhs: Box::new(lhs),
rhs: Box::new(rhs),
line,
};
}
lhs
}
fn parse_and(&mut self) -> Expr {
let mut lhs = self.parse_cmp();
while matches!(self.peek(), Tok::Kw(K::And) | Tok::Amp) {
let op = BinOp::And;
let line = self.line();
self.advance();
let rhs = self.parse_cmp();
lhs = Expr::Binary {
op,
lhs: Box::new(lhs),
rhs: Box::new(rhs),
line,
};
}
lhs
}
fn parse_cmp(&mut self) -> Expr {
let mut lhs = self.parse_add();
loop {
let op = match self.peek() {
Tok::Eq => BinOp::Eq,
Tok::Ne => BinOp::Ne,
Tok::Lt => BinOp::Lt,
Tok::Le => BinOp::Le,
Tok::Gt => BinOp::Gt,
Tok::Ge => BinOp::Ge,
_ => break,
};
let line = self.line();
self.advance();
let rhs = self.parse_add();
lhs = Expr::Binary {
op,
lhs: Box::new(lhs),
rhs: Box::new(rhs),
line,
};
}
lhs
}
fn parse_add(&mut self) -> Expr {
let mut lhs = self.parse_mul();
loop {
let op = match self.peek() {
Tok::Plus => BinOp::Add,
Tok::Minus => BinOp::Sub,
_ => break,
};
let line = self.line();
self.advance();
let rhs = self.parse_mul();
lhs = Expr::Binary {
op,
lhs: Box::new(lhs),
rhs: Box::new(rhs),
line,
};
}
lhs
}
fn parse_mul(&mut self) -> Expr {
let mut lhs = self.parse_unary();
loop {
let op = match self.peek() {
Tok::Star => BinOp::Mul,
Tok::Slash => BinOp::Div,
Tok::Kw(K::Mod) => BinOp::Mod,
Tok::Power => BinOp::Pow,
_ => break,
};
let line = self.line();
self.advance();
let rhs = self.parse_unary();
lhs = Expr::Binary {
op,
lhs: Box::new(lhs),
rhs: Box::new(rhs),
line,
};
}
lhs
}
fn parse_unary(&mut self) -> Expr {
let line = self.line();
match self.peek() {
Tok::Kw(K::Not) => {
self.advance();
Expr::Unary {
op: UnOp::Not,
expr: Box::new(self.parse_unary()),
line,
}
}
Tok::Minus => {
self.advance();
Expr::Unary {
op: UnOp::Neg,
expr: Box::new(self.parse_unary()),
line,
}
}
_ => self.parse_postfix(),
}
}
fn parse_postfix(&mut self) -> Expr {
let mut e = self.parse_primary();
loop {
let line = self.line();
match self.peek() {
Tok::LBrack => {
self.advance();
let index = self.parse_expr();
self.eat(&Tok::RBrack);
e = Expr::Index {
base: Box::new(e),
index: Box::new(index),
line,
};
}
Tok::Dot => {
self.advance();
let field = self.ident().unwrap_or_default();
e = Expr::Member {
base: Box::new(e),
field,
line,
};
}
_ => break,
}
}
e
}
fn parse_primary(&mut self) -> Expr {
let line = self.line();
match self.advance() {
Tok::Int(n) => Expr::Int(n, line),
Tok::Real(r) => Expr::Real(r, line),
Tok::Bool(b) => Expr::Bool(b, line),
Tok::Str(s) => Expr::Str(s, line),
Tok::Time(t) => Expr::Time(t, line),
Tok::LParen => {
let e = self.parse_expr();
self.eat(&Tok::RParen);
e
}
Tok::Ident(name) => {
if self.eat(&Tok::LParen) {
let args = self.parse_call_args();
Expr::Call {
callee: name,
args,
line,
}
} else {
Expr::Ident(name, line)
}
}
// Unrecognized start of expression — yield a placeholder identifier.
_ => Expr::Ident(String::new(), line),
}
}
fn parse_call_args(&mut self) -> Vec<CallArg> {
let mut args = Vec::new();
if self.eat(&Tok::RParen) {
return args;
}
loop {
// Named arg: ident := expr (peek two tokens).
if let Tok::Ident(name) = self.peek().clone() {
if matches!(
self.toks.get(self.pos + 1).map(|t| &t.kind),
Some(Tok::Assign)
) {
self.advance(); // ident
self.advance(); // :=
let value = self.parse_expr();
args.push(CallArg {
name: Some(name),
value,
});
if self.eat(&Tok::Comma) {
continue;
}
break;
}
}
let value = self.parse_expr();
args.push(CallArg { name: None, value });
if self.eat(&Tok::Comma) {
continue;
}
break;
}
self.eat(&Tok::RParen);
args
}
}
/// Parse ST source into its POUs.
pub fn parse(src: &str) -> Vec<Pou> {
let toks = super::lexer::lex(src);
Parser::new(toks).parse_units()
}
#[cfg(test)]
mod tests {
use super::*;
const SAMPLE: &str = r#"
PROGRAM Main
VAR
idx : INT;
pw : STRING := 'admin123';
buf : ARRAY[0..9] OF INT;
ok : BOOL := FALSE;
END_VAR
// a comment
IF idx > 0 THEN
buf[idx] := idx * 2;
ELSE
JMP done;
END_IF;
Comm(IP := '10.0.0.1', PORT := 502);
done:
ok := TRUE;
END_PROGRAM
"#;
#[test]
fn parses_program_vars_and_body() {
let pous = parse(SAMPLE);
assert_eq!(pous.len(), 1, "one POU");
let p = &pous[0];
assert_eq!(p.name, "Main");
assert_eq!(p.kind, PouKind::Program);
// vars: idx, pw, buf, ok
assert_eq!(p.vars.len(), 4);
let pw = p.vars.iter().find(|v| v.name == "pw").expect("pw");
assert!(matches!(&pw.init, Some(Expr::Str(s, _)) if s == "admin123"));
let buf = p.vars.iter().find(|v| v.name == "buf").expect("buf");
assert_eq!(buf.array_bounds, Some((0, 9)));
// body has an IF, a Call, a Label, and an Assign
assert!(p.body.iter().any(|s| matches!(s, Stmt::If { .. })));
assert!(p
.body
.iter()
.any(|s| matches!(s, Stmt::Call { callee, .. } if callee == "Comm")));
assert!(p
.body
.iter()
.any(|s| matches!(s, Stmt::Label { name, .. } if name == "done")));
}
#[test]
fn jmp_inside_if_is_captured() {
let pous = parse(SAMPLE);
let p = &pous[0];
// find the IF, check its else branch has a JMP
let has_jmp = p.body.iter().any(|s| match s {
Stmt::If { else_body, .. } => else_body
.as_ref()
.map(|b| b.iter().any(|s| matches!(s, Stmt::Jump { .. })))
.unwrap_or(false),
_ => false,
});
assert!(has_jmp, "JMP should be parsed inside the ELSE branch");
}
}
@@ -0,0 +1,418 @@
//! PLCopen XML → Structured Text POUs.
//!
//! A PLCopen project stores each POU as `<pou name=".." pouType="..">` with an
//! `<interface>` (typed variable sections) and a `<body>` in one of the IEC
//! 61131-3 languages. We reconstruct an equivalent Structured-Text source for
//! each POU (a `VAR` block from the interface + statements from the body) and run
//! it through the ST parser, so raw `.st` files and PLCopen projects — textual or
//! graphical — flow through one analysis path.
//!
//! Body languages:
//! - **ST** — taken verbatim.
//! - **FBD / LD** — the graphical network is translated to synthetic ST: blocks
//! become calls (`TypeName(pin := arg, …)`), out-variables / coils become
//! assignments, with input pins resolved by tracing connections. This lets the
//! semantic rules see comm calls, hardcoded arguments and safety writes that
//! live in graphical logic, not just in text.
//! - **SFC** — the step/transition graph itself is skipped; the ST/FBD/LD bodies
//! embedded in its actions and transitions are still translated.
use std::collections::HashMap;
use roxmltree::Node;
use super::ast::Pou;
use super::parser;
/// Parse every POU out of a PLCopen XML document (ST, FBD or LD bodies).
pub fn parse_plcopen(xml: &str) -> Vec<Pou> {
let doc = match roxmltree::Document::parse(xml) {
Ok(d) => d,
Err(_) => return Vec::new(),
};
let mut pous = Vec::new();
for pou in doc.descendants().filter(|n| n.has_tag_name("pou")) {
let name = pou.attribute("name").unwrap_or("pou").to_string();
let pou_type = pou.attribute("pouType").unwrap_or("program");
let Some(body) = reconstruct_body(pou) else {
continue;
};
if body.trim().is_empty() {
continue;
}
let var_block = build_var_block(pou);
let kw = match pou_type.to_ascii_lowercase().as_str() {
"function" => "FUNCTION",
"functionblock" | "functionblocktype" => "FUNCTION_BLOCK",
_ => "PROGRAM",
};
let synthetic = format!("{kw} {name}\n{var_block}{body}\nEND_{kw}\n");
pous.extend(parser::parse(&synthetic));
}
pous
}
/// Case-insensitive tag match (PLCopen uses `FBD`/`LD`/`ST`, CODESYS may vary).
fn tag_is(n: &Node, name: &str) -> bool {
n.tag_name().name().eq_ignore_ascii_case(name)
}
/// Reconstruct a POU's body as Structured Text, whatever language it is written
/// in. Concatenates every language body found under `<body>` (SFC actions and
/// transitions carry their own ST/FBD/LD sub-bodies).
fn reconstruct_body(pou: Node) -> Option<String> {
let mut out = String::new();
for body in pou.descendants().filter(|n| tag_is(n, "body")) {
for lang in body.children().filter(|n| n.is_element()) {
let piece = match lang.tag_name().name().to_ascii_uppercase().as_str() {
"ST" | "IL" => collect_text(lang),
"FBD" | "LD" => translate_network(lang),
_ => continue,
};
if !piece.trim().is_empty() {
out.push_str(&piece);
if !piece.ends_with('\n') {
out.push('\n');
}
}
}
}
if out.trim().is_empty() {
None
} else {
Some(out)
}
}
// ── graphical (FBD / LD) → synthetic ST ────────────────────────────────
/// Translate one FBD/LD network into ST statements: blocks → calls,
/// out-variables and coils → assignments.
fn translate_network(net: Node) -> String {
let by_id = index_local_ids(net);
let mut out = String::new();
for el in net.children().filter(|n| n.is_element()) {
let stmt = match el.tag_name().name().to_ascii_lowercase().as_str() {
"block" => block_call(el, &by_id).map(|c| format!("{c};")),
"outvariable" => out_assignment(el, &by_id),
"coil" => coil_assignment(el, &by_id),
_ => None,
};
if let Some(s) = stmt {
out.push_str(&s);
out.push('\n');
}
}
out
}
/// Index every element in a network by its `localId` so connections resolve.
fn index_local_ids<'a, 'input>(net: Node<'a, 'input>) -> HashMap<String, Node<'a, 'input>> {
net.descendants()
.filter(|n| n.is_element())
.filter_map(|n| n.attribute("localId").map(|id| (id.to_string(), n)))
.collect()
}
/// Build a call expression for a block: `TypeName(pin := arg, …)`.
fn block_call(block: Node, by_id: &HashMap<String, Node>) -> Option<String> {
let ty = block.attribute("typeName")?;
let mut args = Vec::new();
if let Some(inputs) = block.children().find(|n| tag_is(n, "inputVariables")) {
for v in inputs.children().filter(|n| tag_is(n, "variable")) {
let Some(expr) = input_expr(v, by_id, 0) else {
continue;
};
match v.attribute("formalParameter") {
Some(pin) if !pin.is_empty() => args.push(format!("{pin} := {expr}")),
_ => args.push(expr),
}
}
}
Some(format!("{ty}({})", args.join(", ")))
}
/// `target := <traced expression>;` for an FBD out-variable.
fn out_assignment(outvar: Node, by_id: &HashMap<String, Node>) -> Option<String> {
let target = expression_text(outvar)?;
let value = input_expr(outvar, by_id, 0).unwrap_or_else(|| "0".to_string());
Some(format!("{target} := {value};"))
}
/// `coil := <traced rung expression>;` for an LD coil (negated → `NOT (…)`).
fn coil_assignment(coil: Node, by_id: &HashMap<String, Node>) -> Option<String> {
let target = child_text(coil, "variable")?;
let rung = input_expr(coil, by_id, 0).unwrap_or_else(|| "TRUE".to_string());
let negated = matches!(coil.attribute("negated"), Some(v) if v.eq_ignore_ascii_case("true"));
let rhs = if negated {
format!("NOT ({rung})")
} else {
rung
};
Some(format!("{target} := {rhs};"))
}
/// Resolve the expression feeding `node`'s single input connection.
fn input_expr(node: Node, by_id: &HashMap<String, Node>, depth: u8) -> Option<String> {
let refid = ref_local_id(node)?;
Some(expr_for(&refid, by_id, depth))
}
/// Build the ST expression produced by the element with this `localId`.
fn expr_for(local_id: &str, by_id: &HashMap<String, Node>, depth: u8) -> String {
if depth > 24 {
return "0".to_string();
}
let Some(node) = by_id.get(local_id) else {
return format!("__net{local_id}");
};
match node.tag_name().name().to_ascii_lowercase().as_str() {
"invariable" | "inoutvariable" => {
expression_text(*node).unwrap_or_else(|| format!("__net{local_id}"))
}
// A block feeding another element: reference it by a synthetic result
// name; the block is emitted as its own call statement, so we neither
// duplicate the call nor lose it.
"block" => format!("__blk{local_id}"),
"contact" => {
let var = child_text(*node, "variable").unwrap_or_else(|| "TRUE".to_string());
let negated =
matches!(node.attribute("negated"), Some(v) if v.eq_ignore_ascii_case("true"));
let term = if negated { format!("NOT {var}") } else { var };
match ref_local_id(*node) {
Some(up) => {
let upstream = expr_for(&up, by_id, depth + 1);
if upstream == "TRUE" {
term
} else {
format!("({upstream} AND {term})")
}
}
None => term,
}
}
"leftpowerrail" => "TRUE".to_string(),
_ => format!("__net{local_id}"),
}
}
/// The `refLocalId` of `node`'s first input connection, if any.
fn ref_local_id(node: Node) -> Option<String> {
node.descendants()
.find(|n| tag_is(n, "connectionPointIn"))
.and_then(|cpi| cpi.descendants().find(|n| tag_is(n, "connection")))
.and_then(|c| c.attribute("refLocalId"))
.map(|s| s.to_string())
}
/// Text of a node's `<expression>` child (variable name or literal).
fn expression_text(node: Node) -> Option<String> {
let e = node.children().find(|n| tag_is(n, "expression"))?;
let t = collect_text(e).trim().to_string();
if t.is_empty() {
None
} else {
Some(t)
}
}
/// Text of a named child element (e.g. `<variable>` of a contact/coil).
fn child_text(node: Node, name: &str) -> Option<String> {
let c = node.children().find(|n| tag_is(n, name))?;
let t = collect_text(c).trim().to_string();
if t.is_empty() {
None
} else {
Some(t)
}
}
/// Concatenate the text of a node's descendant text nodes (bodies are often
/// wrapped in `<xhtml>` and may contain multiple text runs). Only text nodes are
/// gathered: an element's `.text()` would re-yield its first child's text, which
/// (with the text node itself) would duplicate every value.
fn collect_text(node: Node) -> String {
node.descendants()
.filter(|n| n.is_text())
.filter_map(|n| n.text())
.collect::<String>()
}
/// Build an ST `VAR … END_VAR` block from a POU's `<interface>` variable
/// sections, so declarations (types, initial values) reach the rules.
fn build_var_block(pou: Node) -> String {
let Some(interface) = pou.children().find(|n| n.has_tag_name("interface")) else {
return String::new();
};
let mut out = String::from("VAR\n");
let mut any = false;
for container in interface.children().filter(|n| n.is_element()) {
// localVars / inputVars / outputVars / inOutVars / tempVars / globalVars / externalVars
if !container.tag_name().name().ends_with("Vars") {
continue;
}
for var in container.children().filter(|n| n.has_tag_name("variable")) {
let Some(vname) = var.attribute("name") else {
continue;
};
let ty = var
.children()
.find(|n| n.has_tag_name("type"))
.map(type_name)
.unwrap_or_else(|| "BOOL".to_string());
let init = var
.children()
.find(|n| n.has_tag_name("initialValue"))
.and_then(initial_value);
match init {
Some(v) => out.push_str(&format!(" {vname} : {ty} := {v};\n")),
None => out.push_str(&format!(" {vname} : {ty};\n")),
}
any = true;
}
}
out.push_str("END_VAR\n");
if any {
out
} else {
String::new()
}
}
/// Render a PLCopen `<type>` element as an ST type string.
fn type_name(type_node: Node) -> String {
let Some(inner) = type_node.children().find(|n| n.is_element()) else {
return "BOOL".to_string();
};
let tag = inner.tag_name().name();
match tag {
"derived" => inner.attribute("name").unwrap_or("DERIVED").to_string(),
"array" => {
let dim = inner.children().find(|n| n.has_tag_name("dimension"));
let (lo, hi) = dim
.map(|d| {
(
d.attribute("lower").unwrap_or("0").to_string(),
d.attribute("upper").unwrap_or("0").to_string(),
)
})
.unwrap_or_else(|| ("0".to_string(), "0".to_string()));
let base = inner
.children()
.find(|n| n.has_tag_name("baseType"))
.map(type_name)
.unwrap_or_else(|| "INT".to_string());
format!("ARRAY[{lo}..{hi}] OF {base}")
}
"string" | "wstring" => "STRING".to_string(),
// BOOL, INT, DINT, REAL, TIME, ... — the tag name is the ST type.
other => other.to_ascii_uppercase(),
}
}
/// Extract an initial value as an ST literal (quoting strings).
fn initial_value(iv: Node) -> Option<String> {
let simple = iv.descendants().find(|n| n.has_tag_name("simpleValue"))?;
let raw = simple.attribute("value")?.trim().to_string();
if raw.is_empty() {
return None;
}
// Numbers / booleans / time literals pass through; everything else is a
// string literal.
let is_scalar = raw.eq_ignore_ascii_case("true")
|| raw.eq_ignore_ascii_case("false")
|| raw.starts_with(['T', 't', 'D', 'd']) && raw.contains('#')
|| raw
.chars()
.all(|c| c.is_ascii_digit() || c == '.' || c == '-' || c == '+');
if is_scalar || raw.starts_with('\'') || raw.starts_with('"') {
Some(raw)
} else {
Some(format!("'{}'", raw.replace('\'', "''")))
}
}
#[cfg(test)]
mod tests {
use super::parse_plcopen;
use crate::pipeline::plc::rules;
use std::collections::HashSet;
fn rule_ids(xml: &str) -> HashSet<&'static str> {
parse_plcopen(xml)
.iter()
.flat_map(rules::analyze)
.map(|h| h.rule_id)
.collect()
}
/// A Ladder Diagram network: a rung (power rail → contact → coil) plus an
/// insecure comm block. Coils/contacts translate to assignments; the block
/// translates to a call so the port rule fires.
#[test]
fn ld_coil_and_block_translate_and_are_analysed() {
let xml = r#"<?xml version="1.0"?>
<project xmlns="http://www.plcopen.org/xml/tc6_0201">
<types><pous>
<pou name="Rung" pouType="program">
<interface><localVars>
<variable name="Motor"><type><BOOL/></type></variable>
</localVars></interface>
<body><LD>
<leftPowerRail localId="0"/>
<contact localId="1"><variable>Start</variable>
<connectionPointIn><connection refLocalId="0"/></connectionPointIn></contact>
<coil localId="2"><variable>Motor</variable>
<connectionPointIn><connection refLocalId="1"/></connectionPointIn></coil>
<inVariable localId="3"><expression>21</expression></inVariable>
<inVariable localId="4"><expression>FALSE</expression></inVariable>
<block localId="10" typeName="Ftp_Send">
<inputVariables>
<variable formalParameter="PORT">
<connectionPointIn><connection refLocalId="3"/></connectionPointIn></variable>
<variable formalParameter="ENCRYPT">
<connectionPointIn><connection refLocalId="4"/></connectionPointIn></variable>
</inputVariables>
</block>
</LD></body>
</pou>
</pous></types>
</project>"#;
let ids = rule_ids(xml);
// Ftp_Send(PORT := 21, ENCRYPT := FALSE) — port 21 is an insecure protocol.
assert!(
ids.contains("plc-insecure-protocol-port"),
"LD block should flag port 21; got {ids:?}"
);
}
/// Doubled-text regression: a graphical expression must be extracted once,
/// so literals like `502` and `FALSE` stay intact (not `502502`/`FALSEFALSE`).
#[test]
fn graphical_expression_text_is_not_duplicated() {
let xml = r#"<?xml version="1.0"?>
<project xmlns="http://www.plcopen.org/xml/tc6_0201">
<types><pous>
<pou name="Comm" pouType="program">
<body><FBD>
<inVariable localId="1"><expression>502</expression></inVariable>
<inVariable localId="2"><expression>FALSE</expression></inVariable>
<block localId="10" typeName="Modbus_TCP_Master">
<inputVariables>
<variable formalParameter="PORT">
<connectionPointIn><connection refLocalId="1"/></connectionPointIn></variable>
<variable formalParameter="AUTH">
<connectionPointIn><connection refLocalId="2"/></connectionPointIn></variable>
</inputVariables>
</block>
</FBD></body>
</pou>
</pous></types>
</project>"#;
let ids = rule_ids(xml);
assert!(ids.contains("plc-insecure-protocol-port")); // PORT := 502 (not 502502)
assert!(ids.contains("plc-insecure-comm")); // AUTH := FALSE (not FALSEFALSE)
}
}
+632
View File
@@ -0,0 +1,632 @@
//! Semantic control-logic security rules over the Structured Text AST.
//!
//! Each rule walks the parsed [`Pou`] and yields [`RuleHit`]s the scanner turns
//! into findings. Rules reason over structure (declarations, assignments, calls,
//! array accesses, division, jumps) rather than raw text, so they see through
//! formatting and comments.
use std::collections::{HashMap, HashSet};
use compliance_core::models::Severity;
use super::ast::*;
/// One rule match within a POU.
pub struct RuleHit {
pub line: u32,
pub severity: Severity,
pub rule_id: &'static str,
pub title: String,
pub description: String,
pub cwe: Option<&'static str>,
pub remediation: &'static str,
}
/// Run every rule over a POU.
pub fn analyze(pou: &Pou) -> Vec<RuleHit> {
let mut hits = Vec::new();
let ctx = Ctx::build(pou);
// Declaration-level rules.
for v in &pou.vars {
if let Some(init) = &v.init {
check_credential_binding(&v.name, init, &pou.name, &mut hits);
check_default_password(init, &v.name, &pou.name, &mut hits);
}
}
// Body walk.
walk(&pou.body, pou, &ctx, &GuardSet::default(), &mut hits);
hits
}
/// Per-POU context precomputed once.
struct Ctx {
/// Names declared in VAR_INPUT (untrusted / externally driven).
input_vars: HashSet<String>,
/// Array variable name → declared (lo, hi) bounds.
arrays: HashMap<String, (i64, i64)>,
}
impl Ctx {
fn build(pou: &Pou) -> Self {
let mut input_vars = HashSet::new();
let mut arrays = HashMap::new();
for v in &pou.vars {
if v.section == VarSection::Input {
input_vars.insert(v.name.to_ascii_lowercase());
}
if let Some(b) = v.array_bounds {
arrays.insert(v.name.to_ascii_lowercase(), b);
}
}
Self { input_vars, arrays }
}
}
/// Variables proven non-zero on the current control-flow path (from enclosing
/// `IF`/`WHILE` conditions), so guarded divisions aren't false-flagged.
#[derive(Default, Clone)]
struct GuardSet {
nonzero: HashSet<String>,
}
impl GuardSet {
fn with(&self, names: Vec<String>) -> Self {
let mut g = self.clone();
g.nonzero.extend(names);
g
}
fn is_nonzero(&self, name: &str) -> bool {
self.nonzero.contains(name)
}
}
/// Variable names a condition proves non-zero (`v <> 0`, `v > 0`, `v >= 1`,
/// `v < 0`, and conjunctions thereof).
fn guards_from_cond(cond: &Expr) -> Vec<String> {
let mut out = Vec::new();
collect_nonzero(cond, &mut out);
out
}
fn collect_nonzero(e: &Expr, out: &mut Vec<String>) {
let Expr::Binary { op, lhs, rhs, .. } = e else {
return;
};
let is_zero = |x: &Expr| {
matches!(x, Expr::Int(0, _)) || matches!(x, Expr::Real(r, _) if r.abs() < f64::EPSILON)
};
let int_of = |x: &Expr| match x {
Expr::Int(n, _) => Some(*n),
_ => None,
};
match op {
BinOp::And => {
collect_nonzero(lhs, out);
collect_nonzero(rhs, out);
}
BinOp::Ne => {
if let (Some(v), true) = (lhs.as_ident(), is_zero(rhs)) {
out.push(v.to_ascii_lowercase());
}
if let (true, Some(v)) = (is_zero(lhs), rhs.as_ident()) {
out.push(v.to_ascii_lowercase());
}
}
BinOp::Gt | BinOp::Lt => {
// v > 0 or v < 0
if let (Some(v), true) = (lhs.as_ident(), is_zero(rhs)) {
out.push(v.to_ascii_lowercase());
}
}
BinOp::Ge => {
// v >= n, n >= 1
if let (Some(v), Some(n)) = (lhs.as_ident(), int_of(rhs)) {
if n >= 1 {
out.push(v.to_ascii_lowercase());
}
}
}
_ => {}
}
}
// ── the walker ─────────────────────────────────────────────────────
fn walk(stmts: &[Stmt], pou: &Pou, ctx: &Ctx, guards: &GuardSet, hits: &mut Vec<RuleHit>) {
for s in stmts {
match s {
Stmt::Assign {
target,
value,
line,
} => {
check_safety_bypass(target, value, *line, &pou.name, hits);
// A string bound to a secret-looking target is a credential.
if let Some(name) = flatten_ident(target) {
check_credential_binding(&name, value, &pou.name, hits);
check_default_password(value, &name, &pou.name, hits);
}
walk_expr(target, pou, ctx, guards, hits);
walk_expr(value, pou, ctx, guards, hits);
}
Stmt::Call { callee, args, line } => {
check_insecure_comm(callee, args, *line, &pou.name, hits);
check_credentials_in_call(callee, args, *line, &pou.name, hits);
for a in args {
walk_expr(&a.value, pou, ctx, guards, hits);
}
}
Stmt::Jump { label, line } => hits.push(RuleHit {
line: *line,
severity: Severity::Medium,
rule_id: "plc-unstructured-jump",
title: "Unstructured jump (JMP) in control logic".to_string(),
description: format!(
"POU `{}` uses `JMP {label}`. Unstructured jumps make control flow hard to \
verify and can bypass safety interlocks or leave outputs in an undefined \
state on unexpected paths.",
pou.name
),
cwe: Some("CWE-691"),
remediation: "Replace JMP with structured constructs (IF/CASE/loops); reserve \
jumps for well-reviewed state machines only.",
}),
Stmt::If {
branches,
else_body,
..
} => {
for (cond, body) in branches {
walk_expr(cond, pou, ctx, guards, hits);
let child = guards.with(guards_from_cond(cond));
walk(body, pou, ctx, &child, hits);
}
if let Some(b) = else_body {
walk(b, pou, ctx, guards, hits);
}
}
Stmt::Case {
selector,
arms,
else_body,
..
} => {
walk_expr(selector, pou, ctx, guards, hits);
for (labels, body) in arms {
for l in labels {
walk_expr(l, pou, ctx, guards, hits);
}
walk(body, pou, ctx, guards, hits);
}
if let Some(b) = else_body {
walk(b, pou, ctx, guards, hits);
}
}
Stmt::For {
from, to, by, body, ..
} => {
walk_expr(from, pou, ctx, guards, hits);
walk_expr(to, pou, ctx, guards, hits);
if let Some(b) = by {
walk_expr(b, pou, ctx, guards, hits);
}
walk(body, pou, ctx, guards, hits);
}
Stmt::While { cond, body, .. } => {
walk_expr(cond, pou, ctx, guards, hits);
let child = guards.with(guards_from_cond(cond));
walk(body, pou, ctx, &child, hits);
}
Stmt::Repeat { body, until, .. } => {
walk(body, pou, ctx, guards, hits);
walk_expr(until, pou, ctx, guards, hits);
}
Stmt::Return { .. } | Stmt::Exit { .. } | Stmt::Label { .. } => {}
}
}
}
fn walk_expr(e: &Expr, pou: &Pou, ctx: &Ctx, guards: &GuardSet, hits: &mut Vec<RuleHit>) {
match e {
Expr::Index { base, index, line } => {
check_array_bounds(base, index, *line, ctx, &pou.name, hits);
walk_expr(base, pou, ctx, guards, hits);
walk_expr(index, pou, ctx, guards, hits);
}
Expr::Binary { op, lhs, rhs, line } => {
if matches!(op, BinOp::Div | BinOp::Mod) {
check_division(rhs, *line, &pou.name, guards, hits);
}
walk_expr(lhs, pou, ctx, guards, hits);
walk_expr(rhs, pou, ctx, guards, hits);
}
Expr::Unary { expr, .. } => walk_expr(expr, pou, ctx, guards, hits),
Expr::Member { base, .. } => walk_expr(base, pou, ctx, guards, hits),
Expr::Call { args, .. } => {
for a in args {
walk_expr(&a.value, pou, ctx, guards, hits);
}
}
_ => {}
}
}
// ── individual rules ───────────────────────────────────────────────
const SECRET_HINTS: &[&str] = &[
"password",
"passwd",
"pwd",
"secret",
"apikey",
"api_key",
"token",
"credential",
"privkey",
"private_key",
"passphrase",
];
const DEFAULT_PASSWORDS: &[&str] = &[
"admin",
"administrator",
"password",
"passwd",
"1234",
"12345",
"123456",
"0000",
"1111",
"root",
"default",
"admin123",
"changeme",
"letmein",
"guest",
"user",
"system",
"plc",
"codesys",
];
const COMM_FB_HINTS: &[&str] = &[
"modbus", "tcp", "udp", "socket", "mqtt", "opcua", "opc_ua", "ethernet", "ethip", "enip",
"dnp3", "ftp", "telnet", "http", "send", "connect", "sock", "comm", "profinet", "s7",
];
/// Insecure cleartext service ports.
const INSECURE_PORTS: &[i64] = &[21, 23, 80, 502, 20000, 44818, 102];
fn check_credential_binding(var_name: &str, value: &Expr, pou: &str, hits: &mut Vec<RuleHit>) {
let name = var_name.to_ascii_lowercase();
let looks_secret = SECRET_HINTS.iter().any(|h| name.contains(h));
if looks_secret {
if let Expr::Str(s, line) = value {
if !s.is_empty() {
hits.push(RuleHit {
line: *line,
severity: Severity::High,
rule_id: "plc-hardcoded-credential",
title: "Hardcoded credential in PLC program".to_string(),
description: format!(
"POU `{pou}` binds a hardcoded secret to `{var_name}`. Credentials \
embedded in control logic are extracted trivially from a project export \
or a firmware dump and cannot be rotated without a redeploy."
),
cwe: Some("CWE-798"),
remediation: "Store secrets outside the program (secure parameter store / \
operator-entered, retained-but-protected memory); never commit \
them to the POU.",
});
}
}
}
}
fn check_default_password(value: &Expr, var_name: &str, pou: &str, hits: &mut Vec<RuleHit>) {
if let Expr::Str(s, line) = value {
let lower = s.to_ascii_lowercase();
if DEFAULT_PASSWORDS.contains(&lower.as_str()) {
hits.push(RuleHit {
line: *line,
severity: Severity::Critical,
rule_id: "plc-default-password",
title: "Default/weak password in PLC program".to_string(),
description: format!(
"POU `{pou}` uses the well-known default/weak password `{s}` (bound to \
`{var_name}`). Default PLC credentials are the first thing an attacker tries."
),
cwe: Some("CWE-1393"),
remediation:
"Require a strong, unique, operator-set password; block commissioning \
until the default is changed.",
});
}
}
}
fn check_credentials_in_call(
callee: &str,
args: &[CallArg],
line: u32,
pou: &str,
hits: &mut Vec<RuleHit>,
) {
for a in args {
if let Some(name) = &a.name {
let n = name.to_ascii_lowercase();
if SECRET_HINTS.iter().any(|h| n.contains(h)) {
if let Expr::Str(s, l) = &a.value {
if !s.is_empty() {
hits.push(RuleHit {
line: *l,
severity: Severity::High,
rule_id: "plc-hardcoded-credential",
title: "Hardcoded credential passed to a function block".to_string(),
description: format!(
"POU `{pou}` passes a hardcoded secret as `{name}` to `{callee}`."
),
cwe: Some("CWE-798"),
remediation: "Supply credentials from protected configuration at \
runtime, not as a literal argument.",
});
}
}
}
}
}
let _ = line;
}
fn check_safety_bypass(target: &Expr, value: &Expr, line: u32, pou: &str, hits: &mut Vec<RuleHit>) {
let Some(name) = flatten_ident(target) else {
return;
};
let n = name.to_ascii_lowercase();
let safety = [
"safety",
"estop",
"e_stop",
"emergency",
"interlock",
"guard",
"permit",
]
.iter()
.any(|h| n.contains(h));
let watchdog = n.contains("watchdog") || n.contains("wdt");
// A safety enable / interlock / watchdog signal driven to FALSE or 0 in
// application logic is a bypass (e.g. `Safety_Enable := FALSE`, `Watchdog_Kick := 0`).
let disabling = matches!(value, Expr::Bool(false, _)) || matches!(value, Expr::Int(0, _));
if (safety || watchdog) && disabling {
hits.push(RuleHit {
line,
severity: Severity::Critical,
rule_id: "plc-safety-bypass",
title: "Safety interlock / watchdog disabled in logic".to_string(),
description: format!(
"POU `{pou}` disables a safety-related signal (`{name}`) in program logic. \
Bypassing interlocks or watchdogs in code defeats the plant's protective \
functions and is a direct hazard."
),
cwe: Some("CWE-1384"),
remediation: "Never disable safety functions from application logic; safety must be \
handled by a certified safety controller / hard-wired circuit.",
});
}
}
fn check_array_bounds(
base: &Expr,
index: &Expr,
line: u32,
ctx: &Ctx,
pou: &str,
hits: &mut Vec<RuleHit>,
) {
// Only reason about arrays we know the bounds of.
let Some(arr_name) = base.as_ident() else {
return;
};
if !ctx.arrays.contains_key(&arr_name.to_ascii_lowercase()) {
return;
}
// Index by an untrusted input variable → potential out-of-bounds access.
if let Some(idx_name) = index.as_ident() {
if ctx.input_vars.contains(&idx_name.to_ascii_lowercase()) {
hits.push(RuleHit {
line,
severity: Severity::High,
rule_id: "plc-array-unchecked-index",
title: "Array indexed by unvalidated input".to_string(),
description: format!(
"POU `{pou}` indexes array `{arr_name}` with the input variable `{idx_name}` \
without a validated bounds check. An out-of-range index corrupts adjacent \
memory or faults the PLC (loss of control)."
),
cwe: Some("CWE-129"),
remediation: "Clamp or validate the index against the array bounds (e.g. \
`LIMIT`/explicit `IF idx >= lo AND idx <= hi`) before the access.",
});
}
}
}
fn check_division(
divisor: &Expr,
line: u32,
pou: &str,
guards: &GuardSet,
hits: &mut Vec<RuleHit>,
) {
// A divisor proven non-zero by an enclosing guard is safe.
if let Expr::Ident(name, _) = divisor {
if guards.is_nonzero(&name.to_ascii_lowercase()) {
return;
}
}
// Flag division by a variable (could be zero); nonzero literals are fine.
let risky = matches!(
divisor,
Expr::Ident(_, _) | Expr::Member { .. } | Expr::Index { .. } | Expr::Int(0, _)
);
if risky {
hits.push(RuleHit {
line,
severity: Severity::Medium,
rule_id: "plc-division-by-zero",
title: "Division by a variable without a zero-guard".to_string(),
description: format!(
"POU `{pou}` divides by a variable that is not proven non-zero. A zero divisor \
raises a PLC exception and can halt the scan cycle (denial of control)."
),
cwe: Some("CWE-369"),
remediation: "Guard the divisor (`IF d <> 0 THEN …`) or use a safe-divide helper that \
returns a defined value for a zero denominator.",
});
}
}
fn check_insecure_comm(
callee: &str,
args: &[CallArg],
line: u32,
pou: &str,
hits: &mut Vec<RuleHit>,
) {
let c = callee.to_ascii_lowercase();
let is_comm = COMM_FB_HINTS.iter().any(|h| c.contains(h));
if !is_comm {
return;
}
// Auth/encryption explicitly disabled.
for a in args {
if let Some(name) = &a.name {
let n = name.to_ascii_lowercase();
let security_flag = ["auth", "secure", "encrypt", "tls", "ssl", "authentication"]
.iter()
.any(|h| n.contains(h));
if security_flag && matches!(a.value, Expr::Bool(false, _)) {
hits.push(RuleHit {
line,
severity: Severity::High,
rule_id: "plc-insecure-comm",
title: "Network communication with security disabled".to_string(),
description: format!(
"POU `{pou}` calls `{callee}` with `{name} := FALSE`, disabling \
authentication/encryption on an industrial network link."
),
cwe: Some("CWE-319"),
remediation: "Enable authentication + transport encryption; segment OT \
networks and restrict the endpoint to trusted peers.",
});
}
}
// Well-known cleartext port literal.
if let Expr::Int(p, _) = &a.value {
if INSECURE_PORTS.contains(p) {
hits.push(RuleHit {
line,
severity: Severity::Medium,
rule_id: "plc-insecure-protocol-port",
title: "Cleartext industrial protocol port".to_string(),
description: format!(
"POU `{pou}` opens `{callee}` on port {p}, a well-known cleartext OT \
protocol port with no built-in authentication or encryption."
),
cwe: Some("CWE-319"),
remediation: "Front the protocol with a secure gateway/VPN, or use the \
authenticated/encrypted variant; never expose it to untrusted \
networks.",
});
}
}
}
let _ = line;
}
/// The dotted/base identifier of an lvalue expression (`a`, `a.b` → `a.b`,
/// `a[i]` → `a`), for name-based rules.
fn flatten_ident(e: &Expr) -> Option<String> {
match e {
Expr::Ident(n, _) => Some(n.clone()),
Expr::Member { base, field, .. } => flatten_ident(base).map(|b| format!("{b}.{field}")),
Expr::Index { base, .. } => flatten_ident(base),
_ => None,
}
}
#[cfg(test)]
mod tests {
use super::*;
use crate::pipeline::plc::parser;
const VULN: &str = r#"
FUNCTION_BLOCK CommCtrl
VAR_INPUT
cmdIndex : INT;
END_VAR
VAR
Password : STRING := 'admin123';
buffer : ARRAY[0..15] OF INT;
Safety_Enable : BOOL := TRUE;
divisor : INT;
result : INT;
END_VAR
Safety_Enable := FALSE;
result := 100 / divisor;
buffer[cmdIndex] := 1;
Modbus_Connect(IP := '192.168.0.10', PORT := 502, AUTH := FALSE);
IF cmdIndex > 100 THEN
JMP fault;
END_IF;
fault:
result := 0;
END_FUNCTION_BLOCK
"#;
fn rule_ids(src: &str) -> Vec<&'static str> {
parser::parse(src)
.iter()
.flat_map(analyze)
.map(|h| h.rule_id)
.collect()
}
#[test]
fn vulnerable_program_triggers_every_rule() {
let ids = rule_ids(VULN);
for expected in [
"plc-hardcoded-credential",
"plc-default-password",
"plc-safety-bypass",
"plc-division-by-zero",
"plc-array-unchecked-index",
"plc-insecure-comm",
"plc-insecure-protocol-port",
"plc-unstructured-jump",
] {
assert!(
ids.contains(&expected),
"expected rule {expected}, got {ids:?}"
);
}
}
#[test]
fn clean_program_has_no_findings() {
let clean = r#"
PROGRAM Clean
VAR
a : INT := 5;
b : INT := 3;
total : INT;
END_VAR
IF b <> 0 THEN
total := a / b;
END_IF;
END_PROGRAM
"#;
assert!(rule_ids(clean).is_empty(), "clean program should be quiet");
}
}
@@ -0,0 +1,423 @@
//! Dynamic PLC testing via an ephemeral soft-PLC (#183).
//!
//! When a PLC/SPS target ships control logic but no reachable live device, the
//! agent instantiates that logic itself instead of trying to reach the customer's
//! OT network: it provisions a throwaway soft-PLC (OpenPLC) container in-cluster,
//! loads the program, starts the runtime, probes it over industrial protocols,
//! then tears the instance down. No customer network access, sandboxed, and
//! reproducible — destructive tests become safe because the target is ours.
//!
//! - [`provision`] owns the container lifecycle (sub-task 1 + 5).
//! - [`openplc`] loads the program into the running instance (sub-task 2).
//! - [`provision_and_test`] composes them with a hard deadline and guaranteed
//! teardown, and runs the ICS probe against the provisioned endpoint.
pub mod openplc;
pub mod provision;
use std::path::Path;
use std::time::Duration;
use secrecy::ExposeSecret;
use compliance_core::models::dast::{DastFinding, DastScanRun, DastTarget, DastTargetType};
use compliance_core::models::Finding;
use compliance_core::PlcRuntimeConfig;
use crate::error::AgentError;
pub use provision::{DockerSoftPlc, ProvisionedRuntime, SoftPlc};
/// The result of a DAST scan against a provisioned web endpoint.
#[derive(Debug)]
pub struct DastRunResult {
/// The scan-run record (linked to the onboarded target).
pub scan_run: DastScanRun,
/// The DAST findings.
pub findings: Vec<DastFinding>,
}
/// Everything a provision-and-test run produced: the ICS-probe findings plus, if
/// it ran, the DAST scan of the provisioned web endpoint. The caller persists
/// both — keeping this a plain data return means the whole run is portable to a
/// remote execution backend that just hands the results back.
#[derive(Debug, Default)]
pub struct ProvisionOutcome {
/// ICS-probe findings from the provisioned Modbus endpoint.
pub findings: Vec<Finding>,
/// DAST scan of the provisioned web endpoint, if it ran.
pub dast: Option<DastRunResult>,
}
/// A control-logic program ready to load into a soft-PLC: the source text plus a
/// cosmetic file name (OpenPLC re-stores it under its own name).
#[derive(Debug, Clone)]
pub struct PlcProgram {
/// The original file name (for the upload form; OpenPLC renames on storage).
pub file_name: String,
/// The program source — Structured Text or PLCopen XML.
pub source: String,
}
/// A cookie-aware HTTP client for the OpenPLC web UI. A fresh client per scan
/// isolates the OpenPLC session (its Flask login cookie) from every other scan.
pub fn http_client() -> Result<reqwest::Client, AgentError> {
reqwest::Client::builder()
.cookie_store(true)
.timeout(Duration::from_secs(30))
.build()
.map_err(AgentError::Http)
}
/// Pick the control-logic program to run from an ingested PLC source tree.
///
/// OpenPLC runs one program, so we choose the best single candidate: a complete
/// Structured Text program (one carrying a `CONFIGURATION` block) is ideal;
/// failing that the largest ST file; failing that a PLCopen XML export. Returns
/// `None` when the tree holds no loadable control logic.
pub fn extract_program(root: &Path) -> Option<PlcProgram> {
let mut st: Vec<(String, String)> = Vec::new();
let mut xml: Vec<(String, String)> = Vec::new();
for entry in walkdir::WalkDir::new(root)
.into_iter()
.filter_map(Result::ok)
{
if !entry.file_type().is_file() {
continue;
}
let path = entry.path();
let ext = path
.extension()
.and_then(|e| e.to_str())
.unwrap_or("")
.to_ascii_lowercase();
let is_st = matches!(ext.as_str(), "st" | "iecst" | "scl" | "exp" | "il");
let is_xml = matches!(ext.as_str(), "xml" | "plcopen" | "project");
if !is_st && !is_xml {
continue;
}
let Ok(content) = std::fs::read_to_string(path) else {
continue;
};
let name = path
.file_name()
.and_then(|n| n.to_str())
.unwrap_or("program")
.to_string();
if is_st {
st.push((name, content));
} else if looks_like_plcopen(&content) {
xml.push((name, content));
}
}
if let Some((name, source)) = st.iter().find(|(_, c)| has_configuration(c)) {
return Some(PlcProgram {
file_name: name.clone(),
source: source.clone(),
});
}
if let Some((name, source)) = st.iter().max_by_key(|(_, c)| c.len()) {
return Some(PlcProgram {
file_name: name.clone(),
source: source.clone(),
});
}
xml.into_iter()
.max_by_key(|(_, c)| c.len())
.map(|(file_name, source)| PlcProgram { file_name, source })
}
/// Whether an ST source is a complete, runnable program (has a `CONFIGURATION`).
fn has_configuration(source: &str) -> bool {
source.to_ascii_uppercase().contains("CONFIGURATION")
}
/// Whether an XML file looks like a PLCopen project export.
fn looks_like_plcopen(source: &str) -> bool {
let lower = source.to_ascii_lowercase();
lower.contains("<project") || lower.contains("plcopen")
}
/// Provision an ephemeral soft-PLC, load `program`, start it, probe it over
/// industrial protocols, and tear it down. Returns the ICS-probe findings.
///
/// Teardown is guaranteed: the load/probe work runs under a hard deadline
/// (`max_lifetime_secs`) and the instance is removed afterwards on every path —
/// success, error, or deadline expiry.
pub async fn provision_and_test<P: SoftPlc>(
provisioner: &P,
http: &reqwest::Client,
cfg: &PlcRuntimeConfig,
program: &PlcProgram,
target_id: &str,
) -> Result<ProvisionOutcome, AgentError> {
let handle = provisioner.provision(target_id).await?;
tracing::info!(
target_id,
instance = %handle.name,
modbus = %handle.modbus_endpoint,
"provisioned ephemeral soft-PLC"
);
let deadline = Duration::from_secs(cfg.max_lifetime_secs);
let result = tokio::time::timeout(
deadline,
run_dynamic_test(http, cfg, program, target_id, &handle),
)
.await;
// Guaranteed teardown — runs on success, error, and deadline expiry. The
// inner future is panic-free (the workspace lint bans unwrap/expect), so no
// unwind can skip this; a container leaked by an agent *crash* is swept by
// the next run's stale reaper.
provisioner.teardown(&handle).await;
match result {
Ok(inner) => inner,
Err(_) => {
tracing::warn!(
target_id,
instance = %handle.name,
"provision-and-test hit the lifetime deadline; torn down"
);
Ok(ProvisionOutcome::default())
}
}
}
/// The load → start → probe → DAST body, run under the caller's deadline.
async fn run_dynamic_test(
http: &reqwest::Client,
cfg: &PlcRuntimeConfig,
program: &PlcProgram,
target_id: &str,
handle: &ProvisionedRuntime,
) -> Result<ProvisionOutcome, AgentError> {
let ready_budget = Duration::from_secs((cfg.max_lifetime_secs / 3).clamp(10, 60));
openplc::wait_ready(http, &handle.webvisu_url, ready_budget).await?;
let compile_budget = Duration::from_secs((cfg.max_lifetime_secs / 2).clamp(20, 120));
openplc::load_and_start(
http,
&handle.webvisu_url,
&cfg.openplc_user,
cfg.openplc_password.expose_secret(),
program,
compile_budget,
)
.await?;
// Give the runtime a moment to open the Modbus/TCP server before probing.
tokio::time::sleep(Duration::from_secs(3)).await;
let probe_budget = Duration::from_secs(5);
let findings =
crate::pipeline::ics::probe_target(&handle.modbus_endpoint, target_id, probe_budget).await;
tracing::info!(
target_id,
instance = %handle.name,
found = findings.len(),
"provision-and-test probe complete"
);
// DAST the provisioned web endpoint (independently bounded so it can't eat
// the whole lifetime). On the OpenPLC substrate this is OpenPLC's own web UI,
// not a customer HMI — the CODESYS-runtime follow-up raises the fidelity —
// but it proves the deploy→run→probe→DAST loop end to end.
let dast_budget = Duration::from_secs((cfg.max_lifetime_secs / 2).clamp(20, 120));
let dast = match tokio::time::timeout(dast_budget, run_webvisu_dast(handle, target_id)).await {
Ok(d) => d,
Err(_) => {
tracing::warn!(target_id, instance = %handle.name, "provision-and-test DAST timed out");
None
}
};
Ok(ProvisionOutcome { findings, dast })
}
/// Run a bounded DAST scan against the provisioned web endpoint and tag the
/// results with our target id. Best-effort — a DAST failure never fails the run.
async fn run_webvisu_dast(handle: &ProvisionedRuntime, target_id: &str) -> Option<DastRunResult> {
let mut dt = DastTarget::new(
"provisioned-webvisu".to_string(),
handle.webvisu_url.clone(),
DastTargetType::WebApp,
);
dt.repo_id = Some(target_id.to_string());
dt.max_crawl_depth = 2; // shallow — the instance is ephemeral
let orchestrator = compliance_dast::DastOrchestrator::new(100);
match orchestrator.run_scan(&dt, Vec::new()).await {
Ok((mut scan_run, mut findings)) => {
scan_run.target_id = target_id.to_string();
for f in &mut findings {
f.target_id = target_id.to_string();
}
tracing::info!(
target_id,
instance = %handle.name,
dast_findings = findings.len(),
"provision-and-test DAST complete"
);
Some(DastRunResult { scan_run, findings })
}
Err(e) => {
tracing::warn!(target_id, instance = %handle.name, error = %e, "provision-and-test DAST failed");
None
}
}
}
#[cfg(test)]
#[allow(clippy::expect_used, clippy::unwrap_used)]
mod tests {
use super::*;
use std::sync::atomic::{AtomicUsize, Ordering};
use std::sync::Arc;
/// A scratch dir removed on drop.
struct Scratch(std::path::PathBuf);
impl Scratch {
fn new() -> Self {
let p = std::env::temp_dir().join(format!("cs-plc-rt-{}", uuid::Uuid::new_v4()));
std::fs::create_dir_all(&p).expect("mkdir");
Self(p)
}
}
impl Drop for Scratch {
fn drop(&mut self) {
let _ = std::fs::remove_dir_all(&self.0);
}
}
#[test]
fn extract_prefers_a_complete_st_program() {
let s = Scratch::new();
std::fs::write(s.0.join("fragment.st"), "PROGRAM P\nEND_PROGRAM\n").expect("w");
std::fs::write(
s.0.join("full.st"),
"PROGRAM Main\nEND_PROGRAM\nCONFIGURATION Config0\n RESOURCE R\nEND_CONFIGURATION\n",
)
.expect("w");
let prog = extract_program(&s.0).expect("program");
assert_eq!(prog.file_name, "full.st");
assert!(prog.source.contains("CONFIGURATION"));
}
#[test]
fn extract_falls_back_to_largest_st_then_plcopen() {
let s = Scratch::new();
std::fs::write(s.0.join("small.st"), "PROGRAM A\nEND_PROGRAM\n").expect("w");
std::fs::write(
s.0.join("big.st"),
"PROGRAM B\nVAR x : INT; y : INT; z : INT; END_VAR\nEND_PROGRAM\n",
)
.expect("w");
let prog = extract_program(&s.0).expect("program");
assert_eq!(
prog.file_name, "big.st",
"largest ST wins when none complete"
);
// Only a PLCopen XML present.
let s2 = Scratch::new();
std::fs::write(
s2.0.join("proj.xml"),
"<?xml version='1.0'?><project xmlns='http://www.plcopen.org/xml/tc6_0201'><pou/></project>",
)
.expect("w");
let prog2 = extract_program(&s2.0).expect("program");
assert_eq!(prog2.file_name, "proj.xml");
}
#[test]
fn extract_returns_none_without_control_logic() {
let s = Scratch::new();
std::fs::write(s.0.join("readme.md"), "# not a plc program").expect("w");
std::fs::write(s.0.join("data.xml"), "<config><db/></config>").expect("w");
assert!(extract_program(&s.0).is_none());
}
/// A fake provisioner recording provision/teardown calls, for lifecycle tests.
struct FakeSoftPlc {
provisions: Arc<AtomicUsize>,
teardowns: Arc<AtomicUsize>,
fail_provision: bool,
}
impl SoftPlc for FakeSoftPlc {
async fn provision(&self, _target_id: &str) -> Result<ProvisionedRuntime, AgentError> {
self.provisions.fetch_add(1, Ordering::SeqCst);
if self.fail_provision {
return Err(AgentError::Other("provision failed".into()));
}
// Unreachable address so run_dynamic_test blocks on readiness until the
// deadline fires — exercising the teardown-on-deadline path.
Ok(ProvisionedRuntime {
name: "fake-plc".into(),
modbus_endpoint: "fake-plc:502".into(),
webvisu_url: "http://fake-plc.invalid:8080".into(),
})
}
async fn teardown(&self, _handle: &ProvisionedRuntime) {
self.teardowns.fetch_add(1, Ordering::SeqCst);
}
}
fn short_cfg() -> PlcRuntimeConfig {
PlcRuntimeConfig {
enabled: true,
max_lifetime_secs: 1, // keep the deadline path fast
..PlcRuntimeConfig::default()
}
}
#[tokio::test]
async fn teardown_runs_even_when_the_test_never_completes() {
let provisions = Arc::new(AtomicUsize::new(0));
let teardowns = Arc::new(AtomicUsize::new(0));
let fake = FakeSoftPlc {
provisions: provisions.clone(),
teardowns: teardowns.clone(),
fail_provision: false,
};
let http = http_client().expect("client");
let prog = PlcProgram {
file_name: "p.st".into(),
source: "PROGRAM P\nEND_PROGRAM\n".into(),
};
let out = provision_and_test(&fake, &http, &short_cfg(), &prog, "t1")
.await
.expect("ok on deadline");
assert!(out.findings.is_empty(), "deadline path yields no findings");
assert!(out.dast.is_none(), "deadline path runs no DAST");
assert_eq!(provisions.load(Ordering::SeqCst), 1);
assert_eq!(teardowns.load(Ordering::SeqCst), 1, "teardown must run");
}
#[tokio::test]
async fn provision_failure_propagates_and_skips_teardown() {
let provisions = Arc::new(AtomicUsize::new(0));
let teardowns = Arc::new(AtomicUsize::new(0));
let fake = FakeSoftPlc {
provisions: provisions.clone(),
teardowns: teardowns.clone(),
fail_provision: true,
};
let http = http_client().expect("client");
let prog = PlcProgram {
file_name: "p.st".into(),
source: String::new(),
};
let err = provision_and_test(&fake, &http, &short_cfg(), &prog, "t1").await;
assert!(err.is_err(), "provision failure propagates");
assert_eq!(provisions.load(Ordering::SeqCst), 1);
assert_eq!(
teardowns.load(Ordering::SeqCst),
0,
"nothing to tear down when provisioning failed"
);
}
}
@@ -0,0 +1,254 @@
//! Loading a control-logic program into a provisioned OpenPLC (#183, sub-task 2).
//!
//! Drives the OpenPLC v3 web UI over HTTP to turn a static control-logic artifact
//! into a *running* PLC: log in, upload the program, save it, compile it (MatIEC),
//! and start the runtime — at which point OpenPLC opens its Modbus/TCP server on
//! 502 and the ICS probe has something to talk to. The endpoint sequence mirrors
//! the OpenPLC web UI: `POST /login` → `POST /upload-program` (which hands back a
//! server-assigned `prog_file`) → `POST /upload-program-action` →
//! `GET /compile-program?file=<prog_file>` → `GET /start_plc`.
use std::time::Duration;
use crate::error::AgentError;
use super::PlcProgram;
/// Default OpenPLC program name/description recorded in its UI.
const PROG_NAME: &str = "certifai-provisioned";
const PROG_DESCR: &str = "Uploaded by the Certifai provision-and-test scan";
/// Poll interval while waiting for readiness / compilation.
const POLL_INTERVAL: Duration = Duration::from_secs(2);
/// Wait until the OpenPLC web UI answers (any non-5xx reply to `/login`), or the
/// budget elapses. A freshly-started container needs a few seconds to boot.
pub async fn wait_ready(
http: &reqwest::Client,
base_url: &str,
budget: Duration,
) -> Result<(), AgentError> {
let login = format!("{base_url}/login");
let outcome = tokio::time::timeout(budget, async {
loop {
if let Ok(resp) = http.get(&login).send().await {
if !resp.status().is_server_error() {
return;
}
}
tokio::time::sleep(POLL_INTERVAL).await;
}
})
.await;
outcome.map_err(|_| AgentError::Other(format!("OpenPLC at {base_url} did not become ready")))
}
/// Log in, upload the program, compile it, and start the runtime. On success the
/// OpenPLC Modbus/TCP server is listening on 502.
pub async fn load_and_start(
http: &reqwest::Client,
base_url: &str,
user: &str,
password: &str,
program: &PlcProgram,
compile_budget: Duration,
) -> Result<(), AgentError> {
login(http, base_url, user, password).await?;
let prog_file = upload_program(http, base_url, program).await?;
save_program(http, base_url, &prog_file).await?;
compile(http, base_url, &prog_file, compile_budget).await?;
start(http, base_url).await?;
Ok(())
}
/// `POST /login` — establishes the session cookie (the client must have a cookie
/// store; see the provision-and-test entry point).
async fn login(
http: &reqwest::Client,
base_url: &str,
user: &str,
password: &str,
) -> Result<(), AgentError> {
let resp = http
.post(format!("{base_url}/login"))
.form(&[("username", user), ("password", password)])
.send()
.await?;
if resp.status().is_server_error() {
return Err(AgentError::Other(format!(
"OpenPLC login failed: HTTP {}",
resp.status()
)));
}
Ok(())
}
/// `POST /upload-program` (multipart `file`) — OpenPLC stores the program under a
/// server-assigned name and returns it in a hidden `prog_file` form field, which
/// we parse out for the follow-up save/compile steps.
async fn upload_program(
http: &reqwest::Client,
base_url: &str,
program: &PlcProgram,
) -> Result<String, AgentError> {
let part = reqwest::multipart::Part::text(program.source.clone())
.file_name(program.file_name.clone())
.mime_str("application/octet-stream")?;
let form = reqwest::multipart::Form::new().part("file", part);
let resp = http
.post(format!("{base_url}/upload-program"))
.multipart(form)
.send()
.await?;
let html = resp.text().await?;
parse_prog_file(&html).ok_or_else(|| {
AgentError::Other("OpenPLC upload did not return a prog_file handle".to_string())
})
}
/// `POST /upload-program-action` — records the uploaded program in OpenPLC's
/// program list. `epoch_time` must be close to the server's clock (OpenPLC
/// rejects stale timestamps), so we send the current time.
async fn save_program(
http: &reqwest::Client,
base_url: &str,
prog_file: &str,
) -> Result<(), AgentError> {
let epoch = std::time::SystemTime::now()
.duration_since(std::time::UNIX_EPOCH)
.map(|d| d.as_secs())
.unwrap_or(0)
.to_string();
let resp = http
.post(format!("{base_url}/upload-program-action"))
.form(&[
("prog_name", PROG_NAME),
("prog_descr", PROG_DESCR),
("prog_file", prog_file),
("epoch_time", &epoch),
])
.send()
.await?;
if resp.status().is_server_error() {
return Err(AgentError::Other(format!(
"OpenPLC save-program failed: HTTP {}",
resp.status()
)));
}
Ok(())
}
/// `GET /compile-program?file=<prog_file>` then poll `/compilation-logs` until
/// MatIEC reports it finished (or the budget elapses). Errors if compilation
/// finishes with errors — a program that won't compile can't be started.
async fn compile(
http: &reqwest::Client,
base_url: &str,
prog_file: &str,
budget: Duration,
) -> Result<(), AgentError> {
http.get(format!("{base_url}/compile-program"))
.query(&[("file", prog_file)])
.send()
.await?;
let logs_url = format!("{base_url}/compilation-logs");
let outcome = tokio::time::timeout(budget, async {
loop {
if let Ok(resp) = http.get(&logs_url).send().await {
if let Ok(text) = resp.text().await {
if compilation_finished(&text) {
return !compilation_failed(&text);
}
}
}
tokio::time::sleep(POLL_INTERVAL).await;
}
})
.await;
match outcome {
Ok(true) => Ok(()),
Ok(false) => Err(AgentError::Other(
"OpenPLC compilation finished with errors".to_string(),
)),
Err(_) => Err(AgentError::Other(
"OpenPLC compilation did not finish in time".to_string(),
)),
}
}
/// `GET /start_plc` — starts the runtime, opening Modbus/TCP on 502.
async fn start(http: &reqwest::Client, base_url: &str) -> Result<(), AgentError> {
let resp = http.get(format!("{base_url}/start_plc")).send().await?;
if resp.status().is_server_error() {
return Err(AgentError::Other(format!(
"OpenPLC start_plc failed: HTTP {}",
resp.status()
)));
}
Ok(())
}
/// Extract the server-assigned `prog_file` from the `/upload-program` response,
/// which embeds it in a hidden input. Attribute order varies, so accept both
/// `value=… name='prog_file'` and `name='prog_file' … value=…`.
fn parse_prog_file(html: &str) -> Option<String> {
// The OpenPLC template renders `value='<name>.st' id='prog_file'
// name='prog_file'`. Match the value bound to that input, either order.
let value_then_name =
regex::Regex::new(r#"(?is)value=['"]([^'"]+)['"][^>]*name=['"]prog_file['"]"#).ok()?;
if let Some(c) = value_then_name.captures(html) {
return c.get(1).map(|m| m.as_str().to_string());
}
let name_then_value =
regex::Regex::new(r#"(?is)name=['"]prog_file['"][^>]*value=['"]([^'"]+)['"]"#).ok()?;
name_then_value
.captures(html)
.and_then(|c| c.get(1))
.map(|m| m.as_str().to_string())
}
/// Whether the MatIEC compilation log shows the build has finished (either way).
fn compilation_finished(log: &str) -> bool {
log.contains("Compilation finished")
}
/// Whether a finished compilation ended in failure.
fn compilation_failed(log: &str) -> bool {
log.contains("Compilation finished with errors")
}
#[cfg(test)]
#[allow(clippy::expect_used, clippy::unwrap_used)]
mod tests {
use super::*;
#[test]
fn parses_prog_file_value_then_name() {
let html = "<form><input type='hidden' value='483927.st' id='prog_file' \
name='prog_file'/></form>";
assert_eq!(parse_prog_file(html), Some("483927.st".to_string()));
}
#[test]
fn parses_prog_file_name_then_value() {
let html = r#"<input name="prog_file" id="prog_file" value="12.st" />"#;
assert_eq!(parse_prog_file(html), Some("12.st".to_string()));
}
#[test]
fn parse_prog_file_none_when_absent() {
assert_eq!(parse_prog_file("<html>no form here</html>"), None);
}
#[test]
fn compilation_predicates() {
assert!(!compilation_finished("Compiling..."));
assert!(compilation_finished(
"...\nCompilation finished successfully!\n"
));
assert!(compilation_finished("Compilation finished with errors!"));
assert!(compilation_failed("Compilation finished with errors!"));
assert!(!compilation_failed("Compilation finished successfully!"));
}
}
@@ -0,0 +1,306 @@
//! Ephemeral soft-PLC container lifecycle (#183, sub-task 1 + 5).
//!
//! Provisions a throwaway OpenPLC container per scan, isolated on the agent's own
//! Docker network with hard resource caps and **no host port exposure**, then
//! guarantees teardown. The container is reachable in-cluster only, by its name
//! (the shared user-defined network's embedded DNS resolves it); it is never
//! published to the host.
//!
//! The `docker` argv is produced by pure functions so provisioning is unit-tested
//! without a Docker daemon — only the thin [`run_docker`] wrapper touches the OS.
//! It requires the agent's runtime to have Docker access (a socket mount), which
//! is why the whole path is gated behind [`PlcRuntimeConfig::enabled`].
use std::time::{SystemTime, UNIX_EPOCH};
use compliance_core::PlcRuntimeConfig;
use crate::error::AgentError;
/// The Modbus/TCP port an OpenPLC instance opens once a program is running.
const MODBUS_PORT: u16 = 502;
/// The OpenPLC web-UI / WebVisu port.
const WEBVISU_PORT: u16 = 8080;
/// Label key marking a container as an ephemeral PLC runtime we own.
const OWNER_LABEL_KEY: &str = "certifai.ephemeral";
/// Label value for our ephemeral PLC runtimes.
const OWNER_LABEL_VALUE: &str = "plc-runtime";
/// A running ephemeral soft-PLC instance. Reachable in-cluster by `name`.
#[derive(Debug, Clone)]
pub struct ProvisionedRuntime {
/// The container name — also its in-network DNS alias.
pub name: String,
/// `name:502` — the Modbus/TCP endpoint the ICS probe targets.
pub modbus_endpoint: String,
/// `http://name:8080` — the WebVisu / OpenPLC web UI.
pub webvisu_url: String,
}
/// A source of ephemeral soft-PLC instances. Abstracted so the provision-and-test
/// orchestration is unit-testable with a fake that never touches Docker.
pub trait SoftPlc {
/// Start a fresh instance for a target and return its handle.
fn provision(
&self,
target_id: &str,
) -> impl std::future::Future<Output = Result<ProvisionedRuntime, AgentError>> + Send;
/// Tear an instance down. Best-effort and idempotent — never fails the scan.
fn teardown(&self, handle: &ProvisionedRuntime)
-> impl std::future::Future<Output = ()> + Send;
}
/// Provisions OpenPLC instances by shelling out to the Docker CLI.
pub struct DockerSoftPlc {
cfg: PlcRuntimeConfig,
}
impl DockerSoftPlc {
/// Build a provisioner from the PLC-runtime config.
pub fn new(cfg: PlcRuntimeConfig) -> Self {
Self { cfg }
}
}
impl SoftPlc for DockerSoftPlc {
async fn provision(&self, target_id: &str) -> Result<ProvisionedRuntime, AgentError> {
// Best-effort sweep of any container leaked by a crashed earlier run
// before we add another. Only removes instances past their max lifetime,
// so it can never disturb a concurrent run.
reap_stale(&self.cfg, now_epoch()).await;
let name = instance_name(target_id, now_epoch(), &random_suffix());
let args = run_args(&self.cfg, &name, target_id);
let out = run_docker(&args).await?;
if !out.status.success() {
return Err(AgentError::Other(format!(
"docker run for soft-PLC {name} failed: {}",
String::from_utf8_lossy(&out.stderr).trim()
)));
}
Ok(ProvisionedRuntime {
modbus_endpoint: format!("{name}:{MODBUS_PORT}"),
webvisu_url: format!("http://{name}:{WEBVISU_PORT}"),
name,
})
}
async fn teardown(&self, handle: &ProvisionedRuntime) {
match run_docker(&rm_args(&handle.name)).await {
Ok(out) if out.status.success() => {
tracing::info!(instance = %handle.name, "soft-PLC instance torn down");
}
Ok(out) => tracing::warn!(
instance = %handle.name,
"soft-PLC teardown non-zero exit: {}",
String::from_utf8_lossy(&out.stderr).trim()
),
Err(e) => {
tracing::warn!(instance = %handle.name, error = %e, "soft-PLC teardown failed")
}
}
}
}
/// Seconds since the Unix epoch (0 if the clock is before 1970, which never
/// happens in practice).
fn now_epoch() -> u64 {
SystemTime::now()
.duration_since(UNIX_EPOCH)
.map(|d| d.as_secs())
.unwrap_or(0)
}
/// A short random, docker-name-safe suffix.
fn random_suffix() -> String {
uuid::Uuid::new_v4().simple().to_string()
}
/// A unique, docker-safe container name that encodes the creation epoch (for the
/// stale reaper) and the target it belongs to. Shape:
/// `certifai-plc-<epoch>-<target12>-<rand6>`.
fn instance_name(target_id: &str, epoch: u64, rand: &str) -> String {
let short: String = target_id
.chars()
.filter(char::is_ascii_alphanumeric)
.take(12)
.collect();
let rand: String = rand
.chars()
.filter(char::is_ascii_alphanumeric)
.take(6)
.collect();
format!("certifai-plc-{epoch}-{short}-{rand}")
}
/// The creation epoch encoded in an instance name, if it is one of ours.
fn parse_epoch(name: &str) -> Option<u64> {
name.strip_prefix("certifai-plc-")?
.split('-')
.next()?
.parse()
.ok()
}
/// The `docker run` argv for an ephemeral soft-PLC: detached, joined to the
/// agent's network, resource-capped, hardened, labelled for reaping, and — by
/// omitting any `-p` — never published to the host.
fn run_args(cfg: &PlcRuntimeConfig, name: &str, target_id: &str) -> Vec<String> {
vec![
"run".into(),
"-d".into(),
"--name".into(),
name.into(),
"--network".into(),
cfg.network.clone(),
"--memory".into(),
cfg.memory.clone(),
"--cpus".into(),
cfg.cpus.clone(),
"--pids-limit".into(),
"512".into(),
"--security-opt".into(),
"no-new-privileges".into(),
"--stop-timeout".into(),
"5".into(),
"--label".into(),
format!("{OWNER_LABEL_KEY}={OWNER_LABEL_VALUE}"),
"--label".into(),
format!("certifai.target={target_id}"),
cfg.image.clone(),
]
}
/// The `docker rm -f` argv that stops and removes an instance.
fn rm_args(name: &str) -> Vec<String> {
vec!["rm".into(), "-f".into(), name.into()]
}
/// The `docker ps` argv listing the names of every ephemeral PLC container we own.
fn reap_list_args() -> Vec<String> {
vec![
"ps".into(),
"-a".into(),
"--filter".into(),
format!("label={OWNER_LABEL_KEY}={OWNER_LABEL_VALUE}"),
"--format".into(),
"{{.Names}}".into(),
]
}
/// Remove any ephemeral PLC container older than twice the configured max
/// lifetime — i.e. one a crashed run leaked. The generous threshold guarantees a
/// container from a *live* run (still within its own deadline) is never swept.
/// Best-effort: any Docker error (e.g. no daemon) is ignored.
async fn reap_stale(cfg: &PlcRuntimeConfig, now: u64) {
let cutoff = cfg.max_lifetime_secs.saturating_mul(2);
let Ok(out) = run_docker(&reap_list_args()).await else {
return;
};
if !out.status.success() {
return;
}
let names = String::from_utf8_lossy(&out.stdout);
for name in names.lines().map(str::trim).filter(|n| !n.is_empty()) {
let Some(epoch) = parse_epoch(name) else {
continue;
};
if now.saturating_sub(epoch) > cutoff {
tracing::warn!(instance = %name, "reaping stale soft-PLC instance");
let _ = run_docker(&rm_args(name)).await;
}
}
}
/// Run a `docker` subcommand, capturing its output.
async fn run_docker(args: &[String]) -> Result<std::process::Output, AgentError> {
tokio::process::Command::new("docker")
.args(args)
.output()
.await
.map_err(AgentError::Io)
}
#[cfg(test)]
#[allow(clippy::expect_used, clippy::unwrap_used)]
mod tests {
use super::*;
fn cfg() -> PlcRuntimeConfig {
PlcRuntimeConfig {
enabled: true,
image: "registry.example.com/openplc:latest".into(),
network: "certifai".into(),
memory: "512m".into(),
cpus: "0.5".into(),
max_lifetime_secs: 180,
..PlcRuntimeConfig::default()
}
}
#[test]
fn instance_name_is_unique_docker_safe_and_reaper_parseable() {
let a = instance_name("64f0aabbccddeeff00112233", 1_700_000_000, "abcdef123456");
assert_eq!(a, "certifai-plc-1700000000-64f0aabbccdd-abcdef");
assert_eq!(parse_epoch(&a), Some(1_700_000_000));
// Docker names: only [A-Za-z0-9_.-].
assert!(a
.chars()
.all(|c| c.is_ascii_alphanumeric() || matches!(c, '_' | '.' | '-')));
// A different random suffix yields a different name for the same target.
let b = instance_name("64f0aabbccddeeff00112233", 1_700_000_000, "zzzzzz999999");
assert_ne!(a, b);
}
#[test]
fn parse_epoch_rejects_foreign_names() {
assert_eq!(parse_epoch("some-other-container"), None);
assert_eq!(parse_epoch("certifai-plc-notanumber-x"), None);
}
#[test]
fn run_args_cap_resources_harden_label_and_never_publish_a_port() {
let args = run_args(&cfg(), "certifai-plc-1-t-r", "target-123");
// No host port publishing.
assert!(!args.iter().any(|a| a == "-p" || a == "--publish"));
// Detached.
assert!(args.contains(&"-d".to_string()));
// Joined to the agent's own network.
let net = args.iter().position(|a| a == "--network").expect("network");
assert_eq!(args[net + 1], "certifai");
// Resource caps.
let mem = args.iter().position(|a| a == "--memory").expect("memory");
assert_eq!(args[mem + 1], "512m");
let cpu = args.iter().position(|a| a == "--cpus").expect("cpus");
assert_eq!(args[cpu + 1], "0.5");
assert!(args.iter().any(|a| a == "--pids-limit"));
// Hardening.
let so = args
.iter()
.position(|a| a == "--security-opt")
.expect("secopt");
assert_eq!(args[so + 1], "no-new-privileges");
// Ownership + target labels for reaping / attribution.
assert!(args.contains(&"certifai.ephemeral=plc-runtime".to_string()));
assert!(args.contains(&"certifai.target=target-123".to_string()));
// Image is last.
assert_eq!(
args.last().map(String::as_str),
Some("registry.example.com/openplc:latest")
);
}
#[test]
fn rm_args_force_remove() {
assert_eq!(rm_args("x"), vec!["rm", "-f", "x"]);
}
#[test]
fn reap_list_filters_by_owner_label() {
let args = reap_list_args();
assert!(args.contains(&"label=certifai.ephemeral=plc-runtime".to_string()));
assert!(args.contains(&"{{.Names}}".to_string()));
}
}
+253
View File
@@ -0,0 +1,253 @@
//! Control-application dependency SBOM from a CODESYS `.projectarchive`.
//!
//! A `.projectarchive` is a ZIP that bundles the project plus its referenced
//! libraries and the target runtime. Each referenced library is an entry whose
//! path segment follows the CODESYS convention
//! `Name, Major.Minor.Patch.Build (Company)` (e.g. `Standard, 3.5.18.0 (System)`,
//! `CSV Utility SL, 1.9.0.0 (CODESYS)`); the runtime appears as a device-descriptor
//! entry `CODESYS Control … <version> …`. We enumerate those entries — no binary
//! parsing — and emit SBOM components tagged `pkg:codesys/…`, so the CVE pipeline
//! can match them (the runtime `Cmp*` / `3SLicense` components carry real CODESYS
//! CVEs).
use std::collections::BTreeSet;
use std::path::{Path, PathBuf};
use compliance_core::models::SbomEntry;
/// Collect the control-application SBOM from every `.projectarchive` reachable for
/// a target: the ingested artifact file itself (an uploaded archive), plus any
/// `*.projectarchive` committed inside the working tree — e.g. a git repo or an
/// extracted source archive that ships the archive alongside its PLCopen XML / ST
/// exports. Deduplicated by (name, version).
pub fn collect_sbom(artifact_file: &Path, working_path: &Path, repo_id: &str) -> Vec<SbomEntry> {
let mut archives: Vec<PathBuf> = Vec::new();
if artifact_file.is_file() {
archives.push(artifact_file.to_path_buf());
}
for entry in walkdir::WalkDir::new(working_path)
.max_depth(8)
.into_iter()
.filter_map(|e| e.ok())
{
let p = entry.path();
if entry.file_type().is_file()
&& p.extension()
.and_then(|x| x.to_str())
.is_some_and(|x| x.eq_ignore_ascii_case("projectarchive"))
{
archives.push(p.to_path_buf());
}
}
let mut seen: BTreeSet<(String, String)> = BTreeSet::new();
let mut out = Vec::new();
for a in archives {
for e in projectarchive_sbom(&a, repo_id) {
if seen.insert((e.name.clone(), e.version.clone())) {
out.push(e);
}
}
}
out
}
/// Extract CODESYS library + runtime components from a `.projectarchive` (a zip).
/// Best-effort: returns empty if the file is not a readable zip (e.g. a bare
/// `.st`/`.xml` project, which carries no library manifest).
pub fn projectarchive_sbom(archive: &Path, repo_id: &str) -> Vec<SbomEntry> {
let Ok(file) = std::fs::File::open(archive) else {
return Vec::new();
};
let Ok(mut zip) = zip::ZipArchive::new(file) else {
return Vec::new();
};
let mut seen: BTreeSet<(String, String)> = BTreeSet::new();
let mut entries = Vec::new();
for i in 0..zip.len() {
let Ok(entry) = zip.by_index(i) else {
continue;
};
// Entry paths use `\` (Windows-authored) and/or `/` separators; the
// component id is one path segment.
for seg in entry.name().split(['/', '\\']) {
if let Some((name, version)) = parse_library(seg).or_else(|| parse_runtime(seg)) {
if seen.insert((name.clone(), version.clone())) {
let mut e = SbomEntry::new(
repo_id.to_string(),
name.clone(),
version.clone(),
"codesys".to_string(),
);
e.purl = Some(format!(
"pkg:codesys/{}@{version}",
name.replace(' ', "%20")
));
entries.push(e);
}
}
}
}
entries
}
/// `Name, X.Y.Z.W (Company)` → (name, version).
fn parse_library(seg: &str) -> Option<(String, String)> {
let seg = seg.trim();
// Company is the trailing "(…)".
let open = seg.rfind(" (")?;
let rest = &seg[open + 2..];
let close = rest.find(')')?;
if rest[..close].trim().is_empty() {
return None;
}
let head = seg[..open].trim(); // "Name, X.Y.Z.W"
let comma = head.rfind(", ")?;
let name = head[..comma].trim().to_string();
let version = head[comma + 2..].trim().to_string();
if name.is_empty() || !is_dotted_version(&version) {
return None;
}
Some((name, version))
}
/// Device-descriptor entry `CODESYS Control … X.Y.Z.W …` → (runtime name, version).
fn parse_runtime(seg: &str) -> Option<(String, String)> {
let seg = seg.trim();
if !seg.starts_with("CODESYS Control") {
return None;
}
let version = seg
.split_whitespace()
.find(|t| is_dotted_version(t))?
.to_string();
// The runtime name is the first field, before the run of padding spaces that
// precede the descriptor's numeric columns.
let name = seg.split(" ").next().unwrap_or(seg).trim().to_string();
if name.is_empty() {
return None;
}
Some((name, version))
}
/// A dotted numeric version with at least 3 components (`3.5.18.0`, `4.17.0.0`).
fn is_dotted_version(s: &str) -> bool {
let parts: Vec<&str> = s.split('.').collect();
parts.len() >= 3
&& parts
.iter()
.all(|p| !p.is_empty() && p.chars().all(|c| c.is_ascii_digit()))
}
#[cfg(test)]
mod tests {
use super::*;
use std::collections::HashMap;
use std::io::Write;
/// Build a synthetic `.projectarchive` (zip) mirroring the real CODESYS entry
/// naming (verified against Proemion/codesys-examples): a native `.project`,
/// referenced libraries as `Name, Version (Company)` segments, and a runtime
/// device descriptor.
fn synthetic_archive(dir: &Path) -> std::path::PathBuf {
let path = dir.join("App.projectarchive");
write_synthetic_archive(&path);
path
}
fn write_synthetic_archive(path: &Path) {
let file = std::fs::File::create(path).expect("create");
let mut zip = zip::ZipWriter::new(file);
let opts: zip::write::SimpleFileOptions = Default::default();
let names = [
"App.project",
r"{b0b5}\App.Device.Plc.compileinfo",
r"{e179}\Standard, 3.5.18.0 (System) standard.compiled-library-v3",
r"{e179}\Util, 3.5.21.0 (System) util.compiled-library-v3",
r"{e179}\CSV Utility SL, 1.9.0.0 (CODESYS) csv utility sl.compiled-library-v3",
r"{e179}\3SLicense, 3.5.20.0 (CODESYS) 3slicense.compiled-library-v3",
r"{0c63}\CODESYS Control for Linux ARM SL 0000 0006 4.17.0.0 4096 .zip",
];
for n in names {
zip.start_file(n, opts).expect("start");
zip.write_all(b"x").expect("write");
}
zip.finish().expect("finish");
}
#[test]
fn extracts_libraries_and_runtime_from_projectarchive() {
let tmp = std::env::temp_dir().join(format!("cs-plc-sbom-{}", uuid::Uuid::new_v4()));
std::fs::create_dir_all(&tmp).expect("mkdir");
let archive = synthetic_archive(&tmp);
let entries = projectarchive_sbom(&archive, "plc-target");
let by_name: HashMap<&str, &SbomEntry> =
entries.iter().map(|e| (e.name.as_str(), e)).collect();
// Libraries with their versions.
assert_eq!(
by_name.get("Standard").map(|e| e.version.as_str()),
Some("3.5.18.0")
);
assert_eq!(
by_name.get("Util").map(|e| e.version.as_str()),
Some("3.5.21.0")
);
assert_eq!(
by_name.get("CSV Utility SL").map(|e| e.version.as_str()),
Some("1.9.0.0"),
"multi-word library names must parse"
);
assert!(by_name.contains_key("3SLicense"));
// The runtime, from the device descriptor.
assert_eq!(
by_name
.get("CODESYS Control for Linux ARM SL")
.map(|e| e.version.as_str()),
Some("4.17.0.0")
);
// Every component is CODESYS-tagged with a purl the CVE pipeline can match,
// and the native `.project` / compileinfo are not mistaken for components.
for e in &entries {
assert_eq!(e.package_manager, "codesys");
assert!(e.purl.as_deref().unwrap_or("").starts_with("pkg:codesys/"));
}
assert!(!by_name.contains_key("App"));
let _ = std::fs::remove_dir_all(&tmp);
}
#[test]
fn collect_sbom_finds_a_projectarchive_committed_in_a_git_tree() {
let tmp = std::env::temp_dir().join(format!("cs-plc-collect-{}", uuid::Uuid::new_v4()));
let src = tmp.join("clone/src");
std::fs::create_dir_all(&src).expect("mkdir");
// Simulate a git clone that commits the archive alongside its exports.
write_synthetic_archive(&src.join("PumpStation.projectarchive"));
// The artifact "file" is a git URL (not a real file), so the SBOM must
// come from walking the cloned tree.
let entries = collect_sbom(Path::new("https://git.example/plc.git"), &tmp, "t");
let names: std::collections::HashSet<&str> =
entries.iter().map(|e| e.name.as_str()).collect();
assert!(
names.contains("Standard"),
"found libs in the committed archive"
);
assert!(names.contains("CODESYS Control for Linux ARM SL"));
let _ = std::fs::remove_dir_all(&tmp);
}
#[test]
fn non_zip_file_yields_no_sbom() {
let tmp = std::env::temp_dir().join(format!("cs-plc-sbom-st-{}", uuid::Uuid::new_v4()));
std::fs::create_dir_all(&tmp).expect("mkdir");
let st = tmp.join("prog.st");
std::fs::write(&st, "PROGRAM P\nVAR x : INT; END_VAR\nEND_PROGRAM\n").expect("write");
assert!(projectarchive_sbom(&st, "t").is_empty());
let _ = std::fs::remove_dir_all(&tmp);
}
}
+2 -1
View File
@@ -1,3 +1,4 @@
use crate::pipeline::repo_view::RepoView;
use compliance_core::models::*;
use super::dedup::compute_fingerprint;
@@ -14,7 +15,7 @@ impl PipelineOrchestrator {
#[tracing::instrument(skip_all, fields(repo_id = %repo_id, pr_number))]
pub async fn run_pr_review(
&self,
repo: &TrackedRepository,
repo: &RepoView,
repo_id: &str,
pr_number: u64,
base_sha: &str,
@@ -0,0 +1,74 @@
//! `RepoView` — an internal, non-persisted view of a code target for the scan
//! pipeline.
//!
//! It replaces the old persisted `TrackedRepository` model. The pipeline
//! (SAST → SBOM → CVE → triage → issues → DAST, and PR review) only ever needs a
//! flat bundle of git + issue-tracker + auth fields; those are projected from an
//! [`OnboardedTarget`] and its code [`Artifact`] by [`RepoView::from_target`].
//! Nothing here is written to Mongo — onboarded targets are the sole persisted
//! entity.
use compliance_core::models::{Artifact, OnboardedTarget, TrackerType};
/// A flat, pipeline-facing view of a code target. Built from an onboarded
/// target; never persisted.
#[derive(Debug, Clone)]
pub struct RepoView {
/// The onboarded target's id (used as `repo_id` across findings/sbom/etc.).
pub id: Option<mongodb::bson::oid::ObjectId>,
pub name: String,
pub git_url: String,
pub default_branch: String,
pub local_path: Option<String>,
pub scan_schedule: Option<String>,
pub webhook_enabled: bool,
pub webhook_secret: Option<String>,
pub tracker_type: Option<TrackerType>,
pub tracker_owner: Option<String>,
pub tracker_repo: Option<String>,
pub tracker_token: Option<String>,
pub auth_token: Option<String>,
pub auth_username: Option<String>,
pub last_scanned_commit: Option<String>,
pub findings_count: u32,
}
impl RepoView {
/// Project an onboarded target + its code artifact into a pipeline view.
pub fn from_target(target: &OnboardedTarget, code: &Artifact) -> Self {
let mut view = Self {
id: target.id,
name: target.name.clone(),
git_url: code.source_ref.clone(),
default_branch: "main".to_string(),
local_path: None,
scan_schedule: target.scan_schedule.clone(),
webhook_enabled: target.webhook_enabled,
webhook_secret: target.webhook_secret.clone(),
tracker_type: None,
tracker_owner: None,
tracker_repo: None,
tracker_token: None,
auth_token: None,
auth_username: None,
last_scanned_commit: None,
findings_count: target.findings_count,
};
if let Some(git) = &code.git {
view.default_branch = git.default_branch.clone();
view.last_scanned_commit = git.last_scanned_commit.clone();
view.local_path = git.local_path.clone();
}
if let Some(auth) = &code.auth {
view.auth_token = auth.secret.clone();
view.auth_username = auth.username.clone();
}
if let Some(it) = &target.scan_config.issue_tracker {
view.tracker_type = it.tracker_type.clone();
view.tracker_owner = it.owner.clone();
view.tracker_repo = it.repo.clone();
view.tracker_token = it.token.clone();
}
view
}
}
+8 -8
View File
@@ -288,25 +288,25 @@ async fn scan_all_repos(agent: &ComplianceAgent, tenant_id: &str) {
None => return,
};
let cursor = match db.repositories().find(doc! {}).await {
let cursor = match db.onboarded_targets().find(doc! {}).await {
Ok(c) => c,
Err(e) => {
tracing::error!("Failed to list repos for tenant '{tenant_id}': {e}");
tracing::error!("Failed to list targets for tenant '{tenant_id}': {e}");
return;
}
};
let repos: Vec<_> = cursor.filter_map(|r| async { r.ok() }).collect().await;
let targets: Vec<_> = cursor.filter_map(|r| async { r.ok() }).collect().await;
for repo in repos {
let repo_id = repo.id.map(|id| id.to_hex()).unwrap_or_default();
for target in targets {
let target_id = target.id.map(|id| id.to_hex()).unwrap_or_default();
if let Err(e) = agent
.run_scan(tenant_id, &repo_id, ScanTrigger::Scheduled)
.run_target_scan(tenant_id, &target_id, ScanTrigger::Scheduled)
.await
{
tracing::error!(
"Scheduled scan failed for {} (tenant '{tenant_id}'): {e}",
repo.name
target.name
);
}
}
@@ -348,7 +348,7 @@ async fn monitor_cves(agent: &ComplianceAgent, tenant_id: &str) {
std::collections::HashMap::new();
for rid in &repo_ids {
if let Ok(oid) = mongodb::bson::oid::ObjectId::parse_str(rid) {
if let Ok(Some(repo)) = db.repositories().find_one(doc! { "_id": oid }).await {
if let Ok(Some(repo)) = db.onboarded_targets().find_one(doc! { "_id": oid }).await {
repo_names.insert(rid.clone(), repo.name.clone());
}
}
+1 -1
View File
@@ -31,7 +31,7 @@ pub async fn handle_gitea_webhook(
}
};
let repo = match db
.repositories()
.onboarded_targets()
.find_one(mongodb::bson::doc! { "_id": oid })
.await
{
+1 -1
View File
@@ -31,7 +31,7 @@ pub async fn handle_github_webhook(
}
};
let repo = match db
.repositories()
.onboarded_targets()
.find_one(mongodb::bson::doc! { "_id": oid })
.await
{
+1 -1
View File
@@ -27,7 +27,7 @@ pub async fn handle_gitlab_webhook(
}
};
let repo = match db
.repositories()
.onboarded_targets()
.find_one(mongodb::bson::doc! { "_id": oid })
.await
{
+5 -2
View File
@@ -25,8 +25,9 @@ impl TestServer {
let mongodb_uri = std::env::var("TEST_MONGODB_URI")
.unwrap_or_else(|_| "mongodb://root:example@localhost:27017/?authSource=admin".into());
// Unique database name per test run to avoid collisions
let db_name = format!("test_{}", uuid::Uuid::new_v4().simple());
// Unique db-name prefix per run. Must fit the pool's 30-char cap
// (`<prefix>_<32 hex>` <= 63), so use a 16-hex-char suffix.
let db_name = format!("t_{}", &uuid::Uuid::new_v4().simple().to_string()[..16]);
let db_pool = DatabasePool::connect(&mongodb_uri, &db_name)
.await
@@ -44,6 +45,7 @@ impl TestServer {
scan_schedule: String::new(),
cve_monitor_schedule: String::new(),
git_clone_base_path: "/tmp/compliance-scanner-tests/repos".into(),
artifact_store_base_path: "/tmp/compliance-scanner-tests/artifacts".into(),
ssh_key_path: "/tmp/compliance-scanner-tests/ssh/id_ed25519".into(),
github_token: None,
github_webhook_secret: None,
@@ -68,6 +70,7 @@ impl TestServer {
pentest_imap_password: None,
admin_api_token: None,
tenant_registry_url: None,
plc_runtime: compliance_core::PlcRuntimeConfig::default(),
};
let agent = ComplianceAgent::new(config, db_pool);
@@ -113,15 +113,16 @@ async fn delete_repo_cascades_to_dast_and_pentest_data() {
// Create a repo
let resp = server
.post(
"/api/v1/repositories",
"/api/v1/targets",
&json!({
"name": "cascade-test",
"git_url": "https://github.com/example/cascade-test.git",
"target_type": "web_app",
"artifacts": [{ "kind": "git_repo", "source_ref": "https://github.com/example/cascade-test.git", "branch": "main" }],
}),
)
.await;
let body: serde_json::Value = resp.json().await.unwrap();
let repo_id = body["data"]["id"].as_str().unwrap().to_string();
let repo_id = body["data"]["_id"]["$oid"].as_str().unwrap().to_string();
// Insert DAST target linked to repo
let target_id = insert_dast_target(&server, &repo_id, "cascade-target").await;
@@ -140,9 +141,7 @@ async fn delete_repo_cascades_to_dast_and_pentest_data() {
assert_eq!(count_docs(&server, "dast_findings").await, 1);
// Delete the repo
let resp = server
.delete(&format!("/api/v1/repositories/{repo_id}"))
.await;
let resp = server.delete(&format!("/api/v1/targets/{repo_id}")).await;
assert_eq!(resp.status(), 200);
// All downstream data should be gone
@@ -161,15 +160,16 @@ async fn delete_repo_cascades_sast_findings_and_sbom() {
// Create a repo
let resp = server
.post(
"/api/v1/repositories",
"/api/v1/targets",
&json!({
"name": "sast-cascade",
"git_url": "https://github.com/example/sast-cascade.git",
"target_type": "web_app",
"artifacts": [{ "kind": "git_repo", "source_ref": "https://github.com/example/sast-cascade.git", "branch": "main" }],
}),
)
.await;
let body: serde_json::Value = resp.json().await.unwrap();
let repo_id = body["data"]["id"].as_str().unwrap().to_string();
let repo_id = body["data"]["_id"]["$oid"].as_str().unwrap().to_string();
// Insert SAST finding and SBOM entry
let mongodb_uri = std::env::var("TEST_MONGODB_URI")
@@ -209,9 +209,7 @@ async fn delete_repo_cascades_sast_findings_and_sbom() {
assert_eq!(count_docs(&server, "sbom_entries").await, 1);
// Delete repo
server
.delete(&format!("/api/v1/repositories/{repo_id}"))
.await;
server.delete(&format!("/api/v1/targets/{repo_id}")).await;
// Both should be gone
assert_eq!(count_docs(&server, "findings").await, 0);
@@ -2,5 +2,5 @@ mod cascade_delete;
mod dast;
mod findings;
mod health;
mod repositories;
mod onboarding;
mod stats;
@@ -0,0 +1,115 @@
use crate::common::TestServer;
use serde_json::json;
#[tokio::test]
async fn create_list_and_applicable_scans() {
let server = TestServer::start().await;
// Initially empty.
let resp = server.get("/api/v1/targets").await;
assert_eq!(resp.status(), 200);
let body: serde_json::Value = resp.json().await.unwrap();
assert_eq!(body["data"].as_array().unwrap().len(), 0);
// Create a web-app target with a git repo + a live URL.
let resp = server
.post(
"/api/v1/targets",
&json!({
"name": "acme-web",
"target_type": "web_app",
"artifacts": [
{ "kind": "git_repo", "source_ref": "https://git/acme.git", "branch": "main" },
{ "kind": "live_url", "source_ref": "https://acme.example.com" }
]
}),
)
.await;
assert_eq!(resp.status(), 200);
let body: serde_json::Value = resp.json().await.unwrap();
let id = body["data"]["_id"]["$oid"].as_str().unwrap().to_string();
assert!(!id.is_empty());
assert_eq!(body["data"]["artifacts"].as_array().unwrap().len(), 2);
// List returns it.
let resp = server.get("/api/v1/targets").await;
let body: serde_json::Value = resp.json().await.unwrap();
assert_eq!(body["data"].as_array().unwrap().len(), 1);
// Applicable scans: SAST present + DAST offered (live URL present), pentest supported.
let resp = server
.get(&format!("/api/v1/targets/{id}/applicable-scans"))
.await;
assert_eq!(resp.status(), 200);
let body: serde_json::Value = resp.json().await.unwrap();
let scans = body["data"]["scans"].as_array().unwrap();
let names: Vec<&str> = scans.iter().filter_map(|s| s["scan"].as_str()).collect();
assert!(names.contains(&"sast"));
assert!(names.contains(&"dast"));
assert_eq!(body["data"]["pentest_supported"], true);
server.cleanup().await;
}
#[tokio::test]
async fn detect_classifies_a_plc_target() {
let server = TestServer::start().await;
// A PLC project artifact is a strong kind-based signal.
let resp = server
.post(
"/api/v1/targets",
&json!({
"name": "line-controller",
"target_type": "backend_service", // deliberately wrong; detect should suggest PLC
"artifacts": [
{ "kind": "plc_project", "source_ref": "line.xml", "plc_format": "plcopen_xml" }
]
}),
)
.await;
let body: serde_json::Value = resp.json().await.unwrap();
let id = body["data"]["_id"]["$oid"].as_str().unwrap().to_string();
let resp = server
.post(&format!("/api/v1/targets/{id}/detect"), &json!({}))
.await;
assert_eq!(resp.status(), 200);
let body: serde_json::Value = resp.json().await.unwrap();
assert_eq!(body["data"]["classification"]["suggested"], "plc_sps");
server.cleanup().await;
}
#[tokio::test]
async fn add_artifact_and_delete_target() {
let server = TestServer::start().await;
let resp = server
.post(
"/api/v1/targets",
&json!({ "name": "svc", "target_type": "backend_service" }),
)
.await;
let body: serde_json::Value = resp.json().await.unwrap();
let id = body["data"]["_id"]["$oid"].as_str().unwrap().to_string();
// Attach a git repo.
let resp = server
.post(
&format!("/api/v1/targets/{id}/artifacts"),
&json!({ "kind": "git_repo", "source_ref": "https://git/svc.git" }),
)
.await;
assert_eq!(resp.status(), 200);
let body: serde_json::Value = resp.json().await.unwrap();
assert_eq!(body["data"]["artifacts"].as_array().unwrap().len(), 1);
// Delete it.
let resp = server.delete(&format!("/api/v1/targets/{id}")).await;
assert_eq!(resp.status(), 200);
let resp = server.get(&format!("/api/v1/targets/{id}")).await;
assert_eq!(resp.status(), 404);
server.cleanup().await;
}
@@ -1,110 +0,0 @@
use crate::common::TestServer;
use serde_json::json;
#[tokio::test]
async fn add_and_list_repository() {
let server = TestServer::start().await;
// Initially empty
let resp = server.get("/api/v1/repositories").await;
assert_eq!(resp.status(), 200);
let body: serde_json::Value = resp.json().await.unwrap();
assert_eq!(body["data"].as_array().unwrap().len(), 0);
// Add a repository
let resp = server
.post(
"/api/v1/repositories",
&json!({
"name": "test-repo",
"git_url": "https://github.com/example/test-repo.git",
}),
)
.await;
assert_eq!(resp.status(), 200);
let body: serde_json::Value = resp.json().await.unwrap();
let repo_id = body["data"]["id"].as_str().unwrap().to_string();
assert!(!repo_id.is_empty());
// List should now return 1
let resp = server.get("/api/v1/repositories").await;
let body: serde_json::Value = resp.json().await.unwrap();
let repos = body["data"].as_array().unwrap();
assert_eq!(repos.len(), 1);
assert_eq!(repos[0]["name"], "test-repo");
server.cleanup().await;
}
#[tokio::test]
async fn add_duplicate_repository_fails() {
let server = TestServer::start().await;
let payload = json!({
"name": "dup-repo",
"git_url": "https://github.com/example/dup-repo.git",
});
// First add succeeds
let resp = server.post("/api/v1/repositories", &payload).await;
assert_eq!(resp.status(), 200);
// Second add with same git_url should fail (unique index)
let resp = server.post("/api/v1/repositories", &payload).await;
assert_ne!(resp.status(), 200);
server.cleanup().await;
}
#[tokio::test]
async fn delete_repository() {
let server = TestServer::start().await;
// Add a repo
let resp = server
.post(
"/api/v1/repositories",
&json!({
"name": "to-delete",
"git_url": "https://github.com/example/to-delete.git",
}),
)
.await;
let body: serde_json::Value = resp.json().await.unwrap();
let repo_id = body["data"]["id"].as_str().unwrap();
// Delete it
let resp = server
.delete(&format!("/api/v1/repositories/{repo_id}"))
.await;
assert_eq!(resp.status(), 200);
// List should be empty again
let resp = server.get("/api/v1/repositories").await;
let body: serde_json::Value = resp.json().await.unwrap();
assert_eq!(body["data"].as_array().unwrap().len(), 0);
server.cleanup().await;
}
#[tokio::test]
async fn delete_nonexistent_repository_returns_404() {
let server = TestServer::start().await;
let resp = server
.delete("/api/v1/repositories/000000000000000000000000")
.await;
assert_eq!(resp.status(), 404);
server.cleanup().await;
}
#[tokio::test]
async fn delete_invalid_id_returns_400() {
let server = TestServer::start().await;
let resp = server.delete("/api/v1/repositories/not-a-valid-id").await;
assert_eq!(resp.status(), 400);
server.cleanup().await;
}
@@ -5,13 +5,14 @@ use serde_json::json;
async fn stats_overview_reflects_inserted_data() {
let server = TestServer::start().await;
// Add a repo
// Add a target
server
.post(
"/api/v1/repositories",
"/api/v1/targets",
&json!({
"name": "stats-repo",
"git_url": "https://github.com/example/stats-repo.git",
"target_type": "web_app",
"artifacts": [{ "kind": "git_repo", "source_ref": "https://github.com/example/stats-repo.git", "branch": "main" }],
}),
)
.await;
+13 -28
View File
@@ -11,7 +11,7 @@
#![allow(clippy::expect_used, clippy::unwrap_used)]
use compliance_agent::database::DatabasePool;
use compliance_core::models::TrackedRepository;
use compliance_core::models::{Artifact, OnboardedTarget, TargetType};
use compliance_core::{OrgRole, TenantContext, TenantStatus};
use mongodb::bson::doc;
@@ -28,27 +28,12 @@ fn ctx(tenant_id: &str, slug: &str) -> TenantContext {
}
}
fn fixture_repo(name: &str, git_url: &str) -> TrackedRepository {
TrackedRepository {
id: None,
name: name.to_string(),
git_url: git_url.to_string(),
default_branch: "main".to_string(),
local_path: None,
scan_schedule: None,
webhook_enabled: false,
webhook_secret: None,
tracker_type: None,
tracker_owner: None,
tracker_repo: None,
tracker_token: None,
auth_token: None,
auth_username: None,
last_scanned_commit: None,
findings_count: 0,
created_at: chrono::Utc::now(),
updated_at: chrono::Utc::now(),
}
fn fixture_repo(name: &str, git_url: &str) -> OnboardedTarget {
let mut target = OnboardedTarget::new(name.to_string(), TargetType::WebApp);
target
.artifacts
.push(Artifact::git_repo(git_url.to_string(), "main".to_string()));
target
}
#[tokio::test]
@@ -71,12 +56,12 @@ async fn pool_isolates_tenants_at_driver_level() {
// Write distinct repos into each tenant's database.
acme_db
.repositories()
.onboarded_targets()
.insert_one(fixture_repo("acme-app", "git@example.com:acme/app.git"))
.await
.expect("insert acme");
globex_db
.repositories()
.onboarded_targets()
.insert_one(fixture_repo(
"globex-platform",
"git@example.com:globex/platform.git",
@@ -173,12 +158,12 @@ async fn admin_helpers_list_and_drop_tenant_dbs() {
let acme_db = pool.for_tenant(&acme).await.expect("acme db");
let globex_db = pool.for_tenant(&globex).await.expect("globex db");
acme_db
.repositories()
.onboarded_targets()
.insert_one(fixture_repo("acme-app", "git@example.com:acme/app.git"))
.await
.expect("insert acme");
globex_db
.repositories()
.onboarded_targets()
.insert_one(fixture_repo("globex-app", "git@example.com:globex/app.git"))
.await
.expect("insert globex");
@@ -284,9 +269,9 @@ fn short_id() -> String {
}
/// Drain a `repositories` find cursor on the given tenant database.
async fn collect(db: &compliance_agent::database::Database) -> Vec<TrackedRepository> {
async fn collect(db: &compliance_agent::database::Database) -> Vec<OnboardedTarget> {
let mut cursor = db
.repositories()
.onboarded_targets()
.find(doc! {})
.await
.expect("find repositories");
+4
View File
@@ -50,3 +50,7 @@ axum = { version = "0.8", optional = true }
jsonwebtoken = { version = "9", optional = true }
reqwest = { workspace = true, optional = true }
tokio = { workspace = true, optional = true }
[dev-dependencies]
# Parse the declarative TOML job specs in the Werkbank contract tests.
toml = "0.8"
+54
View File
@@ -24,6 +24,9 @@ pub struct AgentConfig {
pub scan_schedule: String,
pub cve_monitor_schedule: String,
pub git_clone_base_path: String,
/// Base directory for content-addressed artifact blobs and per-run working
/// dirs (`<base>/blobs/<sha[0:2]>/<sha>`, `<base>/work/<target>/<artifact>/`).
pub artifact_store_base_path: String,
pub ssh_key_path: String,
pub keycloak_url: Option<String>,
pub keycloak_realm: Option<String>,
@@ -46,6 +49,57 @@ pub struct AgentConfig {
/// of tenants to iterate. When `None` or unreachable, scheduler
/// falls back to `SCHEDULER_TENANT_IDS` env (M7.2-C).
pub tenant_registry_url: Option<String>,
/// Ephemeral soft-PLC provisioning for dynamic PLC testing (#183). Off by
/// default: it needs Docker access in the agent's runtime, which is a
/// deployment opt-in.
pub plc_runtime: PlcRuntimeConfig,
}
/// Configuration for the ephemeral soft-PLC "provision-and-test" path (#183).
///
/// When a PLC/SPS target ships control logic but no reachable live device, the
/// agent can instantiate that logic itself: spin up a throwaway soft-PLC
/// (OpenPLC) container in-cluster, load the program, start the runtime, probe it
/// over industrial protocols, then tear it down. This struct carries the knobs
/// for that container's lifecycle and the OpenPLC web-UI credentials used to
/// upload the program.
#[derive(Clone, Debug)]
pub struct PlcRuntimeConfig {
/// Master switch. Provision-and-test does nothing unless this is set — it
/// shells out to `docker`, which requires the agent container to have Docker
/// access (socket mount), an explicit deployment decision.
pub enabled: bool,
/// Container image for the ephemeral soft-PLC (OpenPLC).
pub image: String,
/// Docker network the instance joins. Must be the agent's own network so it
/// is reachable in-cluster by container name and never published to the host.
pub network: String,
/// Memory cap passed to `docker run --memory` (e.g. `512m`).
pub memory: String,
/// CPU cap passed to `docker run --cpus` (e.g. `0.5`).
pub cpus: String,
/// Hard ceiling on a provisioned instance's lifetime. Teardown is guaranteed
/// no later than this even if a load/probe step hangs.
pub max_lifetime_secs: u64,
/// OpenPLC web-UI username for the program upload (image default `openplc`).
pub openplc_user: String,
/// OpenPLC web-UI password (image default `openplc`).
pub openplc_password: SecretString,
}
impl Default for PlcRuntimeConfig {
fn default() -> Self {
Self {
enabled: false,
image: "registry.meghsakha.com/openplc:latest".to_string(),
network: "certifai".to_string(),
memory: "512m".to_string(),
cpus: "0.5".to_string(),
max_lifetime_secs: 180,
openplc_user: "openplc".to_string(),
openplc_password: SecretString::from("openplc".to_string()),
}
}
}
#[derive(Clone, Debug, Serialize, Deserialize)]
+2 -1
View File
@@ -2,6 +2,7 @@ pub mod config;
pub mod db;
pub mod error;
pub mod models;
pub mod scan_matrix;
#[cfg(feature = "telemetry")]
pub mod telemetry;
pub mod tenant;
@@ -12,6 +13,6 @@ pub mod auth;
#[cfg(feature = "axum")]
pub mod tenant_ctx;
pub use config::{AgentConfig, DashboardConfig};
pub use config::{AgentConfig, DashboardConfig, PlcRuntimeConfig};
pub use error::CoreError;
pub use tenant::{OrgRole, TenantContext, TenantStatus};
+69
View File
@@ -0,0 +1,69 @@
//! Per-tenant API tokens used by `compliance-mcp` to authenticate MCP
//! HTTP requests on behalf of LLM clients (Claude Desktop, Cursor,
//! ChatGPT, etc.) that can't run a Keycloak OIDC flow.
//!
//! Tokens are opaque strings of the form `mcpt_<44 url-safe random
//! chars>`. The raw value is shown to the user exactly once at
//! creation; the database only ever sees the SHA-256 hash. Lookups go
//! through the cross-tenant `<prefix>__admin.mcp_tokens` collection
//! and return the `tenant_id` the MCP server should route to.
use chrono::{DateTime, Utc};
use serde::{Deserialize, Serialize};
/// Persisted token metadata. `token_hash` is the SHA-256 hex of the
/// raw token; the raw token itself is never stored.
#[derive(Debug, Clone, Serialize, Deserialize)]
pub struct McpToken {
#[serde(rename = "_id", skip_serializing_if = "Option::is_none")]
pub id: Option<bson::oid::ObjectId>,
/// SHA-256 hex of the raw token. Unique index in the collection.
pub token_hash: String,
/// First 8 chars of the raw token — purely for UI display so users
/// can identify which token is which without re-issuing.
pub token_prefix: String,
/// Routes to `<db_prefix>_<tenant_id>` on MCP requests.
pub tenant_id: String,
/// User-given label, e.g. "Claude Desktop" or "Sharang's laptop".
pub name: String,
/// Keycloak `sub` of the user who created this token, for audit.
pub created_by: String,
#[serde(with = "super::serde_helpers::bson_datetime")]
pub created_at: DateTime<Utc>,
#[serde(default, with = "super::serde_helpers::opt_bson_datetime")]
pub last_used_at: Option<DateTime<Utc>>,
/// Soft-delete flag. A revoked token doc stays around for audit
/// but never authenticates.
#[serde(default)]
pub revoked: bool,
}
/// Public projection of a token — never includes the hash.
/// Returned by `GET /api/v1/mcp-tokens`.
#[derive(Debug, Clone, Serialize, Deserialize)]
pub struct McpTokenView {
pub id: String,
pub name: String,
/// `mcpt_xxxx…` so the user can identify which row is which.
pub token_prefix: String,
pub created_by: String,
#[serde(with = "super::serde_helpers::bson_datetime")]
pub created_at: DateTime<Utc>,
#[serde(default, with = "super::serde_helpers::opt_bson_datetime")]
pub last_used_at: Option<DateTime<Utc>>,
pub revoked: bool,
}
impl From<&McpToken> for McpTokenView {
fn from(t: &McpToken) -> Self {
Self {
id: t.id.map(|o| o.to_hex()).unwrap_or_default(),
name: t.name.clone(),
token_prefix: t.token_prefix.clone(),
created_by: t.created_by.clone(),
created_at: t.created_at,
last_used_at: t.last_used_at,
revoked: t.revoked,
}
}
}
+14 -1
View File
@@ -7,12 +7,15 @@ pub mod finding;
pub mod graph;
pub mod issue;
pub mod mcp;
pub mod mcp_token;
pub mod notification;
pub mod onboarding;
pub mod pentest;
pub mod repository;
pub mod sbom;
pub mod scan;
pub(crate) mod serde_helpers;
pub mod werkbank;
pub use auth::AuthInfo;
pub use chat::{ChatMessage, ChatRequest, ChatResponse, SourceReference};
@@ -28,13 +31,23 @@ pub use graph::{
};
pub use issue::{IssueStatus, TrackerIssue, TrackerType};
pub use mcp::{McpServerConfig, McpServerStatus, McpTransport};
pub use mcp_token::{McpToken, McpTokenView};
pub use notification::{CveNotification, NotificationSeverity, NotificationStatus};
pub use onboarding::{
default_compliance_profile, Artifact, ArtifactAuth, ArtifactKind, Classification,
ComplianceFramework, ComplianceProfile, DetectedFact, ExternalRef, ExternalSystem,
GitArtifactConfig, IssueTrackerConfig, OnboardedTarget, PlcArtifactConfig, PlcFormat,
TargetScanConfig, TargetType, TargetTypeCandidate, WebArtifactConfig,
};
pub use pentest::{
AttackChainNode, AttackNodeStatus, AuthMode, CodeContextHint, Environment, IdentityProvider,
PentestAuthConfig, PentestConfig, PentestEvent, PentestMessage, PentestSession, PentestStats,
PentestStatus, PentestStrategy, SeverityDistribution, TestUserRecord, TesterInfo,
ToolCallRecord,
};
pub use repository::{ScanTrigger, TrackedRepository};
pub use repository::ScanTrigger;
pub use sbom::{SbomEntry, VulnRef};
pub use scan::{ScanPhase, ScanRun, ScanRunStatus, ScanType};
pub use werkbank::{
DastCollect, Executor, InputRef, Job, JobCollect, JobResult, JobRuntime, JobStatus, JobType,
};
+756
View File
@@ -0,0 +1,756 @@
//! The unified onboarding model.
//!
//! An [`OnboardedTarget`] is the single source of truth for anything the scanner
//! can analyze. It records *what kind of software* the target is ([`TargetType`]),
//! the concrete [`Artifact`]s that were provided for it (a git repo, a firmware
//! image, a live URL, a PLC project, ...), the classifier's verdict, and the scan
//! configuration. It replaces the older git-only `TrackedRepository` and the
//! standalone `DastTarget`, both of which fold into this type as artifacts.
use std::collections::HashMap;
use chrono::{DateTime, Utc};
use serde::{Deserialize, Serialize};
use super::dast::{DastAuthConfig, DastTargetType};
use super::issue::TrackerType;
use super::pentest::{Environment, PentestConfig, PentestStrategy};
use super::scan::ScanType;
/// The family of software a target belongs to.
///
/// Targets look endlessly varied but fall into a small enumerable set classified
/// by where the analyzable signal lives. This drives the scan-applicability
/// matrix and the onboarding wizard's type selection.
#[derive(Debug, Clone, Copy, PartialEq, Eq, Hash, Serialize, Deserialize)]
#[serde(rename_all = "snake_case")]
pub enum TargetType {
/// Browser-facing web application (front end + server).
WebApp,
/// Headless backend service / API (REST, GraphQL, gRPC).
BackendService,
/// Desktop application (Windows/macOS/Linux GUI or CLI binary).
DesktopApp,
/// Android application (APK / AAB).
AndroidApp,
/// iOS application (IPA).
IosApp,
/// Bare-metal embedded firmware (no operating system).
FirmwareBareMetal,
/// Embedded firmware running on an RTOS (Zephyr, FreeRTOS, ...).
FirmwareRtos,
/// Embedded Linux built with Yocto / OpenEmbedded (BSP + image).
EmbeddedLinuxYocto,
/// Programmable logic controller software (IEC 61131-3, PLCopen / SPS).
PlcSps,
}
impl std::fmt::Display for TargetType {
fn fmt(&self, f: &mut std::fmt::Formatter<'_>) -> std::fmt::Result {
match self {
Self::WebApp => write!(f, "web_app"),
Self::BackendService => write!(f, "backend_service"),
Self::DesktopApp => write!(f, "desktop_app"),
Self::AndroidApp => write!(f, "android_app"),
Self::IosApp => write!(f, "ios_app"),
Self::FirmwareBareMetal => write!(f, "firmware_bare_metal"),
Self::FirmwareRtos => write!(f, "firmware_rtos"),
Self::EmbeddedLinuxYocto => write!(f, "embedded_linux_yocto"),
Self::PlcSps => write!(f, "plc_sps"),
}
}
}
/// The kind of artifact provided for a target.
///
/// Which scans are possible is a function of the target type *and* which of
/// these are present (SAST needs code, DAST needs a running URL, and so on).
#[derive(Debug, Clone, Copy, PartialEq, Eq, Serialize, Deserialize)]
#[serde(rename_all = "snake_case")]
pub enum ArtifactKind {
/// A git repository (cloned for static analysis).
GitRepo,
/// A source archive (zip / tarball) with no live git remote.
SourceArchive,
/// A firmware image or binary blob.
FirmwareImage,
/// A mobile package: Android APK/AAB or iOS IPA.
MobilePackage,
/// An OCI/Docker container image reference.
ContainerImage,
/// A reachable running instance (base URL / endpoint) for dynamic testing.
LiveUrl,
/// A PLC project: PLCopen XML or Structured Text source.
PlcProject,
/// Free-form plaintext describing the target (feeds classification only).
PlaintextDescription,
}
impl std::fmt::Display for ArtifactKind {
fn fmt(&self, f: &mut std::fmt::Formatter<'_>) -> std::fmt::Result {
match self {
Self::GitRepo => write!(f, "git_repo"),
Self::SourceArchive => write!(f, "source_archive"),
Self::FirmwareImage => write!(f, "firmware_image"),
Self::MobilePackage => write!(f, "mobile_package"),
Self::ContainerImage => write!(f, "container_image"),
Self::LiveUrl => write!(f, "live_url"),
Self::PlcProject => write!(f, "plc_project"),
Self::PlaintextDescription => write!(f, "plaintext_description"),
}
}
}
/// Credentials attached to an artifact.
///
/// This folds both `TrackedRepository`'s git auth (`auth_token` / `auth_username`
/// / SSH key) and `DastAuthConfig`'s HTTP auth (form / bearer / cookie) into one
/// shape so a single artifact carries whatever it needs to be fetched or probed.
#[derive(Debug, Clone, Default, Serialize, Deserialize)]
pub struct ArtifactAuth {
/// Auth method: `none` | `token` | `basic` | `bearer` | `cookie` | `form` | `ssh`.
#[serde(default)]
pub method: String,
/// Username (git user, basic-auth user, or `x-access-token` for PATs).
pub username: Option<String>,
/// The secret credential: PAT, password, or bearer token. Encrypted at rest.
pub secret: Option<String>,
/// Path to an SSH private key for git-over-SSH.
pub ssh_key_path: Option<String>,
/// Login URL for form-based authentication.
pub login_url: Option<String>,
/// Extra headers to send when authenticating / probing.
pub headers: Option<HashMap<String, String>>,
}
impl From<DastAuthConfig> for ArtifactAuth {
fn from(c: DastAuthConfig) -> Self {
Self {
method: c.method,
username: c.username,
// Prefer a bearer token; otherwise fall back to the password.
secret: c.token.or(c.password),
ssh_key_path: None,
login_url: c.login_url,
headers: c.headers,
}
}
}
/// Git-specific configuration for a [`ArtifactKind::GitRepo`] artifact.
#[derive(Debug, Clone, Serialize, Deserialize)]
pub struct GitArtifactConfig {
/// Branch to scan.
pub default_branch: String,
/// Commit SHA of the last completed scan (change-detection watermark).
pub last_scanned_commit: Option<String>,
/// Local clone path once the repo has been fetched.
pub local_path: Option<String>,
}
impl GitArtifactConfig {
/// Config for a fresh git artifact on the given branch.
pub fn on_branch(branch: impl Into<String>) -> Self {
Self {
default_branch: branch.into(),
last_scanned_commit: None,
local_path: None,
}
}
}
impl Default for GitArtifactConfig {
fn default() -> Self {
Self::on_branch("main")
}
}
/// Dynamic-analysis configuration for a [`ArtifactKind::LiveUrl`] artifact.
#[derive(Debug, Clone, Serialize, Deserialize)]
pub struct WebArtifactConfig {
/// Whether the endpoint is a web app, REST API, or GraphQL API.
pub target_kind: DastTargetType,
/// URL paths to exclude from crawling / scanning.
#[serde(default)]
pub excluded_paths: Vec<String>,
/// Maximum crawl depth.
pub max_crawl_depth: u32,
/// Rate limit in requests per second.
pub rate_limit: u32,
/// Whether destructive methods (DELETE / PUT) are permitted.
#[serde(default)]
pub allow_destructive: bool,
}
impl Default for WebArtifactConfig {
fn default() -> Self {
Self {
target_kind: DastTargetType::WebApp,
excluded_paths: Vec::new(),
max_crawl_depth: 3,
rate_limit: 10,
allow_destructive: false,
}
}
}
/// The source format of a PLC project artifact.
#[derive(Debug, Clone, Copy, PartialEq, Eq, Serialize, Deserialize)]
#[serde(rename_all = "snake_case")]
pub enum PlcFormat {
/// PLCopen XML project export.
PlcopenXml,
/// IEC 61131-3 Structured Text source.
StructuredText,
/// A CODESYS project archive (`.projectarchive` — a zip bundling the project
/// plus its referenced libraries and runtime; the source of the control-app SBOM).
ProjectArchive,
}
/// PLC-specific configuration for a [`ArtifactKind::PlcProject`] artifact.
#[derive(Debug, Clone, Serialize, Deserialize)]
pub struct PlcArtifactConfig {
/// The project source format.
pub format: PlcFormat,
}
/// A single fact discovered about a target by ingest or classification
/// (e.g. `language=rust`, `build_system=cmake`, `mcu=stm32f429`).
#[derive(Debug, Clone, Serialize, Deserialize)]
pub struct DetectedFact {
/// The fact name.
pub key: String,
/// The fact value.
pub value: String,
/// What produced the fact (e.g. `tramiton`, `language-fingerprint`).
pub source: String,
}
impl DetectedFact {
/// Build a fact from its parts.
pub fn new(
key: impl Into<String>,
value: impl Into<String>,
source: impl Into<String>,
) -> Self {
Self {
key: key.into(),
value: value.into(),
source: source.into(),
}
}
}
/// One concrete thing provided for a target: code, a binary, a URL, etc.
#[derive(Debug, Clone, Serialize, Deserialize)]
pub struct Artifact {
/// Stable per-artifact id (UUID v4) — scan steps reference this.
pub id: String,
/// What kind of artifact this is.
pub kind: ArtifactKind,
/// The source reference: git URL, blob id, live URL, or image ref.
pub source_ref: String,
/// Optional human-friendly label.
pub display_name: Option<String>,
/// Content-addressed storage path once ingested (blobs only).
pub stored_path: Option<String>,
/// SHA-256 of the ingested content (git artifacts store the head SHA).
pub content_hash: Option<String>,
/// Size of the stored blob in bytes.
pub size_bytes: Option<u64>,
/// Credentials for fetching or probing this artifact.
pub auth: Option<ArtifactAuth>,
/// Git configuration (present for [`ArtifactKind::GitRepo`]).
pub git: Option<GitArtifactConfig>,
/// Dynamic-analysis configuration (present for [`ArtifactKind::LiveUrl`]).
pub web: Option<WebArtifactConfig>,
/// PLC configuration (present for [`ArtifactKind::PlcProject`]).
pub plc: Option<PlcArtifactConfig>,
/// Facts discovered about this artifact by ingest / classification.
#[serde(default)]
pub detected: Vec<DetectedFact>,
/// When this artifact was last ingested.
#[serde(default, with = "super::serde_helpers::opt_bson_datetime")]
pub ingested_at: Option<DateTime<Utc>>,
}
impl Artifact {
/// A bare artifact of the given kind and source reference.
fn bare(kind: ArtifactKind, source_ref: impl Into<String>) -> Self {
Self {
id: uuid::Uuid::new_v4().to_string(),
kind,
source_ref: source_ref.into(),
display_name: None,
stored_path: None,
content_hash: None,
size_bytes: None,
auth: None,
git: None,
web: None,
plc: None,
detected: Vec::new(),
ingested_at: None,
}
}
/// A git-repository artifact tracking the given branch.
pub fn git_repo(url: impl Into<String>, branch: impl Into<String>) -> Self {
let mut a = Self::bare(ArtifactKind::GitRepo, url);
a.git = Some(GitArtifactConfig::on_branch(branch));
a
}
/// A live-URL artifact with default crawl settings.
pub fn live_url(url: impl Into<String>) -> Self {
let mut a = Self::bare(ArtifactKind::LiveUrl, url);
a.web = Some(WebArtifactConfig::default());
a
}
/// A firmware-image artifact referenced by name (blob ingested later).
pub fn firmware_image(source_ref: impl Into<String>) -> Self {
Self::bare(ArtifactKind::FirmwareImage, source_ref)
}
/// A source-archive artifact referenced by name (blob ingested later).
pub fn source_archive(source_ref: impl Into<String>) -> Self {
Self::bare(ArtifactKind::SourceArchive, source_ref)
}
/// A mobile-package artifact (APK/AAB/IPA) referenced by name.
pub fn mobile_package(source_ref: impl Into<String>) -> Self {
Self::bare(ArtifactKind::MobilePackage, source_ref)
}
/// A container-image artifact referenced by OCI ref.
pub fn container_image(source_ref: impl Into<String>) -> Self {
Self::bare(ArtifactKind::ContainerImage, source_ref)
}
/// A PLC-project artifact in the given format.
pub fn plc_project(source_ref: impl Into<String>, format: PlcFormat) -> Self {
let mut a = Self::bare(ArtifactKind::PlcProject, source_ref);
a.plc = Some(PlcArtifactConfig { format });
a
}
/// A plaintext-description artifact (classification input only).
pub fn plaintext(text: impl Into<String>) -> Self {
Self::bare(ArtifactKind::PlaintextDescription, text)
}
}
/// One ranked candidate produced by the classifier.
#[derive(Debug, Clone, Serialize, Deserialize)]
pub struct TargetTypeCandidate {
/// The candidate target type.
pub target_type: TargetType,
/// Confidence in `[0.0, 1.0]`.
pub confidence: f32,
/// Why this candidate was proposed.
pub rationale: String,
}
/// The classifier's verdict for a target: a suggested type plus ranked
/// alternatives and the facts the decision rested on.
#[derive(Debug, Clone, Serialize, Deserialize)]
pub struct Classification {
/// The top-ranked target type.
pub suggested: TargetType,
/// All candidates, sorted by descending confidence.
#[serde(default)]
pub candidates: Vec<TargetTypeCandidate>,
/// Facts gathered during classification.
#[serde(default)]
pub facts: Vec<DetectedFact>,
/// Which classifiers contributed (e.g. `["tramiton", "language-fingerprint"]`).
#[serde(default)]
pub detected_by: Vec<String>,
/// When classification ran.
#[serde(with = "super::serde_helpers::bson_datetime")]
pub detected_at: DateTime<Utc>,
/// Whether a human confirmed the suggestion.
#[serde(default)]
pub confirmed: bool,
}
/// Issue-tracker linkage, migrated from `TrackedRepository`'s `tracker_*` fields.
#[derive(Debug, Clone, Default, Serialize, Deserialize)]
pub struct IssueTrackerConfig {
/// The tracker platform.
pub tracker_type: Option<TrackerType>,
/// Tracker owner / organization.
pub owner: Option<String>,
/// Tracker repository / project.
pub repo: Option<String>,
/// Per-target tracker access token.
pub token: Option<String>,
}
/// How a target should be scanned.
///
/// `enabled_scans` / `disabled_scans` override the scan-applicability matrix
/// defaults; the pentest and tracker blocks reuse the existing wizard config.
#[derive(Debug, Clone, Default, Serialize, Deserialize)]
pub struct TargetScanConfig {
/// Scans explicitly turned on (empty means "use matrix defaults").
#[serde(default)]
pub enabled_scans: Vec<ScanType>,
/// Scans explicitly turned off.
#[serde(default)]
pub disabled_scans: Vec<ScanType>,
/// Target environment (gates destructive / active testing).
#[serde(default)]
pub environment: Environment,
/// Whether destructive tests are permitted for this target.
#[serde(default)]
pub allow_destructive: bool,
/// Pentest strategy selector.
pub strategy: Option<PentestStrategy>,
/// Full pentest wizard configuration.
pub pentest: Option<PentestConfig>,
/// Issue-tracker linkage.
pub issue_tracker: Option<IssueTrackerConfig>,
}
/// A sibling product in the company suite that may already hold authoritative
/// data for a target. compliance-scanner reconciles with these rather than
/// recomputing what they already know.
#[derive(Debug, Clone, Copy, PartialEq, Eq, Serialize, Deserialize)]
#[serde(rename_all = "snake_case")]
pub enum ExternalSystem {
/// Reproducible-build & firmware compliance engine (build plan, SBOM, VEX,
/// attestation).
Tramiton,
/// Code assistant (downstream remediation consumer).
Werkpilot,
/// Compliance-controls RAG (atomic controls derived from laws).
BreakpilotCompliance,
}
impl std::fmt::Display for ExternalSystem {
fn fmt(&self, f: &mut std::fmt::Formatter<'_>) -> std::fmt::Result {
match self {
Self::Tramiton => write!(f, "tramiton"),
Self::Werkpilot => write!(f, "werkpilot"),
Self::BreakpilotCompliance => write!(f, "breakpilot_compliance"),
}
}
}
/// A link from this target to a record in a sibling product, used to reconcile
/// existing evidence instead of recomputing it.
///
/// For tramiton, `project_id` is the shared cross-product key and
/// `subject_sha256` matches a firmware artifact's [`Artifact::content_hash`]
/// (which equals tramiton's `Artifact.sha256`).
#[derive(Debug, Clone, Serialize, Deserialize)]
pub struct ExternalRef {
/// Which sibling product this reference points at.
pub system: ExternalSystem,
/// The sibling product's project identifier, if known.
pub project_id: Option<String>,
/// Content digest of the subject artifact (firmware sha256), if known.
pub subject_sha256: Option<String>,
/// Reconciliation status: `linked` | `reconciled` | `unavailable`.
#[serde(default)]
pub status: String,
/// Opaque, offline-verifiable entitlement grant (e.g. tramiton's signed
/// `LicenseGrant`), if the tenant provided one.
pub license_grant: Option<String>,
/// When evidence was last reconciled from this system.
#[serde(default, with = "super::serde_helpers::opt_bson_datetime")]
pub last_reconciled_at: Option<DateTime<Utc>>,
}
impl ExternalRef {
/// A freshly linked (not yet reconciled) reference to a sibling system.
pub fn linked(system: ExternalSystem) -> Self {
Self {
system,
project_id: None,
subject_sha256: None,
status: "linked".to_string(),
license_grant: None,
last_reconciled_at: None,
}
}
}
/// A regulatory / standards framework a target must comply with. Drives which
/// controls the mapping engine pulls from the [`crate::traits::ControlsProvider`].
#[derive(Debug, Clone, Copy, PartialEq, Eq, Serialize, Deserialize)]
#[serde(rename_all = "snake_case")]
pub enum ComplianceFramework {
/// EU Cyber Resilience Act.
Cra,
/// IEC 62443 (industrial automation & control systems security).
Iec62443,
/// EU General Data Protection Regulation.
Gdpr,
/// SOC 2.
Soc2,
/// ISO/IEC 27001.
Iso27001,
/// EU Radio Equipment Directive (RED) cybersecurity articles.
RedDirective,
}
impl std::fmt::Display for ComplianceFramework {
fn fmt(&self, f: &mut std::fmt::Formatter<'_>) -> std::fmt::Result {
match self {
Self::Cra => write!(f, "cra"),
Self::Iec62443 => write!(f, "iec_62443"),
Self::Gdpr => write!(f, "gdpr"),
Self::Soc2 => write!(f, "soc2"),
Self::Iso27001 => write!(f, "iso_27001"),
Self::RedDirective => write!(f, "red_directive"),
}
}
}
/// The compliance scope of a target: which frameworks apply and, optionally, the
/// jurisdiction. Captured at onboarding (with per-target-type defaults from
/// [`default_compliance_profile`]).
#[derive(Debug, Clone, Default, Serialize, Deserialize)]
pub struct ComplianceProfile {
/// Applicable frameworks.
#[serde(default)]
pub frameworks: Vec<ComplianceFramework>,
/// Free-form jurisdiction (e.g. `eu`, `us`, `de`).
pub jurisdiction: Option<String>,
}
/// The sensible default compliance scope for a target type. Firmware / PLC /
/// embedded default to CRA + IEC 62443; software defaults to GDPR + SOC 2.
pub fn default_compliance_profile(target_type: TargetType) -> ComplianceProfile {
use ComplianceFramework::{Cra, Gdpr, Iec62443, Soc2};
let frameworks = match target_type {
TargetType::PlcSps
| TargetType::FirmwareBareMetal
| TargetType::FirmwareRtos
| TargetType::EmbeddedLinuxYocto => vec![Cra, Iec62443],
TargetType::WebApp | TargetType::BackendService => vec![Gdpr, Soc2],
TargetType::DesktopApp | TargetType::AndroidApp | TargetType::IosApp => {
vec![Gdpr, Cra]
}
};
ComplianceProfile {
frameworks,
jurisdiction: None,
}
}
/// A target onboarded for scanning: the unified replacement for the legacy
/// `TrackedRepository` (SAST) and `DastTarget` (DAST) records.
#[derive(Debug, Clone, Serialize, Deserialize)]
pub struct OnboardedTarget {
/// Mongo id. Preserved from the legacy record during migration so every
/// downstream collection keyed by `repo_id` / `target_id` keeps resolving.
#[serde(rename = "_id", skip_serializing_if = "Option::is_none")]
pub id: Option<bson::oid::ObjectId>,
/// Human-friendly name.
#[serde(default)]
pub name: String,
/// The software family this target belongs to.
pub target_type: TargetType,
/// Optional free-form description (also a classification input).
pub description: Option<String>,
/// The artifacts provided for this target.
#[serde(default)]
pub artifacts: Vec<Artifact>,
/// The classifier's verdict, once run.
pub classification: Option<Classification>,
/// How this target should be scanned.
#[serde(default)]
pub scan_config: TargetScanConfig,
/// The compliance scope (applicable frameworks / jurisdiction).
#[serde(default)]
pub compliance_profile: ComplianceProfile,
/// Links to sibling products (tramiton, ...) holding reconcilable evidence.
#[serde(default)]
pub external_refs: Vec<ExternalRef>,
/// Cron schedule for recurring scans, if any.
pub scan_schedule: Option<String>,
/// Whether inbound webhooks are enabled for this target.
#[serde(default)]
pub webhook_enabled: bool,
/// HMAC secret for verifying inbound webhooks.
#[serde(default, skip_serializing_if = "Option::is_none")]
pub webhook_secret: Option<String>,
/// Cached count of findings across this target's scans.
#[serde(default)]
pub findings_count: u32,
/// Creation timestamp.
#[serde(
default = "chrono::Utc::now",
with = "super::serde_helpers::bson_datetime"
)]
pub created_at: DateTime<Utc>,
/// Last-update timestamp.
#[serde(
default = "chrono::Utc::now",
with = "super::serde_helpers::bson_datetime"
)]
pub updated_at: DateTime<Utc>,
}
impl OnboardedTarget {
/// A new target of the given type with a freshly generated webhook secret.
pub fn new(name: String, target_type: TargetType) -> Self {
let now = Utc::now();
let webhook_secret = uuid::Uuid::new_v4().to_string().replace('-', "");
Self {
id: None,
name,
target_type,
description: None,
artifacts: Vec::new(),
classification: None,
scan_config: TargetScanConfig::default(),
compliance_profile: default_compliance_profile(target_type),
external_refs: Vec::new(),
scan_schedule: None,
webhook_enabled: false,
webhook_secret: Some(webhook_secret),
findings_count: 0,
created_at: now,
updated_at: now,
}
}
/// The first artifact of the given kind, if present.
pub fn first_of(&self, kind: ArtifactKind) -> Option<&Artifact> {
self.artifacts.iter().find(|a| a.kind == kind)
}
/// Whether the target has at least one artifact of the given kind.
pub fn has(&self, kind: ArtifactKind) -> bool {
self.artifacts.iter().any(|a| a.kind == kind)
}
/// The primary code artifact (git repo or source archive), if any.
pub fn code_artifact(&self) -> Option<&Artifact> {
self.artifacts
.iter()
.find(|a| matches!(a.kind, ArtifactKind::GitRepo | ArtifactKind::SourceArchive))
}
/// The live-URL artifact, if any.
pub fn live_url(&self) -> Option<&Artifact> {
self.first_of(ArtifactKind::LiveUrl)
}
}
#[cfg(test)]
#[allow(clippy::expect_used, clippy::unwrap_used)]
mod tests {
use super::*;
fn sample_target() -> OnboardedTarget {
let mut t = OnboardedTarget::new("acme-web".to_string(), TargetType::WebApp);
t.artifacts.push(Artifact::git_repo(
"https://git.example.com/acme.git",
"main",
));
t.artifacts
.push(Artifact::live_url("https://acme.example.com"));
t
}
#[test]
fn onboarded_target_bson_round_trip() {
let t = sample_target();
let b = bson::to_bson(&t).expect("serialize");
let back: OnboardedTarget = bson::from_bson(b.clone()).expect("deserialize");
let b2 = bson::to_bson(&back).expect("re-serialize");
assert_eq!(b, b2);
}
#[test]
fn enum_display_is_snake_case() {
assert_eq!(
TargetType::FirmwareBareMetal.to_string(),
"firmware_bare_metal"
);
assert_eq!(TargetType::PlcSps.to_string(), "plc_sps");
assert_eq!(ArtifactKind::PlcProject.to_string(), "plc_project");
assert_eq!(ArtifactKind::MobilePackage.to_string(), "mobile_package");
}
#[test]
fn helpers_locate_artifacts() {
let t = sample_target();
assert!(t.has(ArtifactKind::GitRepo));
assert!(t.live_url().is_some());
assert!(t.code_artifact().is_some());
assert!(!t.has(ArtifactKind::FirmwareImage));
assert_eq!(
t.first_of(ArtifactKind::GitRepo).map(|a| a.kind),
Some(ArtifactKind::GitRepo)
);
}
#[test]
fn new_target_generates_webhook_secret() {
let t = OnboardedTarget::new("t".to_string(), TargetType::BackendService);
let secret = t.webhook_secret.expect("secret present");
assert_eq!(secret.len(), 32);
assert!(!secret.contains('-'));
}
#[test]
fn dast_auth_folds_into_artifact_auth() {
let dast = DastAuthConfig {
method: "bearer".to_string(),
login_url: Some("https://x/login".to_string()),
username: Some("user".to_string()),
password: Some("pw".to_string()),
token: Some("tok".to_string()),
headers: None,
};
let auth = ArtifactAuth::from(dast);
assert_eq!(auth.method, "bearer");
// Bearer token wins over password.
assert_eq!(auth.secret.as_deref(), Some("tok"));
assert_eq!(auth.login_url.as_deref(), Some("https://x/login"));
}
#[test]
fn each_artifact_gets_a_unique_id() {
let a = Artifact::firmware_image("fw.bin");
let b = Artifact::firmware_image("fw.bin");
assert_ne!(a.id, b.id);
}
#[test]
fn firmware_default_profile_is_cra_and_62443() {
let p = default_compliance_profile(TargetType::FirmwareBareMetal);
assert!(p.frameworks.contains(&ComplianceFramework::Cra));
assert!(p.frameworks.contains(&ComplianceFramework::Iec62443));
}
#[test]
fn webapp_default_profile_is_gdpr_and_soc2() {
let p = default_compliance_profile(TargetType::WebApp);
assert!(p.frameworks.contains(&ComplianceFramework::Gdpr));
assert!(p.frameworks.contains(&ComplianceFramework::Soc2));
}
#[test]
fn new_target_gets_default_profile_and_no_external_refs() {
let t = OnboardedTarget::new("fw".to_string(), TargetType::FirmwareRtos);
assert!(!t.compliance_profile.frameworks.is_empty());
assert!(t.external_refs.is_empty());
}
#[test]
fn external_ref_linked_defaults() {
let r = ExternalRef::linked(ExternalSystem::Tramiton);
assert_eq!(r.system, ExternalSystem::Tramiton);
assert_eq!(r.status, "linked");
assert!(r.project_id.is_none());
assert!(r.last_reconciled_at.is_none());
}
}
+2 -93
View File
@@ -1,8 +1,6 @@
use chrono::{DateTime, Utc};
use serde::{Deserialize, Deserializer, Serialize};
use super::issue::TrackerType;
use serde::{Deserialize, Serialize};
/// What initiated a scan.
#[derive(Debug, Clone, Serialize, Deserialize, PartialEq, Eq)]
#[serde(rename_all = "snake_case")]
pub enum ScanTrigger {
@@ -10,92 +8,3 @@ pub enum ScanTrigger {
Webhook,
Manual,
}
#[derive(Debug, Clone, Serialize, Deserialize)]
pub struct TrackedRepository {
#[serde(rename = "_id", skip_serializing_if = "Option::is_none")]
pub id: Option<bson::oid::ObjectId>,
#[serde(default)]
pub name: String,
#[serde(default)]
pub git_url: String,
#[serde(default = "default_branch")]
pub default_branch: String,
pub local_path: Option<String>,
pub scan_schedule: Option<String>,
#[serde(default)]
pub webhook_enabled: bool,
/// Auto-generated HMAC secret for verifying incoming webhooks
#[serde(default, skip_serializing_if = "Option::is_none")]
pub webhook_secret: Option<String>,
pub tracker_type: Option<TrackerType>,
pub tracker_owner: Option<String>,
pub tracker_repo: Option<String>,
/// Optional per-repo PAT for the issue tracker (GitHub/GitLab/Jira)
#[serde(default, skip_serializing_if = "Option::is_none")]
pub tracker_token: Option<String>,
/// Optional auth token for HTTPS private repos (PAT or password)
#[serde(default, skip_serializing_if = "Option::is_none")]
pub auth_token: Option<String>,
/// Optional username for HTTPS auth (defaults to "x-access-token" for PATs)
#[serde(default, skip_serializing_if = "Option::is_none")]
pub auth_username: Option<String>,
pub last_scanned_commit: Option<String>,
#[serde(default, deserialize_with = "deserialize_findings_count")]
pub findings_count: u32,
#[serde(
default = "chrono::Utc::now",
with = "super::serde_helpers::bson_datetime"
)]
pub created_at: DateTime<Utc>,
#[serde(
default = "chrono::Utc::now",
with = "super::serde_helpers::bson_datetime"
)]
pub updated_at: DateTime<Utc>,
}
fn default_branch() -> String {
"main".to_string()
}
fn deserialize_findings_count<'de, D>(deserializer: D) -> Result<u32, D::Error>
where
D: Deserializer<'de>,
{
let bson = bson::Bson::deserialize(deserializer)?;
match &bson {
bson::Bson::Int32(n) => Ok(*n as u32),
bson::Bson::Int64(n) => Ok(*n as u32),
bson::Bson::Double(n) => Ok(*n as u32),
_ => Ok(0),
}
}
impl TrackedRepository {
pub fn new(name: String, git_url: String) -> Self {
let now = Utc::now();
// Generate a random webhook secret (hex-encoded UUID v4, no dashes)
let webhook_secret = uuid::Uuid::new_v4().to_string().replace('-', "");
Self {
id: None,
name,
git_url,
default_branch: "main".to_string(),
local_path: None,
scan_schedule: None,
auth_token: None,
auth_username: None,
webhook_enabled: false,
webhook_secret: Some(webhook_secret),
tracker_type: None,
tracker_owner: None,
tracker_repo: None,
tracker_token: None,
last_scanned_commit: None,
findings_count: 0,
created_at: now,
updated_at: now,
}
}
}
+24 -1
View File
@@ -3,7 +3,7 @@ use serde::{Deserialize, Serialize};
use super::repository::ScanTrigger;
#[derive(Debug, Clone, Serialize, Deserialize, PartialEq, Eq)]
#[derive(Debug, Clone, Copy, Serialize, Deserialize, PartialEq, Eq)]
#[serde(rename_all = "lowercase")]
pub enum ScanType {
Sast,
@@ -16,6 +16,17 @@ pub enum ScanType {
SecretDetection,
Lint,
CodeReview,
/// Static analysis of a firmware image (unpack + component CVE).
FirmwareStatic,
/// Control-logic security analysis of PLC / SPS programs.
PlcControlLogic,
/// Static analysis of a mobile package (APK / AAB / IPA).
MobileStatic,
/// Static analysis of a container image.
ContainerScan,
/// Dynamic probing of a running PLC/SPS device over industrial protocols
/// (Modbus/TCP, OPC UA, …) for exposed/unauthenticated control access.
IcsProbe,
}
impl std::fmt::Display for ScanType {
@@ -31,6 +42,11 @@ impl std::fmt::Display for ScanType {
Self::SecretDetection => write!(f, "secret_detection"),
Self::Lint => write!(f, "lint"),
Self::CodeReview => write!(f, "code_review"),
Self::FirmwareStatic => write!(f, "firmware_static"),
Self::PlcControlLogic => write!(f, "plc_control_logic"),
Self::MobileStatic => write!(f, "mobile_static"),
Self::ContainerScan => write!(f, "container_scan"),
Self::IcsProbe => write!(f, "ics_probe"),
}
}
}
@@ -47,6 +63,8 @@ pub enum ScanRunStatus {
#[serde(rename_all = "snake_case")]
pub enum ScanPhase {
ChangeDetection,
ArtifactIngest,
Classification,
Sast,
SbomGeneration,
CveScanning,
@@ -55,9 +73,14 @@ pub enum ScanPhase {
LintScanning,
CodeReview,
GraphBuilding,
FirmwareStatic,
PlcAnalysis,
MobileStatic,
ContainerScan,
LlmTriage,
IssueCreation,
DastScanning,
IcsProbe,
Completed,
}
+378
View File
@@ -0,0 +1,378 @@
//! The Werkbank job/result contract (WB-01).
//!
//! The shared, dependency-free vocabulary the control plane and the Werkbank
//! execution runner agree on: what a [`Job`] is, which [`Executor`] runs it, how
//! it moves through the queue ([`JobStatus`]), and what a [`JobResult`] carries
//! back. Jobs are declarative — TOML on disk, JSON on the wire — and results
//! reuse the existing scanner result types ([`Finding`], [`DastFinding`],
//! [`SbomEntry`]) so the runner produces exactly what the control plane persists.
//!
//! This module is intentionally free of the `mongodb`/`axum` features so the
//! runner can depend on `compliance-core` without pulling the server stack.
use std::collections::BTreeMap;
use chrono::{DateTime, Utc};
use serde::{Deserialize, Serialize};
use super::dast::DastFinding;
use super::finding::Finding;
use super::sbom::SbomEntry;
/// The kind of dynamic-execution job.
#[derive(Debug, Clone, Copy, PartialEq, Eq, Serialize, Deserialize)]
#[serde(rename_all = "kebab-case")]
pub enum JobType {
/// Instantiate control logic on an ephemeral soft-PLC and probe it.
PlcProvision,
/// Boot a firmware image under QEMU and run dynamic checks.
QemuBoot,
/// Crawl and dynamically test a running web endpoint.
Dast,
/// Run an active penetration test against a running target.
Pentest,
}
/// How a runner executes a job — the CI-runner-style classification. A runner
/// advertises exactly one; a job requires one.
#[derive(Debug, Clone, Copy, PartialEq, Eq, Serialize, Deserialize)]
#[serde(rename_all = "lowercase")]
pub enum Executor {
/// A subprocess on the runner host (dev / trusted single-node).
Shell,
/// One or more containers on the runner's Docker (default; QEMU runs here).
Docker,
/// A Pod/Job in a Kubernetes cluster (scale-out / multi-tenant).
K8s,
}
/// Lifecycle state of a job in the queue.
#[derive(Debug, Clone, Copy, PartialEq, Eq, Serialize, Deserialize)]
#[serde(rename_all = "lowercase")]
pub enum JobStatus {
/// Waiting to be leased.
Queued,
/// Leased by a runner but not yet started.
Leased,
/// Executing on a runner.
Running,
/// Completed successfully.
Succeeded,
/// Completed with an error.
Failed,
/// The lease/lifetime deadline elapsed before completion.
Expired,
/// Cancelled by the control plane.
Cancelled,
}
impl JobStatus {
/// Whether the job has reached a terminal state (no further transitions).
pub fn is_terminal(self) -> bool {
matches!(
self,
JobStatus::Succeeded | JobStatus::Failed | JobStatus::Expired | JobStatus::Cancelled
)
}
}
/// A reference to an input artifact. Resolved by the runner from a source it can
/// reach; the blob itself never flows through the control plane (so an on-prem
/// runner keeps customer data local). Exactly one of `blob`/`url` should be set.
#[derive(Debug, Clone, Default, PartialEq, Eq, Serialize, Deserialize)]
pub struct InputRef {
/// Content-addressed blob (e.g. `sha256:…`) the runner fetches from its store.
#[serde(default, skip_serializing_if = "Option::is_none")]
pub blob: Option<String>,
/// A URL the runner can reach (git repo, internal artifact store, …).
#[serde(default, skip_serializing_if = "Option::is_none")]
pub url: Option<String>,
}
impl InputRef {
/// A content-addressed blob reference.
pub fn blob(id: impl Into<String>) -> Self {
Self {
blob: Some(id.into()),
url: None,
}
}
}
/// Sandbox runtime knobs. Fields are executor/job-type specific and all optional;
/// `extra` carries anything not modelled explicitly.
#[derive(Debug, Clone, Default, PartialEq, Eq, Serialize, Deserialize)]
pub struct JobRuntime {
/// Container image (Docker executor).
#[serde(default, skip_serializing_if = "Option::is_none")]
pub image: Option<String>,
/// Memory cap (e.g. `512m`).
#[serde(default, skip_serializing_if = "Option::is_none")]
pub memory: Option<String>,
/// CPU cap (e.g. `0.5`).
#[serde(default, skip_serializing_if = "Option::is_none")]
pub cpus: Option<String>,
/// Network to join (e.g. `isolated`).
#[serde(default, skip_serializing_if = "Option::is_none")]
pub network: Option<String>,
/// QEMU machine type (qemu-boot).
#[serde(default, skip_serializing_if = "Option::is_none")]
pub machine: Option<String>,
/// QEMU target architecture (qemu-boot).
#[serde(default, skip_serializing_if = "Option::is_none")]
pub arch: Option<String>,
/// Executor-specific extras not modelled above.
#[serde(default, skip_serializing_if = "BTreeMap::is_empty")]
pub extra: BTreeMap<String, String>,
}
/// DAST collection settings for jobs that scan a web endpoint.
#[derive(Debug, Clone, PartialEq, Eq, Serialize, Deserialize)]
pub struct DastCollect {
/// Maximum crawl depth (kept shallow for ephemeral instances).
pub max_crawl_depth: u32,
}
/// What to collect from a run.
#[derive(Debug, Clone, Default, PartialEq, Eq, Serialize, Deserialize)]
pub struct JobCollect {
/// Run the industrial-protocol probe (Modbus/OPC-UA/EtherNet-IP).
#[serde(default)]
pub ics_probe: bool,
/// Run DAST against the provisioned/booted web endpoint.
#[serde(default, skip_serializing_if = "Option::is_none")]
pub dast: Option<DastCollect>,
/// Run an active pentest.
#[serde(default)]
pub pentest: bool,
/// Collect an SBOM.
#[serde(default)]
pub sbom: bool,
}
/// A declarative dynamic-execution job the control plane enqueues and a Werkbank
/// runner leases and executes.
#[derive(Debug, Clone, PartialEq, Eq, Serialize, Deserialize)]
pub struct Job {
/// Unique job id (assigned by the control plane on enqueue).
pub id: String,
/// What kind of job this is.
#[serde(rename = "type")]
pub job_type: JobType,
/// Owning tenant.
pub tenant: String,
/// The onboarded target this job tests.
pub target_id: String,
/// The executor a runner must provide to run this job.
pub executor: Executor,
/// Runner capabilities this job requires (e.g. `arch=amd64`, `kvm=true`).
#[serde(default, skip_serializing_if = "Vec::is_empty")]
pub labels: Vec<String>,
/// Hard lifetime deadline for the whole job.
pub timeout_secs: u64,
/// Named input artifacts (e.g. `program`, `firmware`), by reference.
#[serde(default, skip_serializing_if = "BTreeMap::is_empty")]
pub inputs: BTreeMap<String, InputRef>,
/// Sandbox runtime knobs.
#[serde(default)]
pub runtime: JobRuntime,
/// What to collect from the run.
#[serde(default)]
pub collect: JobCollect,
}
impl Job {
/// A `plc-provision` job: instantiate the control logic named `program` on an
/// ephemeral soft-PLC (Docker executor) and collect the ICS probe + DAST.
pub fn plc_provision(
id: impl Into<String>,
tenant: impl Into<String>,
target_id: impl Into<String>,
program: InputRef,
timeout_secs: u64,
) -> Self {
let mut inputs = BTreeMap::new();
inputs.insert("program".to_string(), program);
Self {
id: id.into(),
job_type: JobType::PlcProvision,
tenant: tenant.into(),
target_id: target_id.into(),
executor: Executor::Docker,
labels: Vec::new(),
timeout_secs,
inputs,
runtime: JobRuntime::default(),
collect: JobCollect {
ics_probe: true,
dast: Some(DastCollect { max_crawl_depth: 2 }),
pentest: false,
sbom: false,
},
}
}
}
/// The outcome of running a job, posted back to the control plane. Findings and
/// SBOM reuse the shared scanner types, so the control plane persists them
/// unchanged. Submission is idempotent — keyed by [`JobResult::job_id`].
#[derive(Debug, Clone, Default, Serialize, Deserialize)]
pub struct JobResult {
/// The job this result is for.
pub job_id: String,
/// Terminal status of the job.
pub status: Option<JobStatus>,
/// General scanner findings (e.g. ICS-probe findings).
#[serde(default, skip_serializing_if = "Vec::is_empty")]
pub findings: Vec<Finding>,
/// DAST findings from a web-endpoint scan.
#[serde(default, skip_serializing_if = "Vec::is_empty")]
pub dast_findings: Vec<DastFinding>,
/// SBOM components collected from the run.
#[serde(default, skip_serializing_if = "Vec::is_empty")]
pub sbom: Vec<SbomEntry>,
/// Error message when the job failed.
#[serde(default, skip_serializing_if = "Option::is_none")]
pub error: Option<String>,
/// Captured execution log (truncated by the runner).
#[serde(default, skip_serializing_if = "Option::is_none")]
pub logs: Option<String>,
/// When execution started on the runner.
#[serde(default, skip_serializing_if = "Option::is_none")]
pub started_at: Option<DateTime<Utc>>,
/// When execution finished.
#[serde(default, skip_serializing_if = "Option::is_none")]
pub finished_at: Option<DateTime<Utc>>,
}
impl JobResult {
/// A successful result for a job.
pub fn succeeded(job_id: impl Into<String>) -> Self {
Self {
job_id: job_id.into(),
status: Some(JobStatus::Succeeded),
..Default::default()
}
}
/// A failed result carrying an error message.
pub fn failed(job_id: impl Into<String>, error: impl Into<String>) -> Self {
Self {
job_id: job_id.into(),
status: Some(JobStatus::Failed),
error: Some(error.into()),
..Default::default()
}
}
}
#[cfg(test)]
#[allow(clippy::expect_used, clippy::unwrap_used)]
mod tests {
use super::*;
#[test]
fn job_round_trips_through_json() {
let job = Job::plc_provision("job_1", "acme", "64f0aa", InputRef::blob("sha256:abc"), 180);
let json = serde_json::to_string(&job).expect("serialize");
let back: Job = serde_json::from_str(&json).expect("deserialize");
assert_eq!(job, back);
// Enum wire forms are the kebab/lowercase the contract documents.
assert!(json.contains("\"type\":\"plc-provision\""));
assert!(json.contains("\"executor\":\"docker\""));
}
#[test]
fn parses_the_design_doc_plc_provision_toml() {
// The exact shape from docs/DESIGN.md §5 (wrapped in a [job] table).
#[derive(Deserialize)]
struct JobFile {
job: Job,
}
let src = r#"
[job]
id = "job_01H"
type = "plc-provision"
tenant = "acme"
target_id = "64f0"
executor = "docker"
labels = ["arch=amd64"]
timeout_secs = 180
[job.inputs]
program = { blob = "sha256:deadbeef" }
[job.runtime]
image = "openplc:latest"
memory = "512m"
cpus = "0.5"
network = "isolated"
[job.collect]
ics_probe = true
dast = { max_crawl_depth = 2 }
"#;
let file: JobFile = toml::from_str(src).expect("parse job toml");
let job = file.job;
assert_eq!(job.job_type, JobType::PlcProvision);
assert_eq!(job.executor, Executor::Docker);
assert_eq!(job.labels, vec!["arch=amd64".to_string()]);
assert_eq!(
job.inputs.get("program").and_then(|i| i.blob.as_deref()),
Some("sha256:deadbeef")
);
assert_eq!(job.runtime.image.as_deref(), Some("openplc:latest"));
assert!(job.collect.ics_probe);
assert_eq!(job.collect.dast.map(|d| d.max_crawl_depth), Some(2));
}
#[test]
fn qemu_boot_runtime_fields_parse() {
#[derive(Deserialize)]
struct JobFile {
job: Job,
}
let src = r#"
[job]
id = "j2"
type = "qemu-boot"
tenant = "acme"
target_id = "t"
executor = "docker"
labels = ["kvm=true"]
timeout_secs = 600
[job.inputs]
firmware = { blob = "sha256:cafe" }
[job.runtime]
machine = "virt"
arch = "arm"
memory = "1g"
"#;
let file: JobFile = toml::from_str(src).expect("parse");
assert_eq!(file.job.job_type, JobType::QemuBoot);
assert_eq!(file.job.runtime.arch.as_deref(), Some("arm"));
assert_eq!(
file.job
.inputs
.get("firmware")
.and_then(|i| i.blob.as_deref()),
Some("sha256:cafe")
);
}
#[test]
fn status_terminality() {
assert!(JobStatus::Succeeded.is_terminal());
assert!(JobStatus::Expired.is_terminal());
assert!(!JobStatus::Queued.is_terminal());
assert!(!JobStatus::Running.is_terminal());
}
#[test]
fn result_constructors() {
assert_eq!(JobResult::succeeded("j").status, Some(JobStatus::Succeeded));
let f = JobResult::failed("j", "boom");
assert_eq!(f.status, Some(JobStatus::Failed));
assert_eq!(f.error.as_deref(), Some("boom"));
}
}
+556
View File
@@ -0,0 +1,556 @@
//! The scan-applicability matrix.
//!
//! Which scans are possible for a target is a function of its [`TargetType`] and
//! which [`ArtifactKind`]s are actually present: SAST needs code, DAST needs a
//! running URL, firmware-static analysis needs a firmware image, and so on. This
//! module encodes that as a table — one rule set per target type — and resolves
//! it against a concrete [`OnboardedTarget`] into a list of [`ScanOption`]s the
//! onboarding wizard and the scan pipeline both consume.
use crate::models::{ArtifactKind, OnboardedTarget, ScanType, TargetType};
/// What an artifact a scan needs in order to run.
#[derive(Debug, Clone, Copy, PartialEq, Eq)]
pub enum ArtifactRequirement {
/// Source code — a git repo or a source archive.
Code,
/// A reachable running instance (any live URL / endpoint, scheme-agnostic —
/// e.g. the ICS probe works off the host:port of a modbus:// or http:// ref).
RunningUrl,
/// A reachable **web** endpoint — a live URL with an http(s) scheme. DAST is
/// an HTTP crawler, so a modbus:// / opc.tcp:// endpoint does not satisfy it.
HttpUrl,
/// A firmware image / binary blob.
Firmware,
/// A PLC project (PLCopen XML or Structured Text).
Plc,
/// A mobile package (APK / AAB / IPA).
Mobile,
/// A container image.
Container,
/// No specific artifact required.
Any,
}
/// A static rule: this scan applies to a target type, needs this artifact, and
/// defaults on/off. The rationale explains the entry to the user.
#[derive(Debug, Clone, Copy)]
pub struct ScanRule {
/// The scan this rule governs.
pub scan: ScanType,
/// Whether the scan is on by default (only when its artifact is present).
pub default_on: bool,
/// Human-readable explanation of what the scan does here.
pub rationale: &'static str,
/// The artifact the scan consumes.
pub requires: ArtifactRequirement,
}
impl ScanRule {
const fn new(
scan: ScanType,
default_on: bool,
rationale: &'static str,
requires: ArtifactRequirement,
) -> Self {
Self {
scan,
default_on,
rationale,
requires,
}
}
}
/// A resolved scan choice for a specific target: a rule intersected with the
/// artifacts actually present. `blocked_reason` is `Some` when the required
/// artifact is missing.
#[derive(Debug, Clone)]
pub struct ScanOption {
/// The scan.
pub scan: ScanType,
/// Whether to pre-select the scan (false when blocked).
pub default_on: bool,
/// Why the scan is offered.
pub rationale: String,
/// The artifact kind the scan needs, if any specific one.
pub required_artifact: Option<ArtifactKind>,
/// Set when the required artifact is absent, explaining the block.
pub blocked_reason: Option<String>,
}
/// The SAST umbrella: every static-analysis sub-scan that runs over source code.
fn sast_umbrella() -> Vec<ScanRule> {
use ArtifactRequirement::Code;
vec![
ScanRule::new(
ScanType::Sast,
true,
"Static analysis (Semgrep) over source",
Code,
),
ScanRule::new(
ScanType::Sbom,
true,
"Software bill of materials from source",
Code,
),
ScanRule::new(
ScanType::Cve,
true,
"Match dependencies against known CVEs",
Code,
),
ScanRule::new(
ScanType::SecretDetection,
true,
"Scan source for committed secrets",
Code,
),
ScanRule::new(ScanType::Lint, true, "Language linters over source", Code),
ScanRule::new(
ScanType::Gdpr,
true,
"GDPR data-handling pattern checks",
Code,
),
ScanRule::new(
ScanType::OAuth,
true,
"OAuth misconfiguration patterns",
Code,
),
ScanRule::new(
ScanType::Graph,
true,
"Build the code graph for impact analysis",
Code,
),
ScanRule::new(
ScanType::CodeReview,
false,
"LLM code review over changed source",
Code,
),
]
}
/// The rule set for a target type. Scans that are never applicable to a type are
/// simply absent (e.g. DAST is not listed for a PLC target).
pub fn rules_for(target_type: TargetType) -> Vec<ScanRule> {
use ArtifactRequirement::{Firmware, HttpUrl, Mobile, Plc, RunningUrl};
match target_type {
TargetType::WebApp | TargetType::BackendService => {
let mut r = sast_umbrella();
r.push(ScanRule::new(
ScanType::Dast,
true,
"Dynamic scan of the running endpoint",
HttpUrl,
));
r
}
TargetType::DesktopApp => sast_umbrella(),
TargetType::AndroidApp | TargetType::IosApp => {
let mut r = sast_umbrella();
r.push(ScanRule::new(
ScanType::MobileStatic,
true,
"Static analysis of the mobile package (manifest, permissions, libs)",
Mobile,
));
r
}
TargetType::FirmwareBareMetal | TargetType::FirmwareRtos => {
let mut r = sast_umbrella();
r.push(ScanRule::new(
ScanType::FirmwareStatic,
true,
"Unpack and statically analyze the firmware image",
Firmware,
));
r.push(ScanRule::new(
ScanType::Sbom,
true,
"SBOM from the firmware image (binwalk / tramiton)",
Firmware,
));
r.push(ScanRule::new(
ScanType::Cve,
true,
"Match firmware components against known CVEs",
Firmware,
));
r
}
TargetType::EmbeddedLinuxYocto => {
let mut r = sast_umbrella();
r.push(ScanRule::new(
ScanType::FirmwareStatic,
true,
"EMBA / binwalk static analysis of the image",
Firmware,
));
r.push(ScanRule::new(
ScanType::Sbom,
true,
"SBOM from image layers / recipes",
Firmware,
));
r.push(ScanRule::new(
ScanType::Cve,
true,
"Match image components against known CVEs",
Firmware,
));
r.push(ScanRule::new(
ScanType::Dast,
false,
"Dynamic scan of exposed network services (if any)",
HttpUrl,
));
r
}
TargetType::PlcSps => {
// A PLC/SPS device is a composite: the control application *and* the
// device it runs on (firmware/OS + reachable runtime services). The
// control-logic scan runs on the PLC project; the firmware and DAST
// scans light up only when a firmware image / running endpoint is
// attached (e.g. a CODESYS runtime on a Yocto image with WebVisu).
// Firmware-image SBOM/CVE *execution* is shared with the firmware
// families and tracked in #151/#128; DAST over a WebVisu/OPC-UA
// endpoint uses the existing DAST path.
vec![
ScanRule::new(
ScanType::PlcControlLogic,
true,
"Control-logic security rules over the PLC program",
Plc,
),
// Device-level scans are offered but opt-in (default-off): they
// apply only when a firmware image is attached, and firmware-image
// SBOM/CVE *execution* is shared with the firmware families and
// still landing (#151/#128), so they must not silently auto-run.
ScanRule::new(
ScanType::FirmwareStatic,
false,
"Static analysis of the device firmware image (OS + runtime)",
Firmware,
),
ScanRule::new(
ScanType::Sbom,
false,
"SBOM from the device firmware image (OS packages + CODESYS runtime)",
Firmware,
),
ScanRule::new(
ScanType::Cve,
false,
"Match device firmware components against known CVEs",
Firmware,
),
ScanRule::new(
ScanType::Dast,
false,
"Dynamic scan of the running device (WebVisu / exposed services)",
HttpUrl,
),
ScanRule::new(
ScanType::IcsProbe,
false,
"Probe the running device over industrial protocols (Modbus/TCP, …)",
RunningUrl,
),
]
}
}
}
/// Whether an active penetration test is applicable to this target type.
///
/// Pentest runs as its own session (not a [`ScanType`] scan) and needs a
/// reachable running target, so it is offered only for the network-reachable
/// families.
pub fn supports_pentest(target_type: TargetType) -> bool {
matches!(
target_type,
TargetType::WebApp
| TargetType::BackendService
| TargetType::AndroidApp
| TargetType::IosApp
| TargetType::EmbeddedLinuxYocto
// A PLC/SPS device exposes reachable runtime services (WebVisu, OPC UA,
// the CODESYS programming protocol), so an active pentest applies.
| TargetType::PlcSps
)
}
/// The representative artifact kind a requirement is satisfied by.
fn representative_kind(req: ArtifactRequirement) -> Option<ArtifactKind> {
match req {
ArtifactRequirement::Code => Some(ArtifactKind::GitRepo),
ArtifactRequirement::RunningUrl | ArtifactRequirement::HttpUrl => {
Some(ArtifactKind::LiveUrl)
}
ArtifactRequirement::Firmware => Some(ArtifactKind::FirmwareImage),
ArtifactRequirement::Plc => Some(ArtifactKind::PlcProject),
ArtifactRequirement::Mobile => Some(ArtifactKind::MobilePackage),
ArtifactRequirement::Container => Some(ArtifactKind::ContainerImage),
ArtifactRequirement::Any => None,
}
}
/// Whether a live-URL reference is an http(s) web endpoint (vs. an industrial
/// endpoint like `modbus://` / `opc.tcp://`, which DAST cannot crawl).
fn is_http_url(source_ref: &str) -> bool {
let s = source_ref.trim();
s.starts_with("http://") || s.starts_with("https://")
}
/// Whether the target carries an artifact that satisfies the requirement.
fn requirement_satisfied(req: ArtifactRequirement, target: &OnboardedTarget) -> bool {
match req {
ArtifactRequirement::Code => target.code_artifact().is_some(),
ArtifactRequirement::RunningUrl => target.has(ArtifactKind::LiveUrl),
ArtifactRequirement::HttpUrl => target
.artifacts
.iter()
.any(|a| a.kind == ArtifactKind::LiveUrl && is_http_url(&a.source_ref)),
ArtifactRequirement::Firmware => target.has(ArtifactKind::FirmwareImage),
// A PLC project artifact, or a code artifact (git repo / source archive)
// holding the control logic as PLCopen XML / ST exports — the common way
// CODESYS projects are version-controlled.
ArtifactRequirement::Plc => {
target.has(ArtifactKind::PlcProject) || target.code_artifact().is_some()
}
ArtifactRequirement::Mobile => target.has(ArtifactKind::MobilePackage),
ArtifactRequirement::Container => target.has(ArtifactKind::ContainerImage),
ArtifactRequirement::Any => true,
}
}
/// Resolve the matrix for a concrete target into the scans it can run, marking
/// any whose required artifact is missing as blocked.
pub fn applicable_scans(target: &OnboardedTarget) -> Vec<ScanOption> {
rules_for(target.target_type)
.into_iter()
.map(|rule| {
let satisfied = requirement_satisfied(rule.requires, target);
let required_artifact = representative_kind(rule.requires);
let blocked_reason = if satisfied {
None
} else if rule.requires == ArtifactRequirement::HttpUrl {
// A live URL may be present but non-HTTP (e.g. modbus://): be
// specific so the user knows DAST needs a web endpoint.
Some("no http(s) live URL — DAST needs a web endpoint".to_string())
} else {
Some(match required_artifact {
Some(kind) => format!("no {kind} artifact provided"),
None => "required artifact missing".to_string(),
})
};
ScanOption {
scan: rule.scan,
default_on: rule.default_on && satisfied,
rationale: rule.rationale.to_string(),
required_artifact,
blocked_reason,
}
})
.collect()
}
#[cfg(test)]
#[allow(clippy::expect_used, clippy::unwrap_used)]
mod tests {
use super::*;
use crate::models::{Artifact, PlcFormat};
fn target_with(target_type: TargetType, artifacts: Vec<Artifact>) -> OnboardedTarget {
let mut t = OnboardedTarget::new("t".to_string(), target_type);
t.artifacts = artifacts;
t
}
fn option<'a>(opts: &'a [ScanOption], scan: ScanType) -> Option<&'a ScanOption> {
opts.iter().find(|o| o.scan == scan)
}
#[test]
fn webapp_with_code_and_url_offers_sast_and_dast() {
let t = target_with(
TargetType::WebApp,
vec![
Artifact::git_repo("u", "main"),
Artifact::live_url("http://x"),
],
);
let opts = applicable_scans(&t);
let sast = option(&opts, ScanType::Sast).expect("sast offered");
assert!(sast.default_on && sast.blocked_reason.is_none());
let dast = option(&opts, ScanType::Dast).expect("dast offered");
assert!(dast.default_on && dast.blocked_reason.is_none());
}
#[test]
fn webapp_without_url_blocks_dast() {
let t = target_with(TargetType::WebApp, vec![Artifact::git_repo("u", "main")]);
let opts = applicable_scans(&t);
let dast = option(&opts, ScanType::Dast).expect("dast listed");
assert!(!dast.default_on);
assert!(dast.blocked_reason.is_some());
assert_eq!(dast.required_artifact, Some(ArtifactKind::LiveUrl));
}
#[test]
fn firmware_offers_firmware_static_and_not_dast() {
let t = target_with(
TargetType::FirmwareBareMetal,
vec![Artifact::firmware_image("fw.bin")],
);
let opts = applicable_scans(&t);
let fw = option(&opts, ScanType::FirmwareStatic).expect("firmware static offered");
assert!(fw.default_on && fw.blocked_reason.is_none());
assert!(option(&opts, ScanType::Dast).is_none());
}
#[test]
fn plc_control_logic_is_default_on_and_device_scans_block_without_artifacts() {
// A PLC project alone: control-logic runs; the device-level scans are
// offered but blocked until a firmware image / running endpoint is added.
let t = target_with(
TargetType::PlcSps,
vec![Artifact::plc_project("p.xml", PlcFormat::PlcopenXml)],
);
let opts = applicable_scans(&t);
let plc = option(&opts, ScanType::PlcControlLogic).expect("control-logic offered");
assert!(plc.default_on && plc.blocked_reason.is_none());
for scan in [ScanType::FirmwareStatic, ScanType::Sbom, ScanType::Cve] {
let o = option(&opts, scan).expect("device scan offered");
assert!(
!o.default_on,
"{scan} must not pre-select without a firmware image"
);
assert!(o.blocked_reason.is_some());
}
let dast = option(&opts, ScanType::Dast).expect("dast offered");
assert!(!dast.default_on);
assert!(dast.blocked_reason.is_some());
}
#[test]
fn plc_control_logic_is_satisfied_by_a_git_repo() {
// A CODESYS project version-controlled in git (PLCopen XML / ST exports),
// no uploaded PlcProject artifact.
let t = target_with(TargetType::PlcSps, vec![Artifact::git_repo("u", "main")]);
let opts = applicable_scans(&t);
let plc = option(&opts, ScanType::PlcControlLogic).expect("control-logic offered");
assert!(
plc.default_on && plc.blocked_reason.is_none(),
"a git repo should satisfy PLC control-logic"
);
}
#[test]
fn plc_composite_lights_up_device_scans_with_firmware_and_url() {
// A CODESYS-on-Yocto device: PLC project + firmware image + WebVisu URL.
let t = target_with(
TargetType::PlcSps,
vec![
Artifact::plc_project("p.xml", PlcFormat::PlcopenXml),
Artifact::firmware_image("device.img"),
Artifact::live_url("http://plc.local/webvisu"),
],
);
let opts = applicable_scans(&t);
for scan in [
ScanType::PlcControlLogic,
ScanType::FirmwareStatic,
ScanType::Sbom,
ScanType::Cve,
] {
let o = option(&opts, scan).expect("scan offered");
assert!(o.blocked_reason.is_none(), "{scan} should be unblocked");
}
// Control-logic auto-runs; the device-level scans are unblocked but opt-in
// (default-off) until firmware-image execution lands (#151/#128).
assert!(option(&opts, ScanType::PlcControlLogic).unwrap().default_on);
assert!(!option(&opts, ScanType::Sbom).unwrap().default_on);
assert!(!option(&opts, ScanType::Dast).unwrap().default_on);
assert!(option(&opts, ScanType::Dast)
.unwrap()
.blocked_reason
.is_none());
}
#[test]
fn plc_with_modbus_url_offers_ics_probe_but_blocks_dast() {
// A soft-PLC reachable only over Modbus/TCP (no WebVisu). The ICS probe
// is applicable (it works off host:port), but DAST — an HTTP crawler —
// must be blocked so it isn't offered/run against a non-web endpoint.
let t = target_with(
TargetType::PlcSps,
vec![Artifact::live_url("modbus://plc-sim:502")],
);
let opts = applicable_scans(&t);
let ics = option(&opts, ScanType::IcsProbe).expect("ics probe offered");
assert!(
ics.blocked_reason.is_none(),
"ICS probe should be unblocked for a modbus:// endpoint"
);
assert!(!ics.default_on, "ICS probe stays opt-in (default-off)");
let dast = option(&opts, ScanType::Dast).expect("dast listed");
assert!(
dast.blocked_reason.is_some(),
"DAST must be blocked without an http(s) endpoint"
);
assert!(!dast.default_on);
}
#[test]
fn plc_with_http_webvisu_offers_both_dast_and_ics_probe() {
// A PLC exposing a WebVisu over HTTP: both DAST (web) and the ICS probe
// (OT ports on the same host) are applicable.
let t = target_with(
TargetType::PlcSps,
vec![Artifact::live_url("http://plc.local/webvisu")],
);
let opts = applicable_scans(&t);
assert!(option(&opts, ScanType::Dast)
.expect("dast offered")
.blocked_reason
.is_none());
assert!(option(&opts, ScanType::IcsProbe)
.expect("ics probe offered")
.blocked_reason
.is_none());
}
#[test]
fn pentest_support_matches_reachable_families() {
assert!(supports_pentest(TargetType::WebApp));
assert!(supports_pentest(TargetType::BackendService));
assert!(supports_pentest(TargetType::EmbeddedLinuxYocto));
// A PLC/SPS device is network-reachable (WebVisu / OPC UA / 11740).
assert!(supports_pentest(TargetType::PlcSps));
assert!(!supports_pentest(TargetType::FirmwareBareMetal));
assert!(!supports_pentest(TargetType::DesktopApp));
}
#[test]
fn every_target_type_has_at_least_one_rule() {
for tt in [
TargetType::WebApp,
TargetType::BackendService,
TargetType::DesktopApp,
TargetType::AndroidApp,
TargetType::IosApp,
TargetType::FirmwareBareMetal,
TargetType::FirmwareRtos,
TargetType::EmbeddedLinuxYocto,
TargetType::PlcSps,
] {
assert!(!rules_for(tt).is_empty(), "{tt} has no rules");
}
}
}
+51
View File
@@ -0,0 +1,51 @@
//! The target-classification port.
//!
//! A [`TargetClassifier`] inspects a target's artifacts (and optionally their
//! ingested working directories) and proposes one or more [`ClassifierVerdict`]s
//! — a target type, a confidence, and the facts the decision rested on. Concrete
//! classifiers live in the agent (language/build-system fingerprinting, a
//! firmware detector backed by tramiton, etc.); a registry merges and ranks
//! their verdicts. This mirrors the [`crate::traits::Scanner`] port so the two
//! read the same way.
use std::collections::HashMap;
use std::path::PathBuf;
use crate::error::CoreError;
use crate::models::{Artifact, DetectedFact, TargetType};
/// Everything a classifier needs to reason about a target.
pub struct ClassificationInput<'a> {
/// The artifacts declared for the target.
pub artifacts: &'a [Artifact],
/// Ingested working paths, keyed by [`Artifact::id`]. Absent for artifacts
/// with no on-disk form (e.g. a live URL).
pub working_paths: &'a HashMap<String, PathBuf>,
/// Free-form description of the target, if provided.
pub description: Option<&'a str>,
}
/// A single classifier's proposal for a target.
pub struct ClassifierVerdict {
/// The proposed target type.
pub target_type: TargetType,
/// Confidence in `[0.0, 1.0]`.
pub confidence: f32,
/// Facts that informed the proposal.
pub facts: Vec<DetectedFact>,
/// Human-readable explanation.
pub rationale: String,
}
/// A source of target-type classification.
#[allow(async_fn_in_trait)]
pub trait TargetClassifier: Send + Sync {
/// Stable identifier for this classifier (recorded in `detected_by`).
fn name(&self) -> &str;
/// Propose zero or more ranked verdicts for the given input.
async fn classify(
&self,
input: &ClassificationInput<'_>,
) -> Result<Vec<ClassifierVerdict>, CoreError>;
}
+45
View File
@@ -0,0 +1,45 @@
//! The compliance-controls provider port.
//!
//! The mapping engine turns findings into compliance status against a corpus of
//! controls. That corpus is pluggable: the built-in OSCAL catalog by default, or
//! a tenant-owned RAG of atomic controls derived from laws
//! (`breakpilot-compliance`) when available. A [`ControlsProvider`] abstracts the
//! source so the mapping engine does not hardcode a catalog.
use crate::error::CoreError;
use crate::models::ComplianceFramework;
/// A control retrieved from a controls corpus.
#[derive(Debug, Clone)]
pub struct Control {
/// Stable control identifier (e.g. an OSCAL control id or a RAG chunk id).
pub id: String,
/// The framework this control belongs to.
pub framework: ComplianceFramework,
/// Short human-readable title.
pub title: String,
/// The control text / requirement.
pub text: String,
/// Free-form source reference (catalog name, law citation, ...).
pub source: Option<String>,
}
/// A query for relevant controls.
pub struct ControlQuery<'a> {
/// Frameworks in scope for the target.
pub frameworks: &'a [ComplianceFramework],
/// Free-text describing what to map (a finding summary, a component, ...).
pub context: &'a str,
/// Maximum number of controls to return.
pub limit: usize,
}
/// A source of compliance controls (built-in OSCAL catalog, breakpilot RAG, ...).
#[allow(async_fn_in_trait)]
pub trait ControlsProvider: Send + Sync {
/// Stable identifier for this provider.
fn name(&self) -> &str;
/// Retrieve the controls most relevant to the query.
async fn controls(&self, query: &ControlQuery<'_>) -> Result<Vec<Control>, CoreError>;
}
+58
View File
@@ -0,0 +1,58 @@
//! The external-evidence provider port.
//!
//! A sibling product (tramiton, for firmware) may already hold authoritative
//! analysis for an artifact. An [`EvidenceProvider`] lets compliance-scanner
//! *reconcile* that evidence — a build plan, an SBOM, a VEX document, a
//! reproducible-build lock, an attestation — instead of recomputing it. The key
//! used to match is the artifact content digest (a firmware sha256, which equals
//! [`crate::models::Artifact::content_hash`]).
//!
//! Concrete providers live in the agent (a tramiton CLI shell-out today, a cloud
//! client later) plus a deterministic mock for tests, so nothing here depends on
//! an external binary.
use std::path::Path;
use crate::error::CoreError;
use crate::models::{Artifact, ExternalSystem};
/// A single reconcilable evidence document fetched from a sibling product.
#[derive(Debug, Clone)]
pub struct EvidenceDocument {
/// What the document is: `build_plan` | `sbom` | `vex` | `lock` | `attestation`.
pub kind: String,
/// The document's format (e.g. `cyclonedx-1.5`, `openvex-0.2.0`, `toml`, `json`).
pub format: String,
/// The raw document payload.
pub content: String,
}
/// The evidence a provider could return for a target's artifact.
#[derive(Debug, Clone, Default)]
pub struct ReconciledEvidence {
/// The sibling's project identifier, if resolved.
pub project_id: Option<String>,
/// The subject content digest the evidence pertains to.
pub subject_sha256: Option<String>,
/// The documents fetched (any of build plan / SBOM / VEX / lock / attestation).
pub documents: Vec<EvidenceDocument>,
}
/// A source of externally-held, reconcilable evidence for an artifact.
#[allow(async_fn_in_trait)]
pub trait EvidenceProvider: Send + Sync {
/// Which sibling product this provider integrates.
fn system(&self) -> ExternalSystem;
/// Whether this provider can handle the given artifact + working path
/// (e.g. tramiton handles firmware images / embedded source trees).
fn handles(&self, artifact: &Artifact, working_path: Option<&Path>) -> bool;
/// Reconcile existing evidence for the artifact, keyed by its content digest.
/// Returns `Ok(None)` when the provider has nothing for this artifact.
async fn reconcile(
&self,
artifact: &Artifact,
working_path: Option<&Path>,
) -> Result<Option<ReconciledEvidence>, CoreError>;
}
+6
View File
@@ -1,10 +1,16 @@
pub mod classifier;
pub mod controls;
pub mod dast_agent;
pub mod evidence;
pub mod graph_builder;
pub mod issue_tracker;
pub mod pentest_tool;
pub mod scanner;
pub use classifier::{ClassificationInput, ClassifierVerdict, TargetClassifier};
pub use controls::{Control, ControlQuery, ControlsProvider};
pub use dast_agent::{DastAgent, DastContext, DiscoveredEndpoint, EndpointParameter};
pub use evidence::{EvidenceDocument, EvidenceProvider, ReconciledEvidence};
pub use graph_builder::{LanguageParser, ParseOutput};
pub use issue_tracker::IssueTracker;
pub use pentest_tool::{PentestTool, PentestToolContext, PentestToolResult};
+6 -2
View File
@@ -10,8 +10,10 @@ pub enum Route {
#[layout(AppShell)]
#[route("/")]
OverviewPage {},
#[route("/repositories")]
RepositoriesPage {},
#[route("/targets")]
TargetsPage {},
#[route("/onboard")]
OnboardingPage {},
#[route("/findings")]
FindingsPage {},
#[route("/findings/:id")]
@@ -44,6 +46,8 @@ pub enum Route {
PentestSessionPage { session_id: String },
#[route("/mcp-servers")]
McpServersPage {},
#[route("/mcp-tokens")]
McpTokensPage {},
}
const FAVICON: Asset = asset!("/assets/favicon.svg");
@@ -4,8 +4,9 @@ use dioxus_free_icons::Icon;
use crate::app::Route;
use crate::infrastructure::dast::fetch_dast_targets;
use crate::infrastructure::onboarding::fetch_targets;
use crate::infrastructure::pentest::{create_pentest_session_wizard, lookup_repo_by_url};
use crate::infrastructure::repositories::{fetch_repositories, fetch_ssh_public_key};
use crate::infrastructure::repositories::fetch_ssh_public_key;
const DISCLAIMER_TEXT: &str = "I confirm that I have authorization to perform security testing \
against the specified target. I understand that penetration testing may cause disruption to the \
@@ -39,7 +40,7 @@ pub fn PentestWizard(show: Signal<bool>) -> Element {
let mut show_target_dropdown = use_signal(|| false);
let mut show_repo_dropdown = use_signal(|| false);
let existing_targets = use_resource(|| async { fetch_dast_targets().await.ok() });
let existing_repos = use_resource(|| async { fetch_repositories(1).await.ok() });
let existing_repos = use_resource(|| async { fetch_targets().await.ok() });
// SSH key state for private repos
let mut ssh_public_key = use_signal(String::new);
@@ -211,7 +212,25 @@ pub fn PentestWizard(show: Signal<bool>) -> Element {
Some(Some(data)) => data
.data
.iter()
.map(|r| (r.git_url.clone(), r.name.clone()))
.filter_map(|t| {
let name = t
.get("name")
.and_then(|v| v.as_str())
.unwrap_or_default()
.to_string();
let git_url = t
.get("artifacts")
.and_then(|a| a.as_array())
.and_then(|arr| {
arr.iter().find(|a| {
a.get("kind").and_then(|k| k.as_str()) == Some("git_repo")
})
})
.and_then(|a| a.get("source_ref"))
.and_then(|s| s.as_str())?
.to_string();
Some((git_url, name))
})
.collect(),
_ => Vec::new(),
}
@@ -24,10 +24,15 @@ pub fn Sidebar() -> Element {
icon: rsx! { Icon { icon: BsSpeedometer2, width: 18, height: 18 } },
},
NavItem {
label: "Repositories",
route: Route::RepositoriesPage {},
label: "Targets",
route: Route::TargetsPage {},
icon: rsx! { Icon { icon: BsFolder2Open, width: 18, height: 18 } },
},
NavItem {
label: "Onboard",
route: Route::OnboardingPage {},
icon: rsx! { Icon { icon: BsPlusCircle, width: 18, height: 18 } },
},
NavItem {
label: "Findings",
route: Route::FindingsPage {},
@@ -19,10 +19,6 @@ impl Database {
Ok(Self { inner: db })
}
pub fn repositories(&self) -> Collection<TrackedRepository> {
self.inner.collection("repositories")
}
pub fn findings(&self) -> Collection<Finding> {
self.inner.collection("findings")
}
@@ -0,0 +1,90 @@
//! Server-functions for the MCP-tokens management UI.
//!
//! These wrap the agent's `/api/v1/mcp-tokens` CRUD endpoints. The raw
//! token returned by `create_mcp_token` is only visible at creation
//! time — the agent's storage never holds the plaintext.
use dioxus::prelude::*;
use serde::{Deserialize, Serialize};
#[derive(Debug, Clone, Serialize, Deserialize, Default)]
pub struct McpTokenView {
pub id: String,
pub name: String,
pub token_prefix: String,
pub created_by: String,
pub created_at: serde_json::Value,
#[serde(default)]
pub last_used_at: Option<serde_json::Value>,
#[serde(default)]
pub revoked: bool,
}
#[derive(Debug, Clone, Serialize, Deserialize, Default)]
pub struct McpTokensListResponse {
pub data: Vec<McpTokenView>,
}
#[derive(Debug, Clone, Serialize, Deserialize, Default)]
pub struct CreateMcpTokenResponse {
/// Raw token. Shown ONCE — the user must copy it now.
pub token: String,
pub view: McpTokenView,
}
#[server]
pub async fn fetch_mcp_tokens() -> Result<McpTokensListResponse, ServerFnError> {
let resp = super::agent_client::agent_get("/api/v1/mcp-tokens")
.await?
.send()
.await
.map_err(|e| ServerFnError::new(e.to_string()))?;
let body: McpTokensListResponse = resp
.json()
.await
.map_err(|e| ServerFnError::new(e.to_string()))?;
Ok(body)
}
#[server]
pub async fn create_mcp_token(name: String) -> Result<CreateMcpTokenResponse, ServerFnError> {
if name.trim().is_empty() {
return Err(ServerFnError::new("Name is required"));
}
let resp = super::agent_client::agent_request(reqwest::Method::POST, "/api/v1/mcp-tokens")
.await?
.json(&serde_json::json!({ "name": name.trim() }))
.send()
.await
.map_err(|e| ServerFnError::new(e.to_string()))?;
if !resp.status().is_success() {
let body = resp.text().await.unwrap_or_default();
return Err(ServerFnError::new(format!(
"Failed to create token: {body}"
)));
}
let body: CreateMcpTokenResponse = resp
.json()
.await
.map_err(|e| ServerFnError::new(e.to_string()))?;
Ok(body)
}
#[server]
pub async fn revoke_mcp_token(id: String) -> Result<(), ServerFnError> {
let resp = super::agent_client::agent_request(
reqwest::Method::DELETE,
&format!("/api/v1/mcp-tokens/{id}"),
)
.await?
.send()
.await
.map_err(|e| ServerFnError::new(e.to_string()))?;
if !resp.status().is_success() {
let body = resp.text().await.unwrap_or_default();
return Err(ServerFnError::new(format!(
"Failed to revoke token: {body}"
)));
}
Ok(())
}
@@ -8,7 +8,9 @@ pub mod graph;
pub mod help_chat;
pub mod issues;
pub mod mcp;
pub mod mcp_tokens;
pub mod notifications;
pub mod onboarding;
pub mod pentest;
#[allow(clippy::too_many_arguments)]
pub mod repositories;
@@ -0,0 +1,288 @@
//! Server functions for the onboarding wizard — proxy to the agent's
//! `/api/v1/targets` endpoints.
use dioxus::prelude::*;
use serde::{Deserialize, Serialize};
/// One artifact the wizard collects for a target.
#[derive(Debug, Clone, Serialize, Deserialize, Default, PartialEq)]
pub struct ArtifactInputDto {
pub kind: String,
pub source_ref: String,
#[serde(skip_serializing_if = "Option::is_none")]
pub branch: Option<String>,
#[serde(skip_serializing_if = "Option::is_none")]
pub plc_format: Option<String>,
}
#[derive(Debug, Clone, Serialize, Deserialize, Default)]
pub struct TargetsResponse {
pub data: Vec<serde_json::Value>,
pub total: Option<u64>,
}
#[derive(Debug, Clone, Serialize, Deserialize, Default)]
pub struct TargetResponse {
pub data: serde_json::Value,
}
#[derive(Debug, Clone, Serialize, Deserialize, Default)]
pub struct ApplicableScansData {
#[serde(default)]
pub scans: Vec<serde_json::Value>,
#[serde(default)]
pub pentest_supported: bool,
}
#[derive(Debug, Clone, Serialize, Deserialize, Default)]
pub struct ApplicableScansResponse {
pub data: ApplicableScansData,
}
/// Validate a target name. The name is used as the clone directory downstream,
/// so it must be a single safe segment (no slashes) and free of stray spaces.
pub fn validate_target_name(name: &str) -> Option<String> {
let n = name.trim();
if n.is_empty() {
return Some("Enter a name".to_string());
}
if name != n {
return Some("Remove the leading/trailing spaces".to_string());
}
if n.contains('/') || n.contains('\\') {
return Some("No slashes — the name becomes a folder (e.g. stm32f411-blinky)".to_string());
}
None
}
/// Client-side validation of an artifact reference for its kind. Returns an
/// error message when the value is obviously wrong for its category, so the
/// wizard / editor can flag it up front instead of the scan discovering it.
pub fn validate_artifact_ref(kind: &str, source_ref: &str) -> Option<String> {
let s = source_ref;
if s.trim().is_empty() {
return Some("Cannot be empty".to_string());
}
if s != s.trim() {
return Some("Remove the leading/trailing spaces".to_string());
}
let no_space = !s.contains(char::is_whitespace);
match kind {
"git_repo" => {
let looks_git = s.starts_with("https://")
|| s.starts_with("http://")
|| s.starts_with("ssh://")
|| s.starts_with("git://")
|| (s.contains('@') && s.contains(':'));
(!(looks_git && no_space))
.then(|| "Enter a git URL — https://…, ssh://…, or git@host:path".to_string())
}
"live_url" => {
// http(s) for web/DAST targets; modbus:// and opc.tcp:// for ICS
// devices probed by the ICS probe (e.g. modbus://plc:502).
let ok = (s.starts_with("https://")
|| s.starts_with("http://")
|| s.starts_with("modbus://")
|| s.starts_with("opc.tcp://"))
&& no_space;
(!ok).then(|| {
"Enter a URL — https://app.example.com, or modbus://host:502 for a PLC".to_string()
})
}
"container_image" => {
(!no_space).then(|| "Enter an image ref, e.g. registry/name:tag".to_string())
}
"source_archive" | "firmware_image" | "mobile_package" | "plc_project" => {
(!no_space).then(|| "Enter a path or URL (no spaces)".to_string())
}
// plaintext_description (and anything unknown): accept free-form text.
_ => None,
}
}
/// List onboarded targets.
#[server]
pub async fn fetch_targets() -> Result<TargetsResponse, ServerFnError> {
let resp = super::agent_client::agent_get("/api/v1/targets")
.await?
.send()
.await
.map_err(|e| ServerFnError::new(e.to_string()))?;
resp.json()
.await
.map_err(|e| ServerFnError::new(e.to_string()))
}
/// Create a target with the collected artifacts.
#[server]
pub async fn create_target(
name: String,
target_type: String,
description: Option<String>,
artifacts: Vec<ArtifactInputDto>,
) -> Result<TargetResponse, ServerFnError> {
let body = serde_json::json!({
"name": name,
"target_type": target_type,
"description": description,
"artifacts": artifacts,
});
let resp = super::agent_client::agent_request(reqwest::Method::POST, "/api/v1/targets")
.await?
.json(&body)
.send()
.await
.map_err(|e| ServerFnError::new(e.to_string()))?;
resp.json()
.await
.map_err(|e| ServerFnError::new(e.to_string()))
}
/// Upload a file artifact (PLC project, firmware image, source archive, mobile
/// package) to a target — proxied to the agent as multipart.
#[server]
pub async fn upload_target_artifact(
id: String,
kind: String,
plc_format: Option<String>,
filename: String,
bytes: Vec<u8>,
) -> Result<TargetResponse, ServerFnError> {
let mut form = reqwest::multipart::Form::new().text("kind", kind).part(
"file",
reqwest::multipart::Part::bytes(bytes).file_name(filename),
);
if let Some(pf) = plc_format {
form = form.text("plc_format", pf);
}
let resp = super::agent_client::agent_request(
reqwest::Method::POST,
&format!("/api/v1/targets/{id}/artifacts/upload"),
)
.await?
.multipart(form)
.send()
.await
.map_err(|e| ServerFnError::new(e.to_string()))?;
resp.json()
.await
.map_err(|e| ServerFnError::new(e.to_string()))
}
/// Update a target's name / type / artifacts (dashboard editor).
#[server]
pub async fn update_target(
id: String,
name: Option<String>,
target_type: Option<String>,
artifacts: Option<Vec<ArtifactInputDto>>,
) -> Result<TargetResponse, ServerFnError> {
let mut body = serde_json::Map::new();
if let Some(n) = name {
body.insert("name".to_string(), serde_json::json!(n));
}
if let Some(t) = target_type {
body.insert("target_type".to_string(), serde_json::json!(t));
}
if let Some(a) = artifacts {
body.insert(
"artifacts".to_string(),
serde_json::to_value(a).map_err(|e| ServerFnError::new(e.to_string()))?,
);
}
let resp = super::agent_client::agent_request(
reqwest::Method::PATCH,
&format!("/api/v1/targets/{id}"),
)
.await?
.json(&serde_json::Value::Object(body))
.send()
.await
.map_err(|e| ServerFnError::new(e.to_string()))?;
resp.json()
.await
.map_err(|e| ServerFnError::new(e.to_string()))
}
/// Enable specific opt-in scans on a target by setting `scan_config.enabled_scans`.
/// `scans` are serde scan-type names (lowercase, no underscores — e.g. `icsprobe`).
#[server]
pub async fn enable_target_scans(
id: String,
scans: Vec<String>,
) -> Result<TargetResponse, ServerFnError> {
let body = serde_json::json!({ "scan_config": { "enabled_scans": scans } });
let resp = super::agent_client::agent_request(
reqwest::Method::PATCH,
&format!("/api/v1/targets/{id}"),
)
.await?
.json(&body)
.send()
.await
.map_err(|e| ServerFnError::new(e.to_string()))?;
resp.json()
.await
.map_err(|e| ServerFnError::new(e.to_string()))
}
/// Run kind-based classification on a target.
#[server]
pub async fn detect_target(id: String) -> Result<TargetResponse, ServerFnError> {
let resp = super::agent_client::agent_request(
reqwest::Method::POST,
&format!("/api/v1/targets/{id}/detect"),
)
.await?
.send()
.await
.map_err(|e| ServerFnError::new(e.to_string()))?;
resp.json()
.await
.map_err(|e| ServerFnError::new(e.to_string()))
}
/// Fetch the scan-applicability matrix for a target.
#[server]
pub async fn fetch_applicable_scans(id: String) -> Result<ApplicableScansResponse, ServerFnError> {
let resp = super::agent_client::agent_get(&format!("/api/v1/targets/{id}/applicable-scans"))
.await?
.send()
.await
.map_err(|e| ServerFnError::new(e.to_string()))?;
resp.json()
.await
.map_err(|e| ServerFnError::new(e.to_string()))
}
/// Delete a target (and cascade its findings / SBOM / scan runs / CVE alerts).
#[server]
pub async fn delete_target(id: String) -> Result<serde_json::Value, ServerFnError> {
let resp = super::agent_client::agent_request(
reqwest::Method::DELETE,
&format!("/api/v1/targets/{id}"),
)
.await?
.send()
.await
.map_err(|e| ServerFnError::new(e.to_string()))?;
resp.json()
.await
.map_err(|e| ServerFnError::new(e.to_string()))
}
/// Trigger a scan for a target.
#[server]
pub async fn trigger_target_scan(id: String) -> Result<serde_json::Value, ServerFnError> {
let resp = super::agent_client::agent_request(
reqwest::Method::POST,
&format!("/api/v1/targets/{id}/scan"),
)
.await?
.send()
.await
.map_err(|e| ServerFnError::new(e.to_string()))?;
resp.json()
.await
.map_err(|e| ServerFnError::new(e.to_string()))
}
@@ -1,145 +1,10 @@
//! The agent's SSH deploy public key — shown so a read-only deploy key can be
//! added to private git targets. (The legacy repositories CRUD moved to the
//! unified onboarding/targets API.)
use dioxus::prelude::*;
use serde::{Deserialize, Serialize};
use compliance_core::models::TrackedRepository;
#[derive(Debug, Clone, Serialize, Deserialize, Default)]
pub struct RepositoryListResponse {
pub data: Vec<TrackedRepository>,
pub total: Option<u64>,
pub page: Option<u64>,
}
#[server]
pub async fn fetch_repositories(page: u64) -> Result<RepositoryListResponse, ServerFnError> {
let path = format!("/api/v1/repositories?page={page}&limit=20");
let resp = super::agent_client::agent_get(&path)
.await?
.send()
.await
.map_err(|e| ServerFnError::new(e.to_string()))?;
let body: RepositoryListResponse = resp
.json()
.await
.map_err(|e| ServerFnError::new(e.to_string()))?;
Ok(body)
}
#[server]
pub async fn add_repository(
name: String,
git_url: String,
default_branch: String,
auth_token: Option<String>,
auth_username: Option<String>,
tracker_type: Option<String>,
tracker_owner: Option<String>,
tracker_repo: Option<String>,
tracker_token: Option<String>,
) -> Result<(), ServerFnError> {
let mut body = serde_json::json!({
"name": name,
"git_url": git_url,
"default_branch": default_branch,
});
if let Some(token) = auth_token.filter(|t| !t.is_empty()) {
body["auth_token"] = serde_json::Value::String(token);
}
if let Some(username) = auth_username.filter(|u| !u.is_empty()) {
body["auth_username"] = serde_json::Value::String(username);
}
if let Some(tt) = tracker_type.filter(|t| !t.is_empty()) {
body["tracker_type"] = serde_json::Value::String(tt);
}
if let Some(to) = tracker_owner.filter(|t| !t.is_empty()) {
body["tracker_owner"] = serde_json::Value::String(to);
}
if let Some(tr) = tracker_repo.filter(|t| !t.is_empty()) {
body["tracker_repo"] = serde_json::Value::String(tr);
}
if let Some(tk) = tracker_token.filter(|t| !t.is_empty()) {
body["tracker_token"] = serde_json::Value::String(tk);
}
let resp = super::agent_client::agent_request(reqwest::Method::POST, "/api/v1/repositories")
.await?
.json(&body)
.send()
.await
.map_err(|e| ServerFnError::new(e.to_string()))?;
if !resp.status().is_success() {
let body = resp.text().await.unwrap_or_default();
return Err(ServerFnError::new(format!(
"Failed to add repository: {body}"
)));
}
Ok(())
}
#[server]
pub async fn update_repository(
repo_id: String,
name: Option<String>,
default_branch: Option<String>,
auth_token: Option<String>,
auth_username: Option<String>,
tracker_type: Option<String>,
tracker_owner: Option<String>,
tracker_repo: Option<String>,
tracker_token: Option<String>,
scan_schedule: Option<String>,
) -> Result<(), ServerFnError> {
let mut body = serde_json::Map::new();
if let Some(v) = name.filter(|s| !s.is_empty()) {
body.insert("name".into(), serde_json::Value::String(v));
}
if let Some(v) = default_branch.filter(|s| !s.is_empty()) {
body.insert("default_branch".into(), serde_json::Value::String(v));
}
if let Some(v) = auth_token {
body.insert("auth_token".into(), serde_json::Value::String(v));
}
if let Some(v) = auth_username {
body.insert("auth_username".into(), serde_json::Value::String(v));
}
if let Some(v) = tracker_type {
body.insert("tracker_type".into(), serde_json::Value::String(v));
}
if let Some(v) = tracker_owner {
body.insert("tracker_owner".into(), serde_json::Value::String(v));
}
if let Some(v) = tracker_repo {
body.insert("tracker_repo".into(), serde_json::Value::String(v));
}
if let Some(v) = tracker_token {
body.insert("tracker_token".into(), serde_json::Value::String(v));
}
if let Some(v) = scan_schedule {
body.insert("scan_schedule".into(), serde_json::Value::String(v));
}
let resp = super::agent_client::agent_request(
reqwest::Method::PATCH,
&format!("/api/v1/repositories/{repo_id}"),
)
.await?
.json(&body)
.send()
.await
.map_err(|e| ServerFnError::new(e.to_string()))?;
if !resp.status().is_success() {
let text = resp.text().await.unwrap_or_default();
return Err(ServerFnError::new(format!(
"Failed to update repository: {text}"
)));
}
Ok(())
}
/// Fetch the agent's SSH deploy public key.
#[server]
pub async fn fetch_ssh_public_key() -> Result<String, ServerFnError> {
let resp = super::agent_client::agent_get("/api/v1/settings/ssh-public-key")
@@ -163,86 +28,3 @@ pub async fn fetch_ssh_public_key() -> Result<String, ServerFnError> {
.unwrap_or("")
.to_string())
}
#[server]
pub async fn delete_repository(repo_id: String) -> Result<(), ServerFnError> {
let resp = super::agent_client::agent_request(
reqwest::Method::DELETE,
&format!("/api/v1/repositories/{repo_id}"),
)
.await?
.send()
.await
.map_err(|e| ServerFnError::new(e.to_string()))?;
if !resp.status().is_success() {
let body = resp.text().await.unwrap_or_default();
return Err(ServerFnError::new(format!(
"Failed to delete repository: {body}"
)));
}
Ok(())
}
#[server]
pub async fn trigger_repo_scan(repo_id: String) -> Result<(), ServerFnError> {
super::agent_client::agent_request(
reqwest::Method::POST,
&format!("/api/v1/repositories/{repo_id}/scan"),
)
.await?
.send()
.await
.map_err(|e| ServerFnError::new(e.to_string()))?;
Ok(())
}
#[derive(Debug, Clone, Serialize, Deserialize, Default)]
pub struct WebhookConfigResponse {
pub webhook_secret: Option<String>,
pub tracker_type: String,
}
#[server]
pub async fn fetch_webhook_config(repo_id: String) -> Result<WebhookConfigResponse, ServerFnError> {
let resp =
super::agent_client::agent_get(&format!("/api/v1/repositories/{repo_id}/webhook-config"))
.await?
.send()
.await
.map_err(|e| ServerFnError::new(e.to_string()))?;
let body: WebhookConfigResponse = resp
.json()
.await
.map_err(|e| ServerFnError::new(e.to_string()))?;
Ok(body)
}
/// Check if a repository has any running scans
#[server]
pub async fn check_repo_scanning(repo_id: String) -> Result<bool, ServerFnError> {
let resp = super::agent_client::agent_get("/api/v1/scan-runs?page=1&limit=1")
.await?
.send()
.await
.map_err(|e| ServerFnError::new(e.to_string()))?;
let body: serde_json::Value = resp
.json()
.await
.map_err(|e| ServerFnError::new(e.to_string()))?;
// Check if the most recent scan for this repo is still running
if let Some(scans) = body.get("data").and_then(|d| d.as_array()) {
for scan in scans {
let scan_repo = scan.get("repo_id").and_then(|v| v.as_str()).unwrap_or("");
let status = scan.get("status").and_then(|v| v.as_str()).unwrap_or("");
if scan_repo == repo_id && status == "running" {
return Ok(true);
}
}
}
Ok(false)
}
@@ -1,3 +1,4 @@
use axum::extract::DefaultBodyLimit;
use axum::routing::{get, post};
use axum::{middleware, Extension};
use dioxus::prelude::*;
@@ -66,6 +67,9 @@ pub fn server_start(app: fn() -> Element) -> Result<(), DashboardError> {
// Webhook proxy: forward to agent (no auth required)
.route("/webhook/{platform}/{repo_id}", post(webhook_proxy))
.serve_dioxus_application(ServeConfig::new(), app)
// Allow large artifact uploads through the upload server function
// (PLC .projectarchive, firmware, mobile) — default is 2 MiB.
.layer(DefaultBodyLimit::max(512 * 1024 * 1024))
.layer(Extension(PendingOAuthStore::default()))
.layer(middleware::from_fn(require_auth))
.layer(Extension(server_state))
+28 -6
View File
@@ -2,11 +2,11 @@ use dioxus::prelude::*;
use crate::app::Route;
use crate::components::page_header::PageHeader;
use crate::infrastructure::repositories::fetch_repositories;
use crate::infrastructure::onboarding::fetch_targets;
#[component]
pub fn ChatIndexPage() -> Element {
let repos = use_resource(|| async { fetch_repositories(1).await.ok() });
let repos = use_resource(|| async { fetch_targets().await.ok() });
rsx! {
PageHeader {
@@ -28,10 +28,32 @@ pub fn ChatIndexPage() -> Element {
div { class: "graph-index-grid",
for repo in repo_list {
{
let repo_id = repo.id.map(|id| id.to_hex()).unwrap_or_default();
let name = repo.name.clone();
let url = repo.git_url.clone();
let branch = repo.default_branch.clone();
let repo_id = repo.get("_id").and_then(|o| o.get("$oid")).and_then(|s| s.as_str()).unwrap_or_default().to_string();
let name = repo.get("name").and_then(|n| n.as_str()).unwrap_or_default().to_string();
let url = repo
.get("artifacts")
.and_then(|a| a.as_array())
.and_then(|arr| {
arr.iter().find(|a| {
a.get("kind").and_then(|k| k.as_str()) == Some("git_repo")
})
})
.and_then(|a| a.get("source_ref"))
.and_then(|s| s.as_str())
.unwrap_or_default()
.to_string();
let branch = repo
.get("artifacts")
.and_then(|a| a.as_array())
.and_then(|arr| {
arr.iter().find_map(|a| {
a.get("git")
.and_then(|g| g.get("default_branch"))
.and_then(|b| b.as_str())
})
})
.unwrap_or("main")
.to_string();
rsx! {
Link {
to: Route::ChatPage { repo_id },
+5 -5
View File
@@ -20,7 +20,7 @@ pub fn FindingsPage() -> Element {
let mut selected_ids = use_signal(Vec::<String>::new);
let repos = use_resource(|| async {
crate::infrastructure::repositories::fetch_repositories(1)
crate::infrastructure::onboarding::fetch_targets()
.await
.ok()
});
@@ -86,14 +86,14 @@ pub fn FindingsPage() -> Element {
}
select {
onchange: move |e| { repo_filter.set(e.value()); page.set(1); },
option { value: "", "All Repositories" }
option { value: "", "All Targets" }
{
match &*repos.read() {
Some(Some(resp)) => rsx! {
for repo in &resp.data {
for t in &resp.data {
{
let id = repo.id.as_ref().map(|id| id.to_hex()).unwrap_or_default();
let name = repo.name.clone();
let id = t.get("_id").and_then(|o| o.get("$oid")).and_then(|s| s.as_str()).unwrap_or_default().to_string();
let name = t.get("name").and_then(|n| n.as_str()).unwrap_or_default().to_string();
rsx! {
option { value: "{id}", "{name}" }
}
+29 -25
View File
@@ -2,11 +2,11 @@ use dioxus::prelude::*;
use crate::app::Route;
use crate::components::page_header::PageHeader;
use crate::infrastructure::repositories::fetch_repositories;
use crate::infrastructure::onboarding::fetch_targets;
#[component]
pub fn GraphIndexPage() -> Element {
let repos = use_resource(|| async { fetch_repositories(1).await.ok() });
let repos = use_resource(|| async { fetch_targets().await.ok() });
rsx! {
PageHeader {
@@ -28,27 +28,34 @@ pub fn GraphIndexPage() -> Element {
div { class: "graph-index-grid",
for repo in repo_list {
{
let repo_id = repo.id.map(|id| id.to_hex()).unwrap_or_default();
let name = repo.name.clone();
let url = repo.git_url.clone();
let branch = repo.default_branch.clone();
let findings = repo.findings_count;
let repo_id = repo.get("_id").and_then(|o| o.get("$oid")).and_then(|s| s.as_str()).unwrap_or_default().to_string();
let name = repo.get("name").and_then(|n| n.as_str()).unwrap_or_default().to_string();
let url = repo
.get("artifacts")
.and_then(|a| a.as_array())
.and_then(|arr| {
arr.iter().find(|a| {
a.get("kind").and_then(|k| k.as_str()) == Some("git_repo")
})
})
.and_then(|a| a.get("source_ref"))
.and_then(|s| s.as_str())
.unwrap_or_default()
.to_string();
let branch = repo
.get("artifacts")
.and_then(|a| a.as_array())
.and_then(|arr| {
arr.iter().find_map(|a| {
a.get("git")
.and_then(|g| g.get("default_branch"))
.and_then(|b| b.as_str())
})
})
.unwrap_or("main")
.to_string();
let findings = repo.get("findings_count").and_then(|n| n.as_u64()).unwrap_or(0);
let findings_label = if findings != 1 { format!("{findings} findings") } else { "1 finding".to_string() };
let updated = {
let now = chrono::Utc::now();
let diff = now.signed_duration_since(repo.updated_at);
if diff.num_minutes() < 1 {
"just now".to_string()
} else if diff.num_hours() < 1 {
format!("{}m ago", diff.num_minutes())
} else if diff.num_days() < 1 {
format!("{}h ago", diff.num_hours())
} else if diff.num_days() < 30 {
format!("{}d ago", diff.num_days())
} else {
repo.updated_at.format("%Y-%m-%d").to_string()
}
};
rsx! {
Link {
to: Route::GraphExplorerPage { repo_id },
@@ -67,9 +74,6 @@ pub fn GraphIndexPage() -> Element {
span { class: "graph-repo-card-tag graph-repo-card-tag-findings",
"{findings_label}"
}
span { class: "graph-repo-card-tag",
"Updated {updated}"
}
}
}
}
@@ -0,0 +1,271 @@
use dioxus::prelude::*;
use dioxus_free_icons::icons::bs_icons::*;
use dioxus_free_icons::Icon;
use crate::components::page_header::PageHeader;
use crate::components::toast::{ToastType, Toasts};
use crate::infrastructure::mcp_tokens::{
create_mcp_token, fetch_mcp_tokens, revoke_mcp_token, CreateMcpTokenResponse,
};
#[component]
pub fn McpTokensPage() -> Element {
let mut tokens = use_resource(|| async { fetch_mcp_tokens().await.ok() });
let mut toasts = use_context::<Toasts>();
// Create-form state
let mut show_form = use_signal(|| false);
let mut new_name = use_signal(String::new);
let mut submitting = use_signal(|| false);
// After creation, the raw token shows once in a banner
let mut just_created: Signal<Option<CreateMcpTokenResponse>> = use_signal(|| None);
// Revoke confirmation: (id, name)
let mut confirm_revoke: Signal<Option<(String, String)>> = use_signal(|| None);
rsx! {
PageHeader {
title: "MCP Tokens",
description: "Static bearer tokens for the MCP server. Use in your LLM client (Claude Desktop, Cursor, etc.) — one token per tool/device.",
}
// ── Just-created banner ────────────────────────────────────
if let Some(resp) = just_created() {
div { class: "card mb-4", style: "border: 1px solid var(--accent-warning); background: var(--bg-warning-subtle);",
div { class: "card-header", style: "color: var(--accent-warning);",
Icon { icon: BsExclamationTriangle, width: 14, height: 14 }
" Copy this token now — it won't be shown again"
}
div { style: "padding: 1rem;",
p { style: "margin-bottom: 0.5rem; color: var(--text-secondary);",
"Token for "
strong { "{resp.view.name}" }
}
div { class: "copyable", style: "background: var(--bg-secondary); padding: 0.75rem; border-radius: 4px;",
code { style: "font-family: var(--font-mono); word-break: break-all; flex: 1;", "{resp.token}" }
crate::components::copy_button::CopyButton { value: resp.token.clone(), small: false }
}
div { style: "margin-top: 0.75rem;",
button {
class: "btn btn-sm btn-ghost",
onclick: move |_| just_created.set(None),
"Dismiss"
}
}
}
}
}
// ── Create form ────────────────────────────────────────────
div { class: "mb-4",
button {
class: "btn btn-primary",
onclick: move |_| {
show_form.set(!show_form());
new_name.set(String::new());
},
if show_form() { "Cancel" } else {
Icon { icon: BsPlusLg, width: 14, height: 14 }
" Create Token"
}
}
}
if show_form() {
div { class: "card mb-4",
div { class: "card-header", "New MCP Token" }
div { style: "padding: 1rem;",
div { class: "form-group",
label { "Name" }
input {
r#type: "text",
placeholder: "Claude Desktop on my laptop",
value: "{new_name}",
oninput: move |e| new_name.set(e.value()),
}
small { style: "color: var(--text-secondary);", "A label so you can identify this token in the list. Not visible to LLM clients." }
}
div { style: "margin-top: 1rem;",
button {
class: "btn btn-primary",
disabled: submitting() || new_name().trim().is_empty(),
onclick: move |_| {
let name = new_name().trim().to_string();
if name.is_empty() {
return;
}
spawn(async move {
submitting.set(true);
match create_mcp_token(name).await {
Ok(resp) => {
toasts.push(ToastType::Success, "Token created. Copy it now — it won't be shown again.");
just_created.set(Some(resp));
show_form.set(false);
new_name.set(String::new());
tokens.restart();
}
Err(e) => {
toasts.push(ToastType::Error, format!("Failed to create token: {e}"));
}
}
submitting.set(false);
});
},
if submitting() { "Creating..." } else { "Create" }
}
}
}
}
}
// ── Tokens list ────────────────────────────────────────────
match &*tokens.read() {
Some(Some(resp)) => {
if resp.data.is_empty() {
rsx! {
div { class: "card",
p { style: "padding: 1rem; color: var(--text-secondary);", "No MCP tokens yet. Create one to start using the MCP server from an LLM client." }
}
}
} else {
rsx! {
div { class: "mcp-cards-grid",
for token in resp.data.iter() {
{
let id = token.id.clone();
let name = token.name.clone();
let prefix = token.token_prefix.clone();
let created_str = format_timestamp(&token.created_at);
let last_used_str = token
.last_used_at
.as_ref()
.map(format_timestamp)
.unwrap_or_else(|| "never".to_string());
let revoked = token.revoked;
rsx! {
div { class: "mcp-card", style: if revoked { "opacity: 0.55;" } else { "" },
div { class: "mcp-card-header",
div { class: "mcp-card-title",
Icon { icon: BsKey, width: 14, height: 14 }
h3 { "{name}" }
if revoked {
span { class: "mcp-card-status stopped", "revoked" }
}
}
if !revoked {
button {
class: "btn btn-sm btn-ghost btn-ghost-danger",
title: "Revoke token",
onclick: {
let id = id.clone();
let name = name.clone();
move |_| {
confirm_revoke.set(Some((id.clone(), name.clone())));
}
},
Icon { icon: BsTrash, width: 14, height: 14 }
}
}
}
div { class: "mcp-card-details",
div { class: "mcp-detail-row",
Icon { icon: BsKey, width: 13, height: 13 }
span { class: "mcp-detail-label", "Prefix" }
code { class: "mcp-detail-value", "{prefix}…" }
}
div { class: "mcp-detail-row",
Icon { icon: BsCalendar, width: 13, height: 13 }
span { class: "mcp-detail-label", "Created" }
span { class: "mcp-detail-value", "{created_str}" }
}
div { class: "mcp-detail-row",
Icon { icon: BsClockHistory, width: 13, height: 13 }
span { class: "mcp-detail-label", "Last used" }
span { class: "mcp-detail-value", "{last_used_str}" }
}
}
}
}
}
}
}
}
}
}
Some(None) => rsx! {
div { class: "card",
p { style: "padding: 1rem; color: var(--accent-danger);", "Failed to load MCP tokens." }
}
},
None => rsx! {
div { class: "card",
p { style: "padding: 1rem; color: var(--text-secondary);", "Loading..." }
}
},
}
// ── Revoke confirmation modal ──────────────────────────────
if let Some((id, name)) = confirm_revoke() {
div { class: "modal-overlay",
div { class: "modal",
h3 { "Revoke token?" }
p {
"The token "
strong { "{name}" }
" will stop working immediately. This cannot be undone. Any LLM client using it will start getting 401."
}
div { style: "display: flex; gap: 0.5rem; margin-top: 1rem; justify-content: flex-end;",
button {
class: "btn btn-ghost",
onclick: move |_| confirm_revoke.set(None),
"Cancel"
}
button {
class: "btn btn-danger",
onclick: {
let id = id.clone();
move |_| {
let id = id.clone();
spawn(async move {
match revoke_mcp_token(id).await {
Ok(()) => {
toasts.push(ToastType::Success, "Token revoked");
tokens.restart();
}
Err(e) => {
toasts.push(ToastType::Error, format!("Failed to revoke: {e}"));
}
}
confirm_revoke.set(None);
});
}
},
"Revoke"
}
}
}
}
}
}
}
/// Best-effort timestamp formatter. The agent serializes BSON DateTime
/// as `{"$date":{"$numberLong":"..."}}` in extended JSON. We accept
/// that shape, plain ISO strings, or anything else (best-effort).
fn format_timestamp(v: &serde_json::Value) -> String {
if let Some(s) = v.as_str() {
return s.to_string();
}
if let Some(ms) = v
.get("$date")
.and_then(|d| d.get("$numberLong"))
.and_then(|s| s.as_str())
.and_then(|s| s.parse::<i64>().ok())
{
return chrono::DateTime::<chrono::Utc>::from_timestamp_millis(ms)
.map(|d| d.format("%Y-%m-%d %H:%M").to_string())
.unwrap_or_else(|| ms.to_string());
}
"".to_string()
}
+6 -2
View File
@@ -11,11 +11,13 @@ pub mod graph_index;
pub mod impact_analysis;
pub mod issues;
pub mod mcp_servers;
pub mod mcp_tokens;
pub mod onboarding;
pub mod overview;
pub mod pentest_dashboard;
pub mod pentest_session;
pub mod repositories;
pub mod sbom;
pub mod targets;
pub use chat::ChatPage;
pub use chat_index::ChatIndexPage;
@@ -30,8 +32,10 @@ pub use graph_index::GraphIndexPage;
pub use impact_analysis::ImpactAnalysisPage;
pub use issues::IssuesPage;
pub use mcp_servers::McpServersPage;
pub use mcp_tokens::McpTokensPage;
pub use onboarding::OnboardingPage;
pub use overview::OverviewPage;
pub use pentest_dashboard::PentestDashboardPage;
pub use pentest_session::PentestSessionPage;
pub use repositories::RepositoriesPage;
pub use sbom::SbomPage;
pub use targets::TargetsPage;
@@ -0,0 +1,656 @@
use dioxus::prelude::*;
use crate::components::page_header::PageHeader;
use crate::infrastructure::onboarding::{
create_target, detect_target, enable_target_scans, fetch_applicable_scans, trigger_target_scan,
upload_target_artifact, validate_artifact_ref, validate_target_name, ArtifactInputDto,
};
/// (value, label, one-line description) for the 9 target families.
const TARGET_TYPES: &[(&str, &str, &str)] = &[
("web_app", "Web Application", "Front end + server"),
("backend_service", "Backend / API", "REST, GraphQL, gRPC"),
("desktop_app", "Desktop App", "Windows / macOS / Linux"),
("android_app", "Android App", "APK / AAB"),
("ios_app", "iOS App", "IPA"),
(
"firmware_bare_metal",
"Firmware — bare metal",
"No operating system",
),
("firmware_rtos", "Firmware — RTOS", "Zephyr, FreeRTOS, ..."),
(
"embedded_linux_yocto",
"Embedded Linux / Yocto",
"BSP + image",
),
("plc_sps", "PLC / SPS", "IEC 61131-3"),
];
/// (value, label) for the artifact kinds a user can attach.
const ARTIFACT_KINDS: &[(&str, &str)] = &[
("git_repo", "Git repository"),
("source_archive", "Source archive (zip)"),
("firmware_image", "Firmware image"),
("mobile_package", "Mobile package (APK/IPA)"),
("container_image", "Container image"),
("live_url", "Live URL"),
("plc_project", "PLC project"),
("plaintext_description", "Description (text)"),
];
const STEP_LABELS: &[&str] = &["Target type", "Artifacts", "Review", "Done"];
/// Artifact kinds provided as an uploaded file (rather than a URL/text ref).
fn is_file_kind(kind: &str) -> bool {
matches!(
kind,
"plc_project" | "firmware_image" | "source_archive" | "mobile_package"
)
}
/// A file artifact staged in the wizard, uploaded after the target is created.
#[derive(Clone, PartialEq)]
struct PendingFile {
kind: String,
plc_format: Option<String>,
filename: String,
bytes: Vec<u8>,
}
/// One row in the applicable-scans list on the success step.
#[component]
fn ScanRow(scan: serde_json::Value) -> Element {
let name = scan
.get("scan")
.and_then(|v| v.as_str())
.unwrap_or("?")
.to_string();
let rationale = scan
.get("rationale")
.and_then(|v| v.as_str())
.unwrap_or("")
.to_string();
let blocked = scan
.get("blocked_reason")
.and_then(|v| v.as_str())
.map(String::from);
let default_on = scan
.get("default_on")
.and_then(|v| v.as_bool())
.unwrap_or(false);
let badge_class = if blocked.is_some() {
"badge badge-info"
} else if default_on {
"badge badge-success"
} else {
"badge"
};
rsx! {
div { style: "display: flex; gap: 8px; align-items: center; padding: 6px 0;",
span { class: "{badge_class}", "{name}" }
span { style: "opacity: 0.8;", "{rationale}" }
if let Some(b) = blocked {
span { style: "opacity: 0.6; font-style: italic;", "— {b}" }
}
}
}
}
fn kind_label(kind: &str) -> &str {
ARTIFACT_KINDS
.iter()
.find(|(v, _)| *v == kind)
.map(|(_, l)| *l)
.unwrap_or(kind)
}
fn type_label(value: &str) -> &str {
TARGET_TYPES
.iter()
.find(|(v, _, _)| *v == value)
.map(|(_, l, _)| *l)
.unwrap_or(value)
}
#[component]
pub fn OnboardingPage() -> Element {
let mut step = use_signal(|| 0usize);
let mut name = use_signal(String::new);
let mut target_type = use_signal(String::new);
let mut description = use_signal(String::new);
let mut artifacts = use_signal(Vec::<ArtifactInputDto>::new);
// "Add artifact" mini-form.
let mut new_kind = use_signal(|| "git_repo".to_string());
let mut new_source = use_signal(String::new);
let mut new_branch = use_signal(|| "main".to_string());
// File-upload artifacts (PLC project, firmware image, ...).
let mut new_plc_format = use_signal(|| "plcopen_xml".to_string());
let mut new_file = use_signal(|| Option::<(String, Vec<u8>)>::None);
let mut pending_files = use_signal(Vec::<PendingFile>::new);
// Create + result state.
let mut creating = use_signal(|| false);
let mut error = use_signal(|| Option::<String>::None);
let mut scans = use_signal(Vec::<serde_json::Value>::new);
let mut suggested = use_signal(|| Option::<String>::None);
let mut created_id = use_signal(|| Option::<String>::None);
let mut scan_msg = use_signal(|| Option::<String>::None);
// Opt-in scans (default-off but unblocked) the user ticks to enable before
// running — stored as serde scan-type names (lowercase, no underscores).
let mut enabled_extra = use_signal(Vec::<String>::new);
let step_now = step();
let name_error = validate_target_name(&name());
let can_advance_type = name_error.is_none() && !target_type().trim().is_empty();
let has_artifacts = !artifacts().is_empty() || !pending_files().is_empty();
// Opt-in scans: applicable + unblocked, but default-off (e.g. the ICS probe).
// The user ticks these to enable them before the first run. Each entry is
// (display name for the label, serde scan-type name for the enable call —
// lowercase, no underscores, matching ScanType's rename_all = "lowercase").
let optin_scans: Vec<(String, String)> = scans()
.iter()
.filter_map(|s| {
let unblocked = s.get("blocked_reason").and_then(|v| v.as_str()).is_none();
let default_on = s
.get("default_on")
.and_then(|v| v.as_bool())
.unwrap_or(false);
if unblocked && !default_on {
let display = s.get("scan").and_then(|v| v.as_str())?.to_string();
let serde_name = display.replace('_', "");
Some((display, serde_name))
} else {
None
}
})
.collect();
// Live validation of the artifact reference being typed (empty = no error yet).
let new_source_error = if new_source().is_empty() {
None
} else {
validate_artifact_ref(&new_kind(), &new_source())
};
rsx! {
PageHeader {
title: "Onboard a target",
description: "Add a target, attach its artifacts, and see which scans apply.",
}
// Stepper.
div { class: "wizard-steps",
for (i, label) in STEP_LABELS.iter().enumerate() {
div {
class: if i == step_now { "wizard-step wizard-step-active" } else { "wizard-step" },
span { class: "wizard-step-dot", "{i + 1}" }
span { class: "wizard-step-label", "{label}" }
}
}
}
if let Some(err) = error() {
div { class: "card", style: "border-color: var(--danger, #d33); margin-bottom: 12px;",
div { class: "card-header", "Error" }
div { style: "padding: 12px;", "{err}" }
}
}
div { class: "card",
// ---- Step 0: target type + name ----
if step_now == 0 {
div { class: "card-header", "What kind of software is this?" }
div { style: "padding: 16px;",
div { class: "form-group",
label { "Name" }
input {
r#type: "text",
placeholder: "acme-web",
value: "{name}",
oninput: move |e| name.set(e.value()),
}
if !name().is_empty() {
if let Some(err) = name_error.clone() {
div { style: "color: var(--danger, #d33); font-size: 0.85em; margin-top: 4px;", "{err}" }
}
}
}
div {
style: "display: grid; grid-template-columns: repeat(auto-fill, minmax(200px, 1fr)); gap: 12px; margin-top: 12px;",
for (value, tlabel, tdesc) in TARGET_TYPES.iter().copied() {
div {
class: "card",
style: if target_type() == value {
"padding: 12px; cursor: pointer; border: 2px solid var(--accent, #3b82f6);"
} else {
"padding: 12px; cursor: pointer;"
},
onclick: move |_| target_type.set(value.to_string()),
div { style: "font-weight: 600;", "{tlabel}" }
div { style: "font-size: 0.85em; opacity: 0.7;", "{tdesc}" }
}
}
}
}
}
// ---- Step 1: artifacts ----
if step_now == 1 {
div { class: "card-header", "Attach artifacts" }
if target_type() == "plc_sps" {
div {
style: "margin: 12px 16px 0; padding: 12px 14px; border-left: 3px solid var(--accent, #3b82f6); background: var(--surface-2, rgba(59,130,246,0.08)); font-size: 0.88em; line-height: 1.55;",
div { style: "font-weight: 600; margin-bottom: 4px;", "CODESYS / PLC projects" }
"Attach a "
b { "PLC project" }
" (PLCopen XML / ST, or a .projectarchive), or a "
b { "Git repository" }
" of exported source — every scan is then just a pull."
ul { style: "margin: 6px 0 0; padding-left: 18px;",
li {
b { "Control-logic SAST" }
" — commit "
b { "PLCopen XML exports" }
" (Project → Export PLCopenXML) or raw .st; ST and graphical FBD/LD are both analyzed."
}
li {
b { "Library + runtime SBOM" }
" — include the "
b { ".projectarchive" }
"; PLCopen XML alone carries no libraries."
}
li {
"Avoid committing only the binary "
code { ".project" }
" — it can't be parsed and doesn't diff."
}
}
}
}
div { style: "padding: 16px;",
div { style: "display: flex; gap: 8px; flex-wrap: wrap; align-items: flex-end;",
div { class: "form-group", style: "margin: 0;",
label { "Kind" }
select {
value: "{new_kind}",
oninput: move |e| new_kind.set(e.value()),
for (value, klabel) in ARTIFACT_KINDS.iter().copied() {
option { value: "{value}", "{klabel}" }
}
}
}
if is_file_kind(&new_kind()) {
div { class: "form-group", style: "margin: 0; flex: 1; min-width: 240px;",
label { "File" }
input {
r#type: "file",
onchange: move |evt| {
let Some(file) = evt.files().into_iter().next() else { return; };
let name = file.name();
// Auto-detect the PLC format from the file extension.
let lname = name.to_ascii_lowercase();
if lname.ends_with(".projectarchive") || lname.ends_with(".project") {
new_plc_format.set("project_archive".to_string());
} else if lname.ends_with(".xml") || lname.ends_with(".plcopen") {
new_plc_format.set("plcopen_xml".to_string());
} else if lname.ends_with(".st") || lname.ends_with(".exp") || lname.ends_with(".scl") {
new_plc_format.set("structured_text".to_string());
}
spawn(async move {
if let Ok(bytes) = file.read_bytes().await {
new_file.set(Some((name, bytes.to_vec())));
}
});
},
}
}
if new_kind() == "plc_project" {
div { class: "form-group", style: "margin: 0;",
label { "Format" }
select {
value: "{new_plc_format}",
oninput: move |e| new_plc_format.set(e.value()),
option {
value: "plcopen_xml",
selected: new_plc_format() == "plcopen_xml",
"PLCopen XML",
}
option {
value: "structured_text",
selected: new_plc_format() == "structured_text",
"Structured Text",
}
option {
value: "project_archive",
selected: new_plc_format() == "project_archive",
"Project archive (.projectarchive)",
}
}
}
}
button {
class: "btn btn-secondary",
disabled: new_file().is_none(),
onclick: move |_| {
if let Some((fname, data)) = new_file() {
let kind = new_kind();
let plc_format = if kind == "plc_project" {
Some(new_plc_format())
} else {
None
};
pending_files.write().push(PendingFile {
kind,
plc_format,
filename: fname,
bytes: data,
});
new_file.set(None);
}
},
"+ Add file"
}
} else {
div { class: "form-group", style: "margin: 0; flex: 1; min-width: 240px;",
label { "Reference (URL / path / text)" }
input {
r#type: "text",
placeholder: "https://git.example.com/acme.git",
value: "{new_source}",
oninput: move |e| new_source.set(e.value()),
}
}
if new_kind() == "git_repo" {
div { class: "form-group", style: "margin: 0;",
label { "Branch" }
input {
r#type: "text",
value: "{new_branch}",
oninput: move |e| new_branch.set(e.value()),
}
}
}
button {
class: "btn btn-secondary",
disabled: new_source().trim().is_empty() || new_source_error.is_some(),
onclick: move |_| {
let kind = new_kind();
if !new_source().trim().is_empty()
&& validate_artifact_ref(&kind, &new_source()).is_none()
{
let branch = if kind == "git_repo" { Some(new_branch()) } else { None };
artifacts.write().push(ArtifactInputDto {
kind,
source_ref: new_source(),
branch,
plc_format: None,
});
new_source.set(String::new());
}
},
"+ Add"
}
}
}
if is_file_kind(&new_kind()) {
if let Some((fname, data)) = new_file() {
div { style: "font-size: 0.85em; opacity: 0.7; margin-top: 6px;",
"Selected: {fname} ({data.len()} bytes)"
}
}
} else if let Some(err) = new_source_error.clone() {
div { style: "color: var(--danger, #d33); font-size: 0.85em; margin-top: 6px;", "{err}" }
}
// Staged file artifacts (uploaded after the target is created).
for (i, pf) in pending_files().iter().enumerate() {
div {
style: "display: flex; justify-content: space-between; align-items: center; padding: 8px 12px; border: 1px solid var(--border, #333); border-radius: 6px; margin-top: 6px;",
span {
span { style: "opacity: 0.7;", "{kind_label(&pf.kind)} (file): " }
"{pf.filename} ({pf.bytes.len()} bytes)"
}
button {
class: "btn btn-ghost-danger btn-sm",
onclick: move |_| { pending_files.write().remove(i); },
"Remove"
}
}
}
div { style: "margin-top: 16px;",
if has_artifacts {
for (i, a) in artifacts().iter().enumerate() {
div {
style: "display: flex; justify-content: space-between; align-items: center; padding: 8px 12px; border: 1px solid var(--border, #333); border-radius: 6px; margin-bottom: 6px;",
span {
span { style: "opacity: 0.7;", "{kind_label(&a.kind)}: " }
"{a.source_ref}"
}
button {
class: "btn btn-ghost-danger btn-sm",
onclick: move |_| { artifacts.write().remove(i); },
"Remove"
}
}
}
} else {
div { style: "opacity: 0.6;", "No artifacts yet. Add at least one." }
}
}
}
}
// ---- Step 2: review + create ----
if step_now == 2 {
div { class: "card-header", "Review" }
div { style: "padding: 16px;",
div { class: "wizard-summary",
div { strong { "Name: " } "{name()}" }
div { strong { "Type: " } "{type_label(&target_type())}" }
div { strong { "Artifacts:" } }
ul {
for a in artifacts() {
li { "{kind_label(&a.kind)}: {a.source_ref}" }
}
}
}
div { style: "margin-top: 12px; opacity: 0.7; font-size: 0.9em;",
"The applicable scans (SAST / DAST / firmware / PLC) are shown after the target is created."
}
}
}
// ---- Step 3: created ----
if step_now == 3 {
div { class: "card-header", "Target onboarded" }
div { style: "padding: 16px;",
p {
strong { "{name()}" }
" was created."
if let Some(s) = suggested() {
span { " Suggested type from detection: " strong { "{type_label(&s)}" } "." }
}
}
h4 { style: "margin-top: 16px;", "Applicable scans" }
if scans().is_empty() {
div { style: "opacity: 0.6;", "No scans available (no code / URL / firmware artifact present)." }
} else {
for s in scans() {
ScanRow { scan: s }
}
}
if !optin_scans.is_empty() {
div { style: "margin-top: 12px; padding: 10px; border: 1px dashed var(--border, #ccc); border-radius: 6px;",
div { style: "font-weight: 600; margin-bottom: 6px;", "Enable opt-in scans" }
div { style: "opacity: 0.7; font-size: 0.85em; margin-bottom: 8px;",
"These are applicable but off by default (they touch a live device). Tick to enable before running."
}
for pair in optin_scans.clone() {
{
let (display, serde_name) = pair;
let cb_name = serde_name.clone();
rsx! {
label {
style: "display: flex; gap: 6px; align-items: center; margin-top: 4px;",
input {
r#type: "checkbox",
checked: enabled_extra().contains(&serde_name),
onchange: move |_| {
let mut v = enabled_extra();
if let Some(p) = v.iter().position(|x| x == &cb_name) {
v.remove(p);
} else {
v.push(cb_name.clone());
}
enabled_extra.set(v);
},
}
"Enable {display}"
}
}
}
}
}
}
if let Some(msg) = scan_msg() {
div { style: "margin-top: 8px; color: var(--success, #2a2);", "{msg}" }
}
div { style: "margin-top: 16px; display: flex; gap: 8px;",
button {
class: "btn btn-primary",
onclick: move |_| {
if let Some(id) = created_id() {
let extra = enabled_extra();
scan_msg.set(Some("Scan triggered...".to_string()));
spawn(async move {
// Persist any ticked opt-in scans first, so the
// agent's build_scan_plan includes them this run.
if !extra.is_empty() {
if let Err(e) =
enable_target_scans(id.clone(), extra).await
{
scan_msg.set(Some(format!(
"Failed to enable opt-in scans: {e}"
)));
return;
}
}
match trigger_target_scan(id).await {
Ok(_) => scan_msg.set(Some(
"Scan started — findings will appear as it runs.".to_string(),
)),
Err(e) => scan_msg.set(Some(format!("Failed to start scan: {e}"))),
}
});
}
},
"Run scan"
}
button {
class: "btn btn-secondary",
onclick: move |_| {
step.set(0);
name.set(String::new());
target_type.set(String::new());
description.set(String::new());
artifacts.write().clear();
pending_files.write().clear();
new_file.set(None);
scans.write().clear();
suggested.set(None);
created_id.set(None);
scan_msg.set(None);
error.set(None);
},
"Onboard another"
}
}
}
}
}
// ---- Footer navigation ----
if step_now < 3 {
div { style: "display: flex; justify-content: space-between; margin-top: 16px;",
button {
class: "btn btn-back",
disabled: step_now == 0,
onclick: move |_| { if step() > 0 { step.set(step() - 1); } },
"Back"
}
if step_now < 2 {
button {
class: "btn btn-primary",
disabled: (step_now == 0 && !can_advance_type) || (step_now == 1 && !has_artifacts),
onclick: move |_| step.set(step() + 1),
"Next"
}
} else {
button {
class: "btn btn-primary",
disabled: creating(),
onclick: move |_| {
let n = name();
let tt = target_type();
let desc = description();
let arts = artifacts();
let files = pending_files();
let d = if desc.trim().is_empty() { None } else { Some(desc) };
creating.set(true);
error.set(None);
spawn(async move {
match create_target(n, tt, d, arts).await {
Ok(resp) => {
let id = resp
.data
.get("_id")
.and_then(|o| o.get("$oid"))
.and_then(|s| s.as_str())
.map(String::from);
if let Some(id) = id {
created_id.set(Some(id.clone()));
// Upload staged file artifacts now that the target exists.
for pf in files {
let fname = pf.filename.clone();
if let Err(e) = upload_target_artifact(
id.clone(),
pf.kind,
pf.plc_format,
pf.filename,
pf.bytes,
)
.await
{
error.set(Some(format!(
"Upload failed for {fname}: {e}"
)));
}
}
if let Ok(sc) = fetch_applicable_scans(id.clone()).await {
scans.set(sc.data.scans);
}
if let Ok(det) = detect_target(id).await {
suggested.set(
det.data
.get("classification")
.and_then(|c| c.get("suggested"))
.and_then(|s| s.as_str())
.map(String::from),
);
}
}
step.set(3);
}
Err(e) => error.set(Some(e.to_string())),
}
creating.set(false);
});
},
if creating() { "Creating..." } else { "Create target" }
}
}
}
}
}
}
+4 -4
View File
@@ -6,7 +6,7 @@ use crate::app::Route;
use crate::components::page_header::PageHeader;
use crate::components::stat_card::StatCard;
use crate::infrastructure::mcp::fetch_mcp_servers;
use crate::infrastructure::repositories::fetch_repositories;
use crate::infrastructure::onboarding::fetch_targets;
#[cfg(feature = "server")]
use crate::infrastructure::stats::fetch_overview_stats;
@@ -26,7 +26,7 @@ pub fn OverviewPage() -> Element {
}
});
let repos = use_resource(|| async { fetch_repositories(1).await.ok() });
let repos = use_resource(|| async { fetch_targets().await.ok() });
let mcp_servers = use_resource(|| async { fetch_mcp_servers().await.ok() });
rsx! {
@@ -94,8 +94,8 @@ pub fn OverviewPage() -> Element {
style: "display: grid; grid-template-columns: repeat(3, 1fr); gap: 1rem; padding: 1rem;",
for repo in repo_list {
{
let repo_id = repo.id.map(|id| id.to_hex()).unwrap_or_default();
let name = repo.name.clone();
let repo_id = repo.get("_id").and_then(|o| o.get("$oid")).and_then(|s| s.as_str()).unwrap_or_default().to_string();
let name = repo.get("name").and_then(|n| n.as_str()).unwrap_or_default().to_string();
rsx! {
Link {
to: Route::ChatPage { repo_id },
@@ -1,657 +0,0 @@
use dioxus::prelude::*;
use dioxus_free_icons::icons::bs_icons::*;
#[allow(unused_imports)]
use dioxus_free_icons::icons::bs_icons::{BsGear, BsPencil};
use dioxus_free_icons::Icon;
use crate::components::page_header::PageHeader;
use crate::components::pagination::Pagination;
use crate::components::toast::{ToastType, Toasts};
use crate::pages::graph_explorer::GraphExplorerInline;
async fn async_sleep_5s() {
#[cfg(feature = "web")]
{
gloo_timers::future::TimeoutFuture::new(5_000).await;
}
#[cfg(not(feature = "web"))]
{
tokio::time::sleep(std::time::Duration::from_secs(5)).await;
}
}
#[component]
pub fn RepositoriesPage() -> Element {
let mut page = use_signal(|| 1u64);
let mut show_add_form = use_signal(|| false);
let mut name = use_signal(String::new);
let mut git_url = use_signal(String::new);
let mut branch = use_signal(|| "main".to_string());
let mut auth_token = use_signal(String::new);
let mut auth_username = use_signal(String::new);
let mut show_auth = use_signal(|| false);
let mut ssh_public_key = use_signal(String::new);
let mut show_tracker = use_signal(|| false);
let mut tracker_type_val = use_signal(String::new);
let mut tracker_owner_val = use_signal(String::new);
let mut tracker_repo_val = use_signal(String::new);
let mut tracker_token_val = use_signal(String::new);
let mut adding = use_signal(|| false);
let mut toasts = use_context::<Toasts>();
let mut confirm_delete = use_signal(|| Option::<(String, String)>::None); // (id, name)
let mut edit_repo_id = use_signal(|| Option::<String>::None);
let mut edit_name = use_signal(String::new);
let mut edit_branch = use_signal(String::new);
let mut edit_tracker_type = use_signal(String::new);
let mut edit_tracker_owner = use_signal(String::new);
let mut edit_tracker_repo = use_signal(String::new);
let mut edit_tracker_token = use_signal(String::new);
let mut edit_saving = use_signal(|| false);
let mut edit_webhook_secret = use_signal(|| Option::<String>::None);
let mut edit_webhook_tracker = use_signal(String::new);
let mut scanning_ids = use_signal(Vec::<String>::new);
let mut graph_repo_id = use_signal(|| Option::<String>::None);
let mut repos = use_resource(move || {
let p = page();
async move {
crate::infrastructure::repositories::fetch_repositories(p)
.await
.ok()
}
});
rsx! {
PageHeader {
title: "Repositories",
description: "Tracked git repositories",
}
div { style: "margin-bottom: 16px;",
button {
class: "btn btn-primary",
onclick: move |_| show_add_form.toggle(),
if show_add_form() { "Cancel" } else { "+ Add Repository" }
}
}
if show_add_form() {
div { class: "card",
div { class: "card-header", "Add Repository" }
div { class: "form-group",
label { "Name" }
input {
r#type: "text",
placeholder: "my-project",
value: "{name}",
oninput: move |e| name.set(e.value()),
}
}
div { class: "form-group",
label { "Git URL" }
input {
r#type: "text",
placeholder: "https://github.com/org/repo.git or git@github.com:org/repo.git",
value: "{git_url}",
oninput: move |e| git_url.set(e.value()),
}
}
div { class: "form-group",
label { "Default Branch" }
input {
r#type: "text",
placeholder: "main",
value: "{branch}",
oninput: move |e| branch.set(e.value()),
}
}
// Private repo auth section
div { style: "margin-top: 8px;",
button {
class: "btn btn-ghost",
style: "font-size: 12px; padding: 4px 8px;",
onclick: move |_| {
let opening = !show_auth();
show_auth.toggle();
if opening {
// Fetch SSH key every time the section opens
ssh_public_key.set(String::new());
spawn(async move {
match crate::infrastructure::repositories::fetch_ssh_public_key().await {
Ok(key) => ssh_public_key.set(key),
Err(_) => ssh_public_key.set("(not available)".to_string()),
}
});
}
},
if show_auth() { "Hide auth options" } else { "Private repository?" }
}
}
if show_auth() {
div { class: "auth-section", style: "margin-top: 12px; padding: 12px; border: 1px solid var(--border-subtle); border-radius: 8px;",
// SSH deploy key display
div { style: "margin-bottom: 12px;",
label { style: "font-size: 12px; color: var(--text-secondary);",
"For SSH URLs: add this deploy key (read-only) to your repository"
}
div {
class: "copyable",
style: "margin-top: 4px; padding: 8px; background: var(--bg-secondary); border-radius: 4px;",
code {
style: "font-size: 11px; word-break: break-all; user-select: all;",
if ssh_public_key().is_empty() {
"Loading..."
} else {
"{ssh_public_key}"
}
}
if !ssh_public_key().is_empty() {
crate::components::copy_button::CopyButton { value: ssh_public_key(), small: true }
}
}
}
// HTTPS auth fields
p { style: "font-size: 12px; color: var(--text-secondary); margin-bottom: 8px;",
"For HTTPS URLs: provide an access token (PAT) or username/password"
}
div { class: "form-group",
label { "Auth Token / Password" }
input {
r#type: "password",
placeholder: "ghp_xxxx or personal access token",
value: "{auth_token}",
oninput: move |e| auth_token.set(e.value()),
}
}
div { class: "form-group",
label { "Username (optional, defaults to x-access-token)" }
input {
r#type: "text",
placeholder: "x-access-token",
value: "{auth_username}",
oninput: move |e| auth_username.set(e.value()),
}
}
}
}
// Issue tracker config section
div { style: "margin-top: 8px;",
button {
class: "btn btn-ghost",
style: "font-size: 12px; padding: 4px 8px;",
onclick: move |_| show_tracker.toggle(),
if show_tracker() { "Hide tracker options" } else { "Issue tracker?" }
}
}
if show_tracker() {
div { class: "auth-section", style: "margin-top: 12px; padding: 12px; border: 1px solid var(--border-subtle); border-radius: 8px;",
p { style: "font-size: 12px; color: var(--text-secondary); margin-bottom: 8px;",
"Configure an issue tracker to auto-create issues from findings"
}
div { class: "form-group",
label { "Tracker Type" }
select {
value: "{tracker_type_val}",
onchange: move |e| tracker_type_val.set(e.value()),
option { value: "", "None" }
option { value: "github", "GitHub" }
option { value: "gitlab", "GitLab" }
option { value: "gitea", "Gitea" }
option { value: "jira", "Jira" }
}
}
div { class: "form-group",
label { "Owner / Namespace" }
input {
r#type: "text",
placeholder: "org-name",
value: "{tracker_owner_val}",
oninput: move |e| tracker_owner_val.set(e.value()),
}
}
div { class: "form-group",
label { "Repository / Project" }
input {
r#type: "text",
placeholder: "repo-name",
value: "{tracker_repo_val}",
oninput: move |e| tracker_repo_val.set(e.value()),
}
}
div { class: "form-group",
label { "Tracker Token (PAT)" }
input {
r#type: "password",
placeholder: "ghp_xxxx / glpat-xxxx",
value: "{tracker_token_val}",
oninput: move |e| tracker_token_val.set(e.value()),
}
}
}
}
button {
class: "btn btn-primary",
disabled: adding(),
onclick: move |_| {
let n = name();
let u = git_url();
let b = branch();
let tok = {
let v = auth_token();
if v.is_empty() { None } else { Some(v) }
};
let usr = {
let v = auth_username();
if v.is_empty() { None } else { Some(v) }
};
let tt = { let v = tracker_type_val(); if v.is_empty() { None } else { Some(v) } };
let t_owner = { let v = tracker_owner_val(); if v.is_empty() { None } else { Some(v) } };
let t_repo = { let v = tracker_repo_val(); if v.is_empty() { None } else { Some(v) } };
let t_tok = { let v = tracker_token_val(); if v.is_empty() { None } else { Some(v) } };
adding.set(true);
spawn(async move {
match crate::infrastructure::repositories::add_repository(n, u, b, tok, usr, tt, t_owner, t_repo, t_tok).await {
Ok(_) => {
toasts.push(ToastType::Success, "Repository added");
repos.restart();
}
Err(e) => toasts.push(ToastType::Error, e.to_string()),
}
adding.set(false);
});
show_add_form.set(false);
show_auth.set(false);
show_tracker.set(false);
name.set(String::new());
git_url.set(String::new());
auth_token.set(String::new());
auth_username.set(String::new());
tracker_type_val.set(String::new());
tracker_owner_val.set(String::new());
tracker_repo_val.set(String::new());
tracker_token_val.set(String::new());
},
if adding() { "Validating..." } else { "Add" }
}
}
}
// ── Delete confirmation dialog ──
if let Some((del_id, del_name)) = confirm_delete() {
div { class: "modal-overlay",
div { class: "modal-dialog",
h3 { "Delete Repository" }
p {
"Are you sure you want to delete "
strong { "{del_name}" }
"?"
}
p { class: "modal-warning",
"This will permanently remove all associated findings, SBOM entries, scan runs, graph data, embeddings, and CVE alerts."
}
div { class: "modal-actions",
button {
class: "btn btn-secondary",
onclick: move |_| confirm_delete.set(None),
"Cancel"
}
button {
class: "btn btn-danger",
onclick: move |_| {
let id = del_id.clone();
let name = del_name.clone();
confirm_delete.set(None);
spawn(async move {
match crate::infrastructure::repositories::delete_repository(id).await {
Ok(_) => {
toasts.push(ToastType::Success, format!("{name} deleted"));
repos.restart();
}
Err(e) => toasts.push(ToastType::Error, e.to_string()),
}
});
},
"Delete"
}
}
}
}
}
// ── Edit repository dialog ──
if let Some(eid) = edit_repo_id() {
div { class: "modal-overlay",
div { class: "modal-dialog",
h3 { "Edit Repository" }
div { class: "form-group",
label { "Name" }
input {
r#type: "text",
value: "{edit_name}",
oninput: move |e| edit_name.set(e.value()),
}
}
div { class: "form-group",
label { "Default Branch" }
input {
r#type: "text",
value: "{edit_branch}",
oninput: move |e| edit_branch.set(e.value()),
}
}
h4 { style: "margin-top: 16px; margin-bottom: 8px; font-size: 14px; color: var(--text-secondary);", "Issue Tracker" }
div { class: "form-group",
label { "Tracker Type" }
select {
value: "{edit_tracker_type}",
onchange: move |e| edit_tracker_type.set(e.value()),
option { value: "", "None" }
option { value: "github", "GitHub" }
option { value: "gitlab", "GitLab" }
option { value: "gitea", "Gitea" }
option { value: "jira", "Jira" }
}
}
div { class: "form-group",
label { "Owner / Namespace" }
input {
r#type: "text",
placeholder: "org-name",
value: "{edit_tracker_owner}",
oninput: move |e| edit_tracker_owner.set(e.value()),
}
}
div { class: "form-group",
label { "Repository / Project" }
input {
r#type: "text",
placeholder: "repo-name",
value: "{edit_tracker_repo}",
oninput: move |e| edit_tracker_repo.set(e.value()),
}
}
div { class: "form-group",
label { "Tracker Token (leave empty to keep existing)" }
input {
r#type: "password",
placeholder: "Enter new token to change",
value: "{edit_tracker_token}",
oninput: move |e| edit_tracker_token.set(e.value()),
}
}
// Webhook configuration section
if let Some(secret) = edit_webhook_secret() {
h4 {
style: "margin-top: 16px; margin-bottom: 8px; font-size: 14px; color: var(--text-secondary);",
"Webhook Configuration"
}
p {
style: "font-size: 12px; color: var(--text-secondary); margin-bottom: 8px;",
"Add this webhook in your repository settings to enable push-triggered scans and PR reviews."
}
div { class: "form-group",
label { "Webhook URL" }
{
#[cfg(feature = "web")]
let origin = web_sys::window()
.and_then(|w: web_sys::Window| w.location().origin().ok())
.unwrap_or_default();
#[cfg(not(feature = "web"))]
let origin = String::new();
let webhook_url = format!("{origin}/webhook/{}/{eid}", edit_webhook_tracker());
rsx! {
div { class: "copyable",
input {
r#type: "text",
readonly: true,
style: "font-family: monospace; font-size: 12px; flex: 1;",
value: "{webhook_url}",
}
crate::components::copy_button::CopyButton { value: webhook_url.clone() }
}
}
}
}
div { class: "form-group",
label { "Webhook Secret" }
div { class: "copyable",
input {
r#type: "text",
readonly: true,
style: "font-family: monospace; font-size: 12px; flex: 1;",
value: "{secret}",
}
crate::components::copy_button::CopyButton { value: secret.clone() }
}
}
}
div { class: "modal-actions",
button {
class: "btn btn-secondary",
onclick: move |_| edit_repo_id.set(None),
"Cancel"
}
button {
class: "btn btn-primary",
disabled: edit_saving(),
onclick: move |_| {
let id = eid.clone();
let nm = { let v = edit_name(); if v.is_empty() { None } else { Some(v) } };
let br = { let v = edit_branch(); if v.is_empty() { None } else { Some(v) } };
let tt = { let v = edit_tracker_type(); if v.is_empty() { None } else { Some(v) } };
let t_owner = { let v = edit_tracker_owner(); if v.is_empty() { None } else { Some(v) } };
let t_repo = { let v = edit_tracker_repo(); if v.is_empty() { None } else { Some(v) } };
let t_tok = { let v = edit_tracker_token(); if v.is_empty() { None } else { Some(v) } };
edit_saving.set(true);
spawn(async move {
match crate::infrastructure::repositories::update_repository(
id, nm, br, None, None, tt, t_owner, t_repo, t_tok, None,
).await {
Ok(_) => {
toasts.push(ToastType::Success, "Repository updated");
repos.restart();
}
Err(e) => toasts.push(ToastType::Error, e.to_string()),
}
edit_saving.set(false);
edit_repo_id.set(None);
});
},
if edit_saving() { "Saving..." } else { "Save" }
}
}
}
}
}
match &*repos.read() {
Some(Some(resp)) => {
let total_pages = resp.total.unwrap_or(0).div_ceil(20).max(1);
rsx! {
div { class: "card",
div { class: "table-wrapper",
table {
thead {
tr {
th { "Name" }
th { "Git URL" }
th { "Branch" }
th { "Findings" }
th { "Last Scanned" }
th { "Actions" }
}
}
tbody {
for repo in &resp.data {
{
let repo_id = repo.id.as_ref().map(|id| id.to_hex()).unwrap_or_default();
let repo_id_scan = repo_id.clone();
let repo_id_del = repo_id.clone();
let repo_id_edit = repo_id.clone();
let repo_name_del = repo.name.clone();
let edit_repo_data = repo.clone();
let is_scanning = scanning_ids().contains(&repo_id);
rsx! {
tr {
td { "{repo.name}" }
td {
style: "font-size: 12px; font-family: monospace;",
"{repo.git_url}"
}
td { "{repo.default_branch}" }
td { "{repo.findings_count}" }
td {
{
let now = chrono::Utc::now();
let diff = now.signed_duration_since(repo.updated_at);
let label = if diff.num_minutes() < 1 {
"just now".to_string()
} else if diff.num_hours() < 1 {
format!("{}m ago", diff.num_minutes())
} else if diff.num_days() < 1 {
format!("{}h ago", diff.num_hours())
} else if diff.num_days() < 30 {
format!("{}d ago", diff.num_days())
} else {
repo.updated_at.format("%Y-%m-%d").to_string()
};
rsx! { span { style: "font-size: 12px;", "{label}" } }
}
}
td { style: "display: flex; gap: 4px;",
button {
class: if graph_repo_id().as_deref() == Some(repo_id.as_str()) { "btn btn-ghost btn-active" } else { "btn btn-ghost" },
title: "View graph",
onclick: {
let rid = repo_id.clone();
move |_| {
if graph_repo_id().as_deref() == Some(rid.as_str()) {
graph_repo_id.set(None);
} else {
graph_repo_id.set(Some(rid.clone()));
}
}
},
Icon { icon: BsDiagram3, width: 16, height: 16 }
}
button {
class: "btn btn-ghost",
title: "Edit repository",
onclick: move |_| {
edit_name.set(edit_repo_data.name.clone());
edit_branch.set(edit_repo_data.default_branch.clone());
edit_tracker_type.set(
edit_repo_data.tracker_type.as_ref().map(|t| t.to_string()).unwrap_or_default()
);
edit_tracker_owner.set(edit_repo_data.tracker_owner.clone().unwrap_or_default());
edit_tracker_repo.set(edit_repo_data.tracker_repo.clone().unwrap_or_default());
edit_tracker_token.set(String::new());
edit_webhook_secret.set(None);
edit_webhook_tracker.set(String::new());
edit_repo_id.set(Some(repo_id_edit.clone()));
// Fetch webhook config in background
let rid = repo_id_edit.clone();
spawn(async move {
if let Ok(cfg) = crate::infrastructure::repositories::fetch_webhook_config(rid).await {
edit_webhook_secret.set(cfg.webhook_secret);
edit_webhook_tracker.set(cfg.tracker_type);
}
});
},
Icon { icon: BsPencil, width: 16, height: 16 }
}
button {
class: if is_scanning { "btn btn-ghost btn-scanning" } else { "btn btn-ghost" },
title: "Trigger scan",
disabled: is_scanning,
onclick: move |_| {
let id = repo_id_scan.clone();
// Add to scanning set
let mut ids = scanning_ids();
ids.push(id.clone());
scanning_ids.set(ids);
spawn(async move {
match crate::infrastructure::repositories::trigger_repo_scan(id.clone()).await {
Ok(_) => {
toasts.push(ToastType::Success, "Scan triggered");
// Poll until scan completes
loop {
async_sleep_5s().await;
match crate::infrastructure::repositories::check_repo_scanning(id.clone()).await {
Ok(false) => break,
Ok(true) => continue,
Err(_) => break,
}
}
toasts.push(ToastType::Success, "Scan complete");
repos.restart();
}
Err(e) => toasts.push(ToastType::Error, e.to_string()),
}
// Remove from scanning set
let mut ids = scanning_ids();
ids.retain(|i| i != &id);
scanning_ids.set(ids);
});
},
if is_scanning {
span { class: "spinner" }
} else {
Icon { icon: BsPlayCircle, width: 16, height: 16 }
}
}
button {
class: "btn btn-ghost btn-ghost-danger",
title: "Delete repository",
onclick: move |_| {
confirm_delete.set(Some((repo_id_del.clone(), repo_name_del.clone())));
},
Icon { icon: BsTrash, width: 16, height: 16 }
}
}
}
}
}
}
}
}
}
Pagination {
current_page: page(),
total_pages: total_pages,
on_page_change: move |p| page.set(p),
}
}
// Inline graph explorer
if let Some(rid) = graph_repo_id() {
div { class: "card", style: "margin-top: 16px;",
div { class: "card-header", style: "display: flex; justify-content: space-between; align-items: center;",
span { "Code Graph" }
button {
class: "btn btn-sm btn-ghost",
title: "Close graph",
onclick: move |_| { graph_repo_id.set(None); },
Icon { icon: BsX, width: 18, height: 18 }
}
}
GraphExplorerInline { repo_id: rid }
}
}
}
},
Some(None) => rsx! {
div { class: "card", p { "Failed to load repositories." } }
},
None => rsx! {
div { class: "loading", "Loading repositories..." }
},
}
}
}
+9 -9
View File
@@ -28,9 +28,9 @@ pub fn SbomPage() -> Element {
let mut diff_repo_a = use_signal(String::new);
let mut diff_repo_b = use_signal(String::new);
// ── Repos for dropdowns ──
// ── Targets for dropdowns ──
let repos = use_resource(|| async {
crate::infrastructure::repositories::fetch_repositories(1)
crate::infrastructure::onboarding::fetch_targets()
.await
.ok()
});
@@ -114,14 +114,14 @@ pub fn SbomPage() -> Element {
select {
class: "sbom-filter-select",
onchange: move |e| { repo_filter.set(e.value()); page.set(1); },
option { value: "", "All Repositories" }
option { value: "", "All Targets" }
{
match &*repos.read() {
Some(Some(resp)) => rsx! {
for repo in &resp.data {
{
let id = repo.id.as_ref().map(|id| id.to_hex()).unwrap_or_default();
let name = repo.name.clone();
let id = repo.get("_id").and_then(|o| o.get("$oid")).and_then(|s| s.as_str()).unwrap_or_default().to_string();
let name = repo.get("name").and_then(|n| n.as_str()).unwrap_or_default().to_string();
rsx! { option { value: "{id}", "{name}" } }
}
}
@@ -476,8 +476,8 @@ pub fn SbomPage() -> Element {
Some(Some(resp)) => rsx! {
for repo in &resp.data {
{
let id = repo.id.as_ref().map(|id| id.to_hex()).unwrap_or_default();
let name = repo.name.clone();
let id = repo.get("_id").and_then(|o| o.get("$oid")).and_then(|s| s.as_str()).unwrap_or_default().to_string();
let name = repo.get("name").and_then(|n| n.as_str()).unwrap_or_default().to_string();
rsx! { option { value: "{id}", "{name}" } }
}
}
@@ -498,8 +498,8 @@ pub fn SbomPage() -> Element {
Some(Some(resp)) => rsx! {
for repo in &resp.data {
{
let id = repo.id.as_ref().map(|id| id.to_hex()).unwrap_or_default();
let name = repo.name.clone();
let id = repo.get("_id").and_then(|o| o.get("$oid")).and_then(|s| s.as_str()).unwrap_or_default().to_string();
let name = repo.get("name").and_then(|n| n.as_str()).unwrap_or_default().to_string();
rsx! { option { value: "{id}", "{name}" } }
}
}
+544
View File
@@ -0,0 +1,544 @@
//! Targets page — lists onboarded targets (the unified `OnboardedTarget`
//! records the wizard creates) and lets the user run a scan, inspect the
//! classification / applicable scans, or delete a target.
//!
//! Creation lives in the Onboard wizard (`/onboard`); this page is the
//! "where is my target, and what did the scan find" surface.
use dioxus::prelude::*;
use dioxus_free_icons::icons::bs_icons::*;
use dioxus_free_icons::Icon;
use crate::components::page_header::PageHeader;
use crate::components::toast::{ToastType, Toasts};
use crate::infrastructure::onboarding::{
delete_target, fetch_applicable_scans, fetch_targets, trigger_target_scan, update_target,
validate_artifact_ref, validate_target_name, ArtifactInputDto,
};
/// The nine target families (value, label) for the edit form's type selector.
const TARGET_TYPES: &[(&str, &str)] = &[
("web_app", "Web Application"),
("backend_service", "Backend / API"),
("desktop_app", "Desktop App"),
("android_app", "Android App"),
("ios_app", "iOS App"),
("firmware_bare_metal", "Firmware — bare metal"),
("firmware_rtos", "Firmware — RTOS"),
("embedded_linux_yocto", "Embedded Linux / Yocto"),
("plc_sps", "PLC / SPS"),
];
/// The artifact kinds (value, label) for the edit form.
const ARTIFACT_KINDS: &[(&str, &str)] = &[
("git_repo", "Git repository"),
("source_archive", "Source archive (zip)"),
("firmware_image", "Firmware image"),
("mobile_package", "Mobile package (APK/IPA)"),
("container_image", "Container image"),
("live_url", "Live URL"),
("plc_project", "PLC project"),
("plaintext_description", "Description (text)"),
];
/// Prettify a snake_case target-type value into a human label.
fn pretty_type(v: &str) -> String {
match v {
"web_app" => "Web Application".into(),
"backend_service" => "Backend / API".into(),
"desktop_app" => "Desktop App".into(),
"android_app" => "Android App".into(),
"ios_app" => "iOS App".into(),
"firmware_bare_metal" => "Firmware — bare metal".into(),
"firmware_rtos" => "Firmware — RTOS".into(),
"embedded_linux_yocto" => "Embedded Linux / Yocto".into(),
"plc_sps" => "PLC / SPS".into(),
other => other.replace('_', " "),
}
}
fn str_at<'a>(v: &'a serde_json::Value, key: &str) -> &'a str {
v.get(key).and_then(|x| x.as_str()).unwrap_or("")
}
fn target_id(t: &serde_json::Value) -> String {
t.get("_id")
.and_then(|o| o.get("$oid"))
.and_then(|s| s.as_str())
.unwrap_or_default()
.to_string()
}
/// The applicable-scans matrix for one target, fetched on expand.
#[component]
fn TargetScans(id: String) -> Element {
let scan_id = id.clone();
let scans = use_resource(move || {
let id = scan_id.clone();
async move { fetch_applicable_scans(id).await.ok() }
});
let snapshot = scans.read().clone();
match &snapshot {
Some(Some(resp)) => {
let rows = resp.data.scans.clone();
let pentest = resp.data.pentest_supported;
rsx! {
div { style: "margin-top: 8px;",
if rows.is_empty() {
div { style: "opacity: 0.6;", "No scans available (no code / URL / firmware artifact present)." }
}
for s in rows {
{
let name = str_at(&s, "scan").to_string();
let rationale = str_at(&s, "rationale").to_string();
let blocked = s.get("blocked_reason").and_then(|b| b.as_str()).map(String::from);
let default_on = s.get("default_on").and_then(|b| b.as_bool()).unwrap_or(false);
let badge = if blocked.is_some() {
"badge badge-info"
} else if default_on {
"badge badge-success"
} else {
"badge"
};
rsx! {
div { style: "display: flex; gap: 8px; align-items: center; padding: 4px 0;",
span { class: "{badge}", "{name}" }
span { style: "opacity: 0.8; font-size: 0.9em;", "{rationale}" }
if let Some(b) = blocked {
span { style: "opacity: 0.6; font-style: italic; font-size: 0.9em;", "— {b}" }
}
}
}
}
}
if pentest {
div { style: "margin-top: 6px; opacity: 0.75; font-size: 0.85em;",
"Active pentest is supported for this target type."
}
}
}
}
}
Some(None) => rsx! { div { style: "opacity: 0.6;", "Failed to load applicable scans." } },
None => rsx! { div { style: "opacity: 0.6;", "Loading scans..." } },
}
}
#[component]
pub fn TargetsPage() -> Element {
let mut toasts = use_context::<Toasts>();
let mut scanning_ids = use_signal(Vec::<String>::new);
let mut expanded_ids = use_signal(Vec::<String>::new);
let mut confirm_delete = use_signal(|| Option::<(String, String)>::None);
// Edit-target modal state.
let mut edit_id = use_signal(|| Option::<String>::None);
let mut edit_name = use_signal(String::new);
let mut edit_type = use_signal(String::new);
let mut edit_arts = use_signal(Vec::<ArtifactInputDto>::new);
let mut edit_saving = use_signal(|| false);
// In-modal "add artifact" mini-form.
let mut e_kind = use_signal(|| "git_repo".to_string());
let mut e_source = use_signal(String::new);
let mut e_branch = use_signal(|| "main".to_string());
let mut targets = use_resource(move || async move { fetch_targets().await.ok() });
rsx! {
PageHeader {
title: "Targets",
description: "Onboarded targets and what their scans found. Add new targets from Onboard.",
}
div { style: "margin-bottom: 16px; display: flex; gap: 8px;",
Link { to: crate::app::Route::OnboardingPage {}, class: "btn btn-primary",
"+ Onboard a target"
}
button {
class: "btn btn-secondary",
onclick: move |_| targets.restart(),
"Refresh"
}
}
// ── Delete confirmation ──
if let Some((del_id, del_name)) = confirm_delete() {
div { class: "modal-overlay",
div { class: "modal-dialog",
h3 { "Delete Target" }
p { "Delete " strong { "{del_name}" } "?" }
p { class: "modal-warning",
"This permanently removes the target and its findings, SBOM entries, scan runs, and CVE alerts."
}
div { class: "modal-actions",
button {
class: "btn btn-secondary",
onclick: move |_| confirm_delete.set(None),
"Cancel"
}
button {
class: "btn btn-danger",
onclick: move |_| {
let id = del_id.clone();
let name = del_name.clone();
confirm_delete.set(None);
spawn(async move {
match delete_target(id).await {
Ok(_) => {
toasts.push(ToastType::Success, format!("{name} deleted"));
targets.restart();
}
Err(e) => toasts.push(ToastType::Error, e.to_string()),
}
});
},
"Delete"
}
}
}
}
}
// ── Edit target ──
if let Some(eid) = edit_id() {
{
let name_err = validate_target_name(&edit_name());
let e_source_err = if e_source().is_empty() {
None
} else {
validate_artifact_ref(&e_kind(), &e_source())
};
rsx! {
div { class: "modal-overlay",
div { class: "modal-dialog",
h3 { "Edit target" }
div { class: "form-group",
label { "Name" }
input {
r#type: "text",
value: "{edit_name}",
oninput: move |e| edit_name.set(e.value()),
}
if !edit_name().is_empty() {
if let Some(err) = name_err.clone() {
div { style: "color: var(--danger, #d33); font-size: 0.85em;", "{err}" }
}
}
}
div { class: "form-group",
label { "Type" }
select {
value: "{edit_type}",
oninput: move |e| edit_type.set(e.value()),
for (v, l) in TARGET_TYPES.iter().copied() {
option { value: "{v}", selected: edit_type() == v, "{l}" }
}
}
}
label { style: "font-weight: 600;", "Artifacts" }
for (i, a) in edit_arts().iter().enumerate() {
div { style: "display: flex; justify-content: space-between; align-items: center; padding: 4px 0;",
span { style: "font-size: 0.9em;",
span { style: "opacity: 0.7;", "{a.kind}: " }
span { style: "font-family: monospace;", "{a.source_ref}" }
}
button {
class: "btn btn-ghost btn-ghost-danger btn-sm",
onclick: move |_| { edit_arts.write().remove(i); },
"Remove"
}
}
}
div { style: "display: flex; gap: 8px; align-items: flex-end; margin-top: 8px;",
div { class: "form-group", style: "margin: 0;",
label { "Kind" }
select {
value: "{e_kind}",
oninput: move |e| e_kind.set(e.value()),
for (v, l) in ARTIFACT_KINDS.iter().copied() {
option { value: "{v}", selected: e_kind() == v, "{l}" }
}
}
}
div { class: "form-group", style: "margin: 0; flex: 1;",
label { "Reference" }
input {
r#type: "text",
value: "{e_source}",
oninput: move |e| e_source.set(e.value()),
}
}
if e_kind() == "git_repo" {
div { class: "form-group", style: "margin: 0;",
label { "Branch" }
input {
r#type: "text",
value: "{e_branch}",
oninput: move |e| e_branch.set(e.value()),
}
}
}
button {
class: "btn btn-secondary",
disabled: e_source().trim().is_empty() || e_source_err.is_some(),
onclick: move |_| {
let kind = e_kind();
if !e_source().trim().is_empty()
&& validate_artifact_ref(&kind, &e_source()).is_none()
{
let branch = if kind == "git_repo" { Some(e_branch()) } else { None };
edit_arts.write().push(ArtifactInputDto {
kind,
source_ref: e_source(),
branch,
plc_format: None,
});
e_source.set(String::new());
}
},
"+ Add"
}
}
if let Some(err) = e_source_err.clone() {
div { style: "color: var(--danger, #d33); font-size: 0.85em;", "{err}" }
}
div { class: "modal-actions",
button {
class: "btn btn-secondary",
onclick: move |_| edit_id.set(None),
"Cancel"
}
button {
class: "btn btn-primary",
disabled: edit_saving() || name_err.is_some(),
onclick: move |_| {
let id = eid.clone();
let nm = edit_name();
let tt = edit_type();
let arts = edit_arts();
edit_saving.set(true);
spawn(async move {
match update_target(id, Some(nm), Some(tt), Some(arts)).await {
Ok(_) => {
toasts.push(ToastType::Success, "Target updated");
targets.restart();
edit_id.set(None);
}
Err(e) => toasts.push(ToastType::Error, e.to_string()),
}
edit_saving.set(false);
});
},
if edit_saving() { "Saving..." } else { "Save" }
}
}
}
}
}
}
}
{
let targets_snapshot = targets.read().clone();
match &targets_snapshot {
Some(Some(resp)) => {
let rows = resp.data.clone();
if rows.is_empty() {
rsx! {
div { class: "card", style: "padding: 24px; text-align: center;",
p { style: "opacity: 0.7;", "No targets yet." }
Link { to: crate::app::Route::OnboardingPage {}, class: "btn btn-primary",
"Onboard your first target"
}
}
}
} else {
rsx! {
div { class: "card",
div { class: "table-wrapper",
table {
thead {
tr {
th { "Name" }
th { "Type" }
th { "Detected" }
th { "Artifacts" }
th { "Findings" }
th { "Actions" }
}
}
tbody {
for t in rows {
{
let id = target_id(&t);
let name = str_at(&t, "name").to_string();
let ttype = pretty_type(str_at(&t, "target_type"));
let suggested = t
.get("classification")
.and_then(|c| c.get("suggested"))
.and_then(|s| s.as_str())
.map(pretty_type);
let artifacts = t
.get("artifacts")
.and_then(|a| a.as_array())
.cloned()
.unwrap_or_default();
let findings = t
.get("findings_count")
.and_then(|n| n.as_u64())
.unwrap_or(0);
let facts = t
.get("classification")
.and_then(|c| c.get("facts"))
.and_then(|f| f.as_array())
.cloned()
.unwrap_or_default();
let is_scanning = scanning_ids().contains(&id);
let is_expanded = expanded_ids().contains(&id);
let id_scan = id.clone();
let id_exp = id.clone();
let id_del = id.clone();
let id_edit = id.clone();
let name_del = name.clone();
let name_edit = name.clone();
let ttype_raw = str_at(&t, "target_type").to_string();
let artifacts_detail = artifacts.clone();
let artifacts_edit = artifacts.clone();
rsx! {
tr {
td { strong { "{name}" } }
td { "{ttype}" }
td {
if let Some(sug) = suggested.clone() {
span { class: "badge badge-success", "{sug}" }
} else {
span { style: "opacity: 0.5;", "" }
}
}
td { "{artifacts.len()}" }
td { "{findings}" }
td { style: "display: flex; gap: 4px;",
button {
class: "btn btn-ghost",
title: "Details",
onclick: move |_| {
let mut ids = expanded_ids();
if ids.contains(&id_exp) {
ids.retain(|i| i != &id_exp);
} else {
ids.push(id_exp.clone());
}
expanded_ids.set(ids);
},
Icon { icon: BsInfoCircle, width: 16, height: 16 }
}
button {
class: "btn btn-ghost",
title: "Edit target",
onclick: move |_| {
edit_name.set(name_edit.clone());
edit_type.set(ttype_raw.clone());
let arts: Vec<ArtifactInputDto> = artifacts_edit
.iter()
.map(|a| ArtifactInputDto {
kind: str_at(a, "kind").to_string(),
source_ref: str_at(a, "source_ref").to_string(),
branch: a
.get("git")
.and_then(|g| g.get("default_branch"))
.and_then(|b| b.as_str())
.map(String::from),
plc_format: None,
})
.collect();
edit_arts.set(arts);
e_source.set(String::new());
edit_id.set(Some(id_edit.clone()));
},
Icon { icon: BsPencil, width: 16, height: 16 }
}
button {
class: if is_scanning { "btn btn-ghost btn-scanning" } else { "btn btn-ghost" },
title: "Run scan",
disabled: is_scanning,
onclick: move |_| {
let id = id_scan.clone();
let mut ids = scanning_ids();
ids.push(id.clone());
scanning_ids.set(ids);
spawn(async move {
match trigger_target_scan(id.clone()).await {
Ok(_) => toasts.push(ToastType::Success, "Scan triggered — findings appear as it runs. Use Refresh."),
Err(e) => toasts.push(ToastType::Error, e.to_string()),
}
let mut ids = scanning_ids();
ids.retain(|i| i != &id);
scanning_ids.set(ids);
});
},
if is_scanning {
span { class: "spinner" }
} else {
Icon { icon: BsPlayCircle, width: 16, height: 16 }
}
}
button {
class: "btn btn-ghost btn-ghost-danger",
title: "Delete target",
onclick: move |_| {
confirm_delete.set(Some((id_del.clone(), name_del.clone())));
},
Icon { icon: BsTrash, width: 16, height: 16 }
}
}
}
if is_expanded {
tr {
td { colspan: "6",
div { style: "padding: 12px 8px;",
h4 { style: "margin: 0 0 6px;", "Artifacts" }
if artifacts_detail.is_empty() {
div { style: "opacity: 0.6;", "No artifacts." }
}
for a in artifacts_detail {
div { style: "font-size: 0.9em; padding: 2px 0;",
span { style: "opacity: 0.7;", "{str_at(&a, \"kind\")}: " }
span { style: "font-family: monospace;", "{str_at(&a, \"source_ref\")}" }
}
}
if !facts.is_empty() {
h4 { style: "margin: 12px 0 6px;", "Detected facts" }
for f in facts {
div { style: "font-size: 0.9em; padding: 2px 0;",
span { style: "font-family: monospace;", "{str_at(&f, \"key\")}={str_at(&f, \"value\")}" }
span { style: "opacity: 0.5;", " ({str_at(&f, \"source\")})" }
}
}
}
h4 { style: "margin: 12px 0 6px;", "Applicable scans" }
TargetScans { id: id.clone() }
}
}
}
}
}
}
}
}
}
}
}
}
}
}
Some(None) => rsx! {
div { class: "card", p { "Failed to load targets." } }
},
None => rsx! {
div { class: "loading", "Loading targets..." }
},
}
}
}
}
+4 -1
View File
@@ -4,7 +4,7 @@ version = "0.1.0"
edition = "2021"
[dependencies]
compliance-core = { workspace = true, features = ["mongodb"] }
compliance-core = { workspace = true, features = ["mongodb", "axum"] }
rmcp = { version = "0.16", features = ["server", "macros", "transport-io", "transport-streamable-http-server"] }
tokio = { workspace = true }
serde = { workspace = true }
@@ -19,3 +19,6 @@ bson = { version = "2", features = ["chrono-0_4"] }
schemars = "1.0"
axum = "0.8"
tower-http = { version = "0.6", features = ["cors"] }
sha2 = { workspace = true }
hex = { workspace = true }
dashmap = { workspace = true }

Some files were not shown because too many files have changed in this diff Show More