Compare commits

...
Author SHA1 Message Date
Sharang ParnerkarandClaude Fable 5 82ed4afd10 feat(controls): B2 — grounded surface checks for absence-based CRA controls
CI / Check (push) Skipped
CI / Check (pull_request) Successful in 5m44s
CI / Detect Changes (pull_request) Skipped
CI / Deploy Agent (pull_request) Skipped
CI / Deploy Dashboard (pull_request) Skipped
CI / Deploy Docs (pull_request) Skipped
CI / Deploy MCP (pull_request) Skipped
Second slice of B (hybrid coverage): the controls violated by an *absence*
(no rate limiting, no security logging, no update-signature check) have no
syntactic pattern for semgrep, so we retrieve the code surface each governs and
let the grounded judge decide whether the control holds.

- controls/surface.rs: deterministic, bounded surface retrieval (keyword +
  window, capped per control) for cra-ai-6,11,24,27,28,29,30.
- grounded_surface_findings(): retrieve surfaces -> GroundedControlChecker ->
  net-new findings, each already tagged with its control and grounded to a real
  snippet (ground() drops anything not quoting verbatim code).
- orchestrator Stage 5d, gated on breakpilot.grounded_control_checks
  (BREAKPILOT_GROUNDED_CHECKS, default off) — absence detection is the least
  deterministic path, kept off until tuned against live scans.
- LUT: the 7 controls' notes now point to the gated grounded mechanism (kept
  needs_tooling; coverage stays honest until live-validated).

Local validation (real Qwen, temp 0), correct positive+negative discrimination:
  cra-ai-11 unprotected login  -> violates, CWE-307, grounded; protected -> false
  cra-ai-24 unlogged admin del -> violates, CWE-778, grounded; logged   -> false

Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>
2026-07-21 14:41:22 +02:00
sharang 38fedc661b feat(controls): B1 — custom semgrep detectors for 4 CRA controls (#218)
CI / Check (push) Skipped
CI / Detect Changes (push) Successful in 3s
CI / Deploy Dashboard (push) Skipped
CI / Deploy Docs (push) Skipped
CI / Deploy MCP (push) Skipped
CI / Deploy Agent (push) Failing after 4s
2026-07-21 12:31:20 +00:00
sharang 36a49cdeac ci: push images to Harbor (repo.meghsakha.com) + cosign (#216)
CI / Check (push) Skipped
CI / Detect Changes (push) Successful in 3s
CI / Deploy Agent (push) Skipped
CI / Deploy Dashboard (push) Skipped
CI / Deploy Docs (push) Skipped
CI / Deploy MCP (push) Skipped
2026-07-21 12:08:04 +00:00
sharang 0ef2cd1b23 feat(agent): cache control embedding index + auto-wire semantic pass (gated) (#217)
CI / Check (push) Skipped
CI / Detect Changes (push) Successful in 3s
CI / Deploy Docs (push) Skipped
CI / Deploy Agent (push) Failing after 3s
CI / Deploy Dashboard (push) Failing after 3s
CI / Deploy MCP (push) Failing after 2s
2026-07-21 11:29:16 +00:00
sharang f516ecf3b5 feat(agent): semantic control mapping — embedding index + region->control retrieval (#215)
CI / Check (push) Skipped
CI / Detect Changes (push) Successful in 5s
CI / Deploy Dashboard (push) Skipped
CI / Deploy Docs (push) Skipped
CI / Deploy MCP (push) Skipped
CI / Deploy Agent (push) Failing after 5s
2026-07-21 10:50:21 +00:00
sharang 18a23403a1 feat(oscal): emit unmapped findings as-is + MCP oscal_assessment tool (#214)
CI / Deploy Dashboard (push) Failing after 3s
CI / Deploy MCP (push) Failing after 2s
CI / Check (push) Skipped
CI / Detect Changes (push) Successful in 3s
CI / Deploy Docs (push) Skipped
CI / Deploy Agent (push) Failing after 3s
2026-07-21 09:48:37 +00:00
sharang c6baf72c6d feat: control-driven SAST — LUT + grounded LLM triage over tool findings (#213)
CI / Check (push) Skipped
CI / Detect Changes (push) Successful in 3s
CI / Deploy Agent (push) Successful in 3m45s
CI / Deploy Docs (push) Skipped
CI / Deploy Dashboard (push) Successful in 2m40s
CI / Deploy MCP (push) Successful in 1m46s
2026-07-21 09:01:51 +00:00
sharang 5285fb67ae feat(oscal): live assessment endpoint POST /api/v1/oscal/assess (#212)
CI / Check (push) Skipped
CI / Detect Changes (push) Successful in 2s
CI / Deploy Docs (push) Skipped
CI / Deploy Agent (push) Successful in 3m43s
CI / Deploy Dashboard (push) Successful in 2m36s
CI / Deploy MCP (push) Successful in 1m48s
2026-07-20 19:13:47 +00:00
sharang ca4e31cb65 feat(oscal): assessment-results emitter + finding->control linker (#211)
CI / Deploy MCP (push) Successful in 1m47s
CI / Check (push) Skipped
CI / Detect Changes (push) Successful in 3s
CI / Deploy Docs (push) Skipped
CI / Deploy Agent (push) Successful in 3m44s
CI / Deploy Dashboard (push) Successful in 2m39s
2026-07-20 16:53:39 +00:00
sharang d4884cfe4f feat(oscal): ingest breakpilot OSCAL catalog via OscalControlsProvider (#210)
CI / Deploy Agent (push) Successful in 3m40s
CI / Check (push) Skipped
CI / Detect Changes (push) Successful in 2s
CI / Deploy Docs (push) Skipped
CI / Deploy Dashboard (push) Successful in 2m34s
CI / Deploy MCP (push) Successful in 2m0s
2026-07-20 16:19:09 +00:00
sharang 94c0d51a11 feat(werkbank): make the loop runnable — enqueue + artifact serve/fetch (WB-05b) (#209)
CI / Check (push) Has been skipped
CI / Detect Changes (push) Successful in 3s
CI / Deploy Agent (push) Successful in 3m43s
CI / Deploy Dashboard (push) Has been skipped
CI / Deploy Docs (push) Has been skipped
CI / Deploy MCP (push) Has been skipped
2026-07-17 14:34:00 +00:00
sharang 70a4ee55ab refactor(werkbank): extract soft-PLC provisioning + ICS probe into werkbank-exec (WB-04a) (#208)
CI / Check (push) Has been skipped
CI / Detect Changes (push) Successful in 3s
CI / Deploy Agent (push) Successful in 3m46s
CI / Deploy Dashboard (push) Successful in 2m53s
CI / Deploy Docs (push) Has been skipped
CI / Deploy MCP (push) Successful in 2m2s
2026-07-17 12:56:15 +00:00
sharang 91a87677bc feat(werkbank): runner queue endpoints + result persistence (WB-05) (#207)
CI / Check (push) Has been skipped
CI / Detect Changes (push) Successful in 4s
CI / Deploy Agent (push) Successful in 3m44s
CI / Deploy Dashboard (push) Successful in 2m37s
CI / Deploy Docs (push) Has been skipped
CI / Deploy MCP (push) Successful in 1m49s
2026-07-17 11:42:29 +00:00
sharang 633f945a1e feat(werkbank): Mongo-backed job queue with lease + visibility timeout (WB-02) (#206)
CI / Check (push) Has been skipped
CI / Detect Changes (push) Successful in 3s
CI / Deploy Agent (push) Successful in 3m31s
CI / Deploy Dashboard (push) Successful in 2m38s
CI / Deploy Docs (push) Has been skipped
CI / Deploy MCP (push) Successful in 1m47s
2026-07-17 09:15:23 +00:00
sharang 7b218fffef feat(werkbank): job/result contract in compliance-core (WB-01) (#205)
CI / Check (push) Has been skipped
CI / Deploy Dashboard (push) Successful in 2m38s
CI / Deploy Docs (push) Has been skipped
CI / Deploy MCP (push) Successful in 1m47s
CI / Detect Changes (push) Successful in 3s
CI / Deploy Agent (push) Successful in 3m51s
2026-07-17 08:54:11 +00:00
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
125 changed files with 16131 additions and 2362 deletions
+18
View File
@@ -34,6 +34,24 @@ 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
# Werkbank runner API (/api/v1/werkbank/jobs/*, /api/v1/werkbank/artifacts/*).
# When set, mounts the runner-facing queue + artifact endpoints behind this
# bearer token; runners present the same token. Unset = endpoints not mounted.
WERKBANK_RUNNER_TOKEN=
# Dashboard
DASHBOARD_PORT=8080
AGENT_API_URL=http://localhost:3001
+22 -10
View File
@@ -107,6 +107,10 @@ jobs:
run: cargo clippy -p compliance-dashboard --features web --no-default-features -- -D warnings
- name: Clippy (mcp)
run: cargo clippy -p compliance-mcp -- -D warnings
- name: Clippy (werkbank-exec)
run: cargo clippy -p werkbank-exec -- -D warnings
- name: Clippy (control-map)
run: cargo clippy -p control-map -- -D warnings
# Security audit
- name: Security Audit
@@ -115,8 +119,8 @@ jobs:
RUSTC_WRAPPER: ""
# Tests (reuses compilation artifacts from clippy)
- name: Tests (core + agent)
run: cargo test -p compliance-core -p compliance-agent --lib
- name: Tests (core + agent + werkbank-exec + control-map)
run: cargo test -p compliance-core -p compliance-agent -p werkbank-exec -p control-map --lib
- name: Tests (dashboard server)
run: cargo test -p compliance-dashboard --features server --no-default-features
- name: Tests (dashboard web)
@@ -202,11 +206,13 @@ jobs:
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 "${{ secrets.REGISTRY_USERNAME }}" --password-stdin
IMAGE=repo.meghsakha.com/certifai/compliance-agent
echo "${{ secrets.REGISTRY_PASSWORD }}" | docker login repo.meghsakha.com -u "${{ secrets.REGISTRY_USERNAME }}" --password-stdin
DOCKER_BUILDKIT=1 docker build --secret id=tramiton_token,env=TRAMITON_FETCH_TOKEN \
-f Dockerfile.agent -t "$IMAGE:latest" -t "$IMAGE:${GITHUB_SHA}" .
docker push "$IMAGE:latest" && docker push "$IMAGE:${GITHUB_SHA}"
command -v cosign >/dev/null 2>&1 || { curl -sSfLo /usr/local/bin/cosign https://github.com/sigstore/cosign/releases/download/v2.4.3/cosign-linux-amd64 && chmod +x /usr/local/bin/cosign; }
cosign sign --yes --key env://COSIGN_KEY "$IMAGE:latest" || echo "::warning::cosign failed"
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 $2}')
RESP=$(curl -fsS -w "\nHTTP %{http_code}" -X POST "http://46.225.100.82:6880/api/v1/webhooks/github" -H "Content-Type: application/json" -H "X-Hub-Signature-256: sha256=$SIG" -d "$PAYLOAD"); echo "$RESP"
@@ -226,11 +232,13 @@ jobs:
apk add --no-cache git curl openssl
git init && git remote add origin "${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
IMAGE=repo.meghsakha.com/certifai/compliance-dashboard
echo "${{ secrets.REGISTRY_PASSWORD }}" | docker login repo.meghsakha.com -u "${{ secrets.REGISTRY_USERNAME }}" --password-stdin
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}"
command -v cosign >/dev/null 2>&1 || { curl -sSfLo /usr/local/bin/cosign https://github.com/sigstore/cosign/releases/download/v2.4.3/cosign-linux-amd64 && chmod +x /usr/local/bin/cosign; }
cosign sign --yes --key env://COSIGN_KEY "$IMAGE:latest" || echo "::warning::cosign failed"
PAYLOAD=$(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 $2}')
RESP=$(curl -fsS -w "\nHTTP %{http_code}" -X POST "http://46.225.100.82:6880/api/v1/webhooks/github" -H "Content-Type: application/json" -H "X-Hub-Signature-256: sha256=$SIG" -d "$PAYLOAD"); echo "$RESP"
@@ -248,10 +256,12 @@ jobs:
apk add --no-cache git curl openssl
git init && git remote add origin "${GITHUB_SERVER_URL}/${GITHUB_REPOSITORY}.git"
git fetch --depth=1 origin "${GITHUB_SHA}" && git checkout FETCH_HEAD
IMAGE=registry.meghsakha.com/compliance-docs
echo "${{ secrets.REGISTRY_PASSWORD }}" | docker login registry.meghsakha.com -u "${{ secrets.REGISTRY_USERNAME }}" --password-stdin
IMAGE=repo.meghsakha.com/certifai/compliance-docs
echo "${{ secrets.REGISTRY_PASSWORD }}" | docker login repo.meghsakha.com -u "${{ secrets.REGISTRY_USERNAME }}" --password-stdin
docker build -f Dockerfile.docs -t "$IMAGE:latest" -t "$IMAGE:${GITHUB_SHA}" .
docker push "$IMAGE:latest" && docker push "$IMAGE:${GITHUB_SHA}"
command -v cosign >/dev/null 2>&1 || { curl -sSfLo /usr/local/bin/cosign https://github.com/sigstore/cosign/releases/download/v2.4.3/cosign-linux-amd64 && chmod +x /usr/local/bin/cosign; }
cosign sign --yes --key env://COSIGN_KEY "$IMAGE:latest" || echo "::warning::cosign failed"
PAYLOAD=$(printf '{"ref":"refs/heads/main","repository":{"full_name":"sharang/compliance-scanner-agent"},"head_commit":{"id":"%s","message":"deploy docs"}}' "${GITHUB_SHA}")
SIG=$(printf '%s' "$PAYLOAD" | openssl dgst -sha256 -hmac "${{ secrets.ORCA_WEBHOOK_SECRET }}" | awk '{print $2}')
RESP=$(curl -fsS -w "\nHTTP %{http_code}" -X POST "http://46.225.100.82:6880/api/v1/webhooks/github" -H "Content-Type: application/json" -H "X-Hub-Signature-256: sha256=$SIG" -d "$PAYLOAD"); echo "$RESP"
@@ -271,11 +281,13 @@ jobs:
apk add --no-cache git curl openssl
git init && git remote add origin "${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
IMAGE=repo.meghsakha.com/certifai/compliance-mcp
echo "${{ secrets.REGISTRY_PASSWORD }}" | docker login repo.meghsakha.com -u "${{ secrets.REGISTRY_USERNAME }}" --password-stdin
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}"
command -v cosign >/dev/null 2>&1 || { curl -sSfLo /usr/local/bin/cosign https://github.com/sigstore/cosign/releases/download/v2.4.3/cosign-linux-amd64 && chmod +x /usr/local/bin/cosign; }
cosign sign --yes --key env://COSIGN_KEY "$IMAGE:latest" || echo "::warning::cosign failed"
PAYLOAD=$(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 $2}')
RESP=$(curl -fsS -w "\nHTTP %{http_code}" -X POST "http://46.225.100.82:6880/api/v1/webhooks/github" -H "Content-Type: application/json" -H "X-Hub-Signature-256: sha256=$SIG" -d "$PAYLOAD"); echo "$RESP"
Generated
+53 -8
View File
@@ -666,6 +666,7 @@ dependencies = [
"compliance-core",
"compliance-dast",
"compliance-graph",
"control-map",
"dashmap",
"dotenvy",
"futures-core",
@@ -679,6 +680,7 @@ dependencies = [
"rand 0.9.2",
"regex",
"reqwest",
"roxmltree",
"secrecy",
"serde",
"serde_json",
@@ -698,6 +700,7 @@ dependencies = [
"urlencoding",
"uuid",
"walkdir",
"werkbank-exec",
"zip",
]
@@ -722,6 +725,7 @@ dependencies = [
"sha2",
"thiserror 2.0.18",
"tokio",
"toml",
"tracing",
"tracing-opentelemetry",
"tracing-subscriber",
@@ -965,6 +969,15 @@ dependencies = [
"charset",
]
[[package]]
name = "control-map"
version = "0.1.0"
dependencies = [
"serde",
"serde_json",
"thiserror 2.0.18",
]
[[package]]
name = "convert_case"
version = "0.8.0"
@@ -2103,7 +2116,7 @@ source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "39cab71617ae0d63f51a36d69f866391735b51691dbda63cf6f96d042b63efeb"
dependencies = [
"libc",
"windows-sys 0.52.0",
"windows-sys 0.61.2",
]
[[package]]
@@ -3698,7 +3711,7 @@ version = "0.50.3"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "7957b9740744892f114936ab4a57b3f487491bbeafaf8083688b16841a4240e5"
dependencies = [
"windows-sys 0.60.2",
"windows-sys 0.61.2",
]
[[package]]
@@ -4628,6 +4641,12 @@ 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"
@@ -4679,7 +4698,7 @@ dependencies = [
"errno",
"libc",
"linux-raw-sys 0.4.15",
"windows-sys 0.52.0",
"windows-sys 0.59.0",
]
[[package]]
@@ -4692,7 +4711,7 @@ dependencies = [
"errno",
"libc",
"linux-raw-sys 0.12.1",
"windows-sys 0.52.0",
"windows-sys 0.61.2",
]
[[package]]
@@ -5080,6 +5099,12 @@ dependencies = [
"digest",
]
[[package]]
name = "sha1_smol"
version = "1.0.1"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "bbfa15b3dddfee50a0fff136974b3e1bde555604ba463834a7eb7deb6417705d"
[[package]]
name = "sha2"
version = "0.10.9"
@@ -5215,7 +5240,7 @@ 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",
@@ -5570,10 +5595,10 @@ source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "82a72c767771b47409d2345987fda8628641887d5466101319899796367354a0"
dependencies = [
"fastrand",
"getrandom 0.3.4",
"getrandom 0.4.1",
"once_cell",
"rustix 1.1.4",
"windows-sys 0.52.0",
"windows-sys 0.61.2",
]
[[package]]
@@ -6463,6 +6488,7 @@ dependencies = [
"getrandom 0.4.1",
"js-sys",
"serde_core",
"sha1_smol",
"wasm-bindgen",
]
@@ -6706,6 +6732,25 @@ dependencies = [
"rustls-pki-types",
]
[[package]]
name = "werkbank-exec"
version = "0.1.0"
dependencies = [
"compliance-core",
"compliance-dast",
"futures-util",
"hex",
"regex",
"reqwest",
"secrecy",
"sha2",
"thiserror 2.0.18",
"tokio",
"tracing",
"uuid",
"walkdir",
]
[[package]]
name = "which"
version = "6.0.3"
@@ -6746,7 +6791,7 @@ version = "0.1.11"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "c2a7b1c03c876122aa43f3020e6c3c3ee5c05081c9a00739faf7503aeba10d22"
dependencies = [
"windows-sys 0.48.0",
"windows-sys 0.61.2",
]
[[package]]
+5 -2
View File
@@ -7,6 +7,8 @@ members = [
"compliance-dast",
"compliance-mcp",
"compliance-smoke",
"werkbank-exec",
"control-map",
]
resolver = "2"
@@ -16,6 +18,7 @@ expect_used = "deny"
[workspace.dependencies]
compliance-core = { path = "compliance-core", default-features = false }
control-map = { path = "control-map" }
serde = { version = "1", features = ["derive"] }
serde_json = "1"
tokio = { version = "1", features = ["full"] }
@@ -23,11 +26,11 @@ 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"
uuid = { version = "1", features = ["v4", "serde"] }
uuid = { version = "1", features = ["v4", "v5", "serde"] }
secrecy = { version = "0.10", features = ["serde"] }
regex = "1"
zip = { version = "2", features = ["aes-crypto", "deflate"] }
+30 -13
View File
@@ -13,6 +13,12 @@ RUN --mount=type=secret,id=tramiton_token \
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/*
@@ -40,20 +46,30 @@ RUN pip3 install --break-system-packages semgrep
# Install ruff for Python linting
RUN pip3 install --break-system-packages ruff
# Install nix-portable (rootless nix) so the firmware-SBOM pipeline can drive a
# tramiton reproducible build (NixBackend). Best-effort: if the download fails,
# the agent falls back to analysis-only firmware SBOMs (never breaks a scan).
# The nix store lives under NP_LOCATION — mount a PERSISTENT volume there in the
# deployment, else every firmware scan re-fetches nixpkgs + cross toolchains.
ARG NIX_PORTABLE_VERSION=v012
RUN curl -fsSL -o /usr/local/bin/nix-portable \
"https://github.com/DavHau/nix-portable/releases/download/${NIX_PORTABLE_VERSION}/nix-portable-x86_64" \
&& chmod +x /usr/local/bin/nix-portable \
|| { rm -f /usr/local/bin/nix-portable; echo "WARN: nix-portable install skipped; firmware SBOM uses analysis-only fallback"; }
ENV NP_LOCATION=/data/compliance-scanner
RUN mkdir -p /data/compliance-scanner
# 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
@@ -65,5 +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"]
+8 -2
View File
@@ -8,8 +8,12 @@ workspace = true
[dependencies]
compliance-core = { workspace = true, features = ["mongodb", "telemetry", "axum"] }
control-map = { workspace = true }
compliance-graph = { path = "../compliance-graph" }
compliance-dast = { path = "../compliance-dast" }
# Shared dynamic-execution logic (soft-PLC provisioning + ICS probing), also
# used by the Werkbank runner.
werkbank-exec = { path = "../werkbank-exec" }
# 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
@@ -34,7 +38,7 @@ 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"
@@ -42,6 +46,8 @@ 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"
@@ -63,5 +69,5 @@ 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"] }
+117
View File
@@ -0,0 +1,117 @@
# Custom semgrep rules for CRA controls that no off-the-shelf ruleset digs out.
# Each rule id is `cra-ai-<n>-<slug>` and is keyed back to its control via the
# `control-map` LUT (by rule-id suffix, so semgrep's path prefix on check_id does
# not matter). Detection here is deterministic; the grounded LLM judge downstream
# only confirms/refutes — it never detects. Keep patterns tight: a false positive
# that the judge refutes marks the whole finding a false positive.
rules:
# --- cra-ai-1: Secure-by-Default-Konfiguration -------------------------------
- id: cra-ai-1-flask-debug-enabled
languages: [python]
severity: WARNING
message: Flask app started with debug=True — ships an interactive debugger / code execution in production (secure-by-default violation).
metadata:
cwe: ["CWE-489: Active Debug Code"]
control: cra-ai-1
patterns:
- pattern: '$APP.run(..., debug=True, ...)'
- id: cra-ai-1-django-debug-true
languages: [python]
severity: WARNING
message: Django DEBUG = True — leaks stack traces / settings in production (secure-by-default violation).
metadata:
cwe: ["CWE-489: Active Debug Code"]
control: cra-ai-1
patterns:
- pattern: 'DEBUG = True'
- id: cra-ai-1-tls-verify-disabled
languages: [python]
severity: ERROR
message: TLS certificate verification disabled (verify=False) — defeats transport security by default.
metadata:
cwe: ["CWE-295: Improper Certificate Validation"]
control: cra-ai-1
patterns:
- pattern: 'requests.$M(..., verify=False, ...)'
- id: cra-ai-1-cors-wildcard
languages: [javascript, typescript]
severity: WARNING
message: CORS Access-Control-Allow-Origin set to "*" — opens the API to any origin by default.
metadata:
cwe: ["CWE-942: Permissive Cross-domain Policy with Untrusted Domains"]
control: cra-ai-1
patterns:
- pattern-either:
- pattern: '$RES.header("Access-Control-Allow-Origin", "*")'
- pattern: '$RES.setHeader("Access-Control-Allow-Origin", "*")'
# --- cra-ai-7: Starke Authentifizierung (weak password hashing) --------------
- id: cra-ai-7-weak-password-hash
languages: [python]
severity: ERROR
message: Password/secret hashed with a fast, broken digest (md5/sha1) — use a password KDF (bcrypt/scrypt/argon2).
metadata:
cwe: ["CWE-916: Use of Password Hash With Insufficient Computational Effort"]
control: cra-ai-7
patterns:
- pattern-either:
- pattern: 'hashlib.md5($PW)'
- pattern: 'hashlib.sha1($PW)'
- metavariable-regex:
metavariable: $PW
regex: '(?i).*(pass|pwd|secret|cred|token).*'
# --- cra-ai-10: Sitzungsmanagement (insecure session cookies) ----------------
- id: cra-ai-10-session-cookie-insecure
languages: [python]
severity: ERROR
message: Session cookie hardened flag explicitly disabled (Secure/HttpOnly = False) — session token exposed to theft.
metadata:
cwe: ["CWE-614: Sensitive Cookie in HTTPS Session Without 'Secure' Attribute"]
control: cra-ai-10
patterns:
- pattern-either:
- pattern: 'SESSION_COOKIE_SECURE = False'
- pattern: 'SESSION_COOKIE_HTTPONLY = False'
- id: cra-ai-10-express-cookie-insecure
languages: [javascript, typescript]
severity: ERROR
message: Express cookie set with secure/httpOnly = false — session token exposed to interception / XSS theft.
metadata:
cwe: ["CWE-614: Sensitive Cookie in HTTPS Session Without 'Secure' Attribute"]
control: cra-ai-10
patterns:
- pattern-either:
- pattern: '$RES.cookie($NAME, $VAL, {..., secure: false, ...})'
- pattern: '$RES.cookie($NAME, $VAL, {..., httpOnly: false, ...})'
# --- cra-ai-14: Speicher-Schutz / Data at Rest (weak cipher) -----------------
- id: cra-ai-14-python-weak-cipher
languages: [python]
severity: ERROR
message: Data-at-rest encrypted with a broken cipher/mode (ECB, DES, 3DES) — provides no real confidentiality.
metadata:
cwe: ["CWE-327: Use of a Broken or Risky Cryptographic Algorithm"]
control: cra-ai-14
patterns:
- pattern-either:
- pattern: 'AES.new($K, AES.MODE_ECB, ...)'
- pattern: 'DES.new(...)'
- pattern: 'DES3.new(...)'
- id: cra-ai-14-node-weak-cipher
languages: [javascript, typescript]
severity: ERROR
message: Data-at-rest encrypted with a broken cipher (DES / deprecated createCipher) — provides no real confidentiality.
metadata:
cwe: ["CWE-327: Use of a Broken or Risky Cryptographic Algorithm"]
control: cra-ai-14
patterns:
- pattern-either:
- pattern: 'crypto.createCipheriv("des-ecb", ...)'
- pattern: 'crypto.createCipheriv("des", ...)'
- pattern: 'crypto.createCipher(...)'
+14 -20
View File
@@ -63,21 +63,12 @@ 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());
if self.config.unified_pipeline {
orchestrator.run_target(repo_id, trigger).await
} else {
orchestrator.run(repo_id, trigger).await
}
orchestrator.run_target(repo_id, trigger).await
}
/// Run a scan for an onboarded target through the unified pipeline,
/// unconditionally.
///
/// Unlike [`Self::run_scan`], this does *not* consult the
/// `unified_pipeline` transition flag: the caller (the `/targets/{id}/scan`
/// endpoint) operates on `onboarded_targets` by construction, so it must
/// always dispatch to `run_target` regardless of how the legacy paths
/// (scheduler, webhooks, `/repositories/{id}/scan`) are configured.
/// 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,
@@ -100,16 +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);
+2 -2
View File
@@ -10,17 +10,17 @@ pub mod issues;
pub mod mcp_tokens;
pub mod notifications;
pub mod onboarding;
pub mod oscal;
pub mod pentest_handlers;
pub use pentest_handlers as pentest;
pub mod repos;
pub mod sbom;
pub mod scans;
pub mod werkbank_jobs;
// Re-export all handler functions so routes.rs can use `handlers::function_name`
pub use dto::*;
pub use findings::*;
pub use health::*;
pub use issues::*;
pub use repos::*;
pub use sbom::*;
pub use scans::*;
+228 -7
View File
@@ -5,7 +5,7 @@
use std::collections::HashMap;
use std::sync::Arc;
use axum::extract::{Extension, Path, Query};
use axum::extract::{Extension, Multipart, Path, Query};
use axum::http::StatusCode;
use axum::Json;
use mongodb::bson::{doc, oid::ObjectId, to_bson};
@@ -75,6 +75,9 @@ pub struct UpdateTargetRequest {
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.
@@ -214,6 +217,13 @@ pub async fn update_target(
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 })
@@ -236,15 +246,116 @@ pub async fn delete_target(
.delete_one(doc! { "_id": oid })
.await
.map_err(|_| StatusCode::INTERNAL_SERVER_ERROR)?;
// Cascade the collections keyed by repo_id == target id (best-effort).
let by_repo = doc! { "repo_id": &id };
let _ = db.findings().delete_many(by_repo.clone()).await;
let _ = db.scan_runs().delete_many(by_repo.clone()).await;
let _ = db.sbom_entries().delete_many(by_repo.clone()).await;
let _ = db.cve_alerts().delete_many(by_repo).await;
// 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(
@@ -266,6 +377,116 @@ pub async fn add_artifact(
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(
@@ -0,0 +1,48 @@
//! OSCAL assessment endpoint.
//!
//! Returns a standard OSCAL assessment-results document for a target's findings,
//! driven by each finding's stamped `control_refs` (from the scan's control-triage
//! stage): mapped findings target their controls, unmapped findings are reported
//! as-is. See `compliance_core::models::oscal_assessment`.
use axum::extract::Extension;
use axum::http::StatusCode;
use axum::response::{IntoResponse, Response};
use axum::Json;
use mongodb::bson::doc;
use serde::Deserialize;
use compliance_core::models::oscal_assessment::assess;
use compliance_core::models::Finding;
use compliance_core::tenant_ctx::TenantCtx;
use super::dto::{collect_cursor_async, tenant_db, AgentExt};
#[derive(Debug, Deserialize)]
pub struct AssessRequest {
/// The target / repo id whose findings are assessed.
pub target_id: String,
}
/// `POST /api/v1/oscal/assess` — OSCAL assessment-results for a target's findings.
pub async fn assess_target(
Extension(agent): AgentExt,
tenant: TenantCtx,
Json(req): Json<AssessRequest>,
) -> Response {
let db = match tenant_db(&agent, &tenant).await {
Ok(db) => db,
Err(code) => return code.into_response(),
};
let findings: Vec<Finding> = match db.findings().find(doc! { "repo_id": &req.target_id }).await
{
Ok(cursor) => collect_cursor_async(cursor).await,
Err(e) => {
tracing::warn!(error = %e, "failed to load findings for OSCAL assessment");
return StatusCode::INTERNAL_SERVER_ERROR.into_response();
}
};
Json(assess(&findings, chrono::Utc::now())).into_response()
}
@@ -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!({
"name": r.name,
"default_branch": r.default_branch,
"last_scanned_commit": r.last_scanned_commit,
}),
Some(r) => {
let git = r.code_artifact().and_then(|c| c.git.as_ref());
serde_json::json!({
"name": r.name,
"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,
@@ -0,0 +1,289 @@
//! Werkbank runner endpoints (`/api/v1/werkbank/jobs/*`).
//!
//! The pull API a Werkbank runner talks to: lease a job, heartbeat while it runs,
//! and post the result back. Machine auth is a **static bearer token**
//! (`WERKBANK_RUNNER_TOKEN`) — not a Keycloak JWT, because a runner acts across
//! tenants (each request names its `tenant`). Routes are only mounted when the
//! token is configured; with none set they don't exist (404).
//!
//! On completion the runner's findings are persisted against the job's target,
//! so a job run by a remote runner lands the same findings an in-process run
//! would (WB-05, the control-plane cut-over).
use axum::extract::{Extension, Path, Request};
use axum::http::{header, StatusCode};
use axum::middleware::Next;
use axum::response::{IntoResponse, Response};
use axum::Json;
use mongodb::bson::{doc, oid::ObjectId};
use secrecy::ExposeSecret;
use serde::{Deserialize, Serialize};
use std::time::Duration;
use compliance_core::models::werkbank::{
CompleteRequest, CompleteResponse, HeartbeatRequest, InputRef, Job, JobResult, LeaseRequest,
};
use compliance_core::models::ArtifactKind;
use super::dto::AgentExt;
use crate::database::Database;
use crate::werkbank::JobQueue;
/// Gate the runner endpoints behind the static runner bearer token.
pub async fn require_runner_token(
Extension(agent): AgentExt,
request: Request,
next: Next,
) -> Response {
let Some(expected) = agent.config.werkbank_runner_token.as_ref() else {
return (StatusCode::NOT_FOUND, "werkbank runner API disabled").into_response();
};
let presented = request
.headers()
.get(header::AUTHORIZATION)
.and_then(|v| v.to_str().ok())
.and_then(|s| s.strip_prefix("Bearer "))
.map(str::trim)
.filter(|s| !s.is_empty());
let Some(presented) = presented else {
return (StatusCode::UNAUTHORIZED, "Missing bearer token").into_response();
};
if !constant_time_eq(presented, expected.expose_secret()) {
return (StatusCode::UNAUTHORIZED, "Invalid runner token").into_response();
}
next.run(request).await
}
/// `POST /api/v1/werkbank/jobs/lease` — lease the oldest runnable job, or `204`.
#[tracing::instrument(skip_all, fields(tenant = %req.tenant, runner = %req.runner_id))]
pub async fn lease(
Extension(agent): AgentExt,
Json(req): Json<LeaseRequest>,
) -> Result<Response, StatusCode> {
let queue = JobQueue::new(&tenant_db(&agent, &req.tenant).await?);
let leased = queue
.lease(
&req.runner_id,
req.executor,
&req.labels,
Duration::from_secs(req.lease_ttl_secs),
chrono::Utc::now(),
)
.await
.map_err(internal)?;
Ok(match leased {
Some(job) => Json(job).into_response(),
None => StatusCode::NO_CONTENT.into_response(),
})
}
/// `POST /api/v1/werkbank/jobs/heartbeat` — extend the lease; `409` if it's lost.
#[tracing::instrument(skip_all, fields(tenant = %req.tenant, job = %req.job_id))]
pub async fn heartbeat(
Extension(agent): AgentExt,
Json(req): Json<HeartbeatRequest>,
) -> Result<Response, StatusCode> {
let queue = JobQueue::new(&tenant_db(&agent, &req.tenant).await?);
let ack = queue
.heartbeat(
&req.job_id,
&req.lease_token,
Duration::from_secs(req.lease_ttl_secs),
chrono::Utc::now(),
)
.await
.map_err(internal)?;
Ok(match ack {
Some(ack) => Json(ack).into_response(),
// Lease lost — the runner should abandon the job.
None => StatusCode::CONFLICT.into_response(),
})
}
/// `POST /api/v1/werkbank/jobs/complete` — record the result and persist findings.
#[tracing::instrument(skip_all, fields(tenant = %req.tenant, job = %req.job_id))]
pub async fn complete(
Extension(agent): AgentExt,
Json(req): Json<CompleteRequest>,
) -> Result<Json<CompleteResponse>, StatusCode> {
let db = tenant_db(&agent, &req.tenant).await?;
let queue = JobQueue::new(&db);
let now = chrono::Utc::now();
let recorded = queue
.complete(&req.job_id, &req.lease_token, &req.result, now)
.await
.map_err(internal)?;
// Only persist findings for the run that actually recorded the result, so a
// duplicate/late completion can't double-insert.
if recorded {
if let Some(record) = queue.get(&req.job_id).await.map_err(internal)? {
persist_findings(&db, &record.job.target_id, &req.result).await;
}
}
Ok(Json(CompleteResponse { recorded }))
}
/// `GET /api/v1/werkbank/artifacts/{hash}` — serve a content-addressed blob (the
/// program a runner needs to load). The hash is validated against traversal by
/// [`crate::ingest::blob::read_blob`]; a runner fetches this for a job's `blob`
/// input.
#[tracing::instrument(skip_all, fields(hash = %hash))]
pub async fn serve_artifact(
Extension(agent): AgentExt,
Path(hash): Path<String>,
) -> Result<Response, StatusCode> {
let base = std::path::Path::new(&agent.config.artifact_store_base_path);
match crate::ingest::blob::read_blob(base, &hash) {
Ok(bytes) => {
Ok(([(header::CONTENT_TYPE, "application/octet-stream")], bytes).into_response())
}
Err(_) => Err(StatusCode::NOT_FOUND),
}
}
/// Enqueue a `plc-provision` job for a target: extract its control-logic program,
/// stash it as a content-addressed blob (which the runner fetches via
/// [`serve_artifact`]), and queue the job. This is the control-plane "enqueue"
/// half of the loop — a runner then leases it, provisions, and posts results.
#[derive(Debug, Deserialize)]
pub struct EnqueueRequest {
/// The tenant whose queue to enqueue into.
pub tenant: String,
/// The onboarded target to test.
pub target_id: String,
}
/// The enqueued job's id.
#[derive(Debug, Serialize)]
pub struct EnqueueResponse {
/// The new job id.
pub job_id: String,
/// Whether this call inserted it (false = already queued).
pub enqueued: bool,
}
#[tracing::instrument(skip_all, fields(tenant = %req.tenant, target = %req.target_id))]
pub async fn enqueue(
Extension(agent): AgentExt,
Json(req): Json<EnqueueRequest>,
) -> Result<Json<EnqueueResponse>, StatusCode> {
let db = tenant_db(&agent, &req.tenant).await?;
let oid = ObjectId::parse_str(&req.target_id).map_err(|_| StatusCode::BAD_REQUEST)?;
let target = db
.onboarded_targets()
.find_one(doc! { "_id": oid })
.await
.map_err(internal)?
.ok_or(StatusCode::NOT_FOUND)?;
// Extract the control-logic program from the target's PLC-source artifacts
// (same selection as the in-process PLC scan).
let ctx = crate::ingest::IngestContext::from_config(&agent.config, &req.target_id);
let ingest_set = crate::ingest::ingest_all(&target, &ctx).map_err(internal)?;
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())?;
werkbank_exec::plc::extract_program(&path)
})
.ok_or(StatusCode::UNPROCESSABLE_ENTITY)?;
// Stash the program source so the runner can fetch it by hash.
let base = std::path::Path::new(&agent.config.artifact_store_base_path);
let hash =
crate::ingest::blob::store_bytes(base, program.source.as_bytes()).map_err(internal)?;
let job_id = format!("job_{}", uuid::Uuid::new_v4().simple());
let job = Job::plc_provision(
&job_id,
&req.tenant,
&req.target_id,
InputRef::blob(hash),
agent.config.plc_runtime.max_lifetime_secs,
);
let enqueued = JobQueue::new(&db)
.enqueue(job, chrono::Utc::now())
.await
.map_err(internal)?;
Ok(Json(EnqueueResponse { job_id, enqueued }))
}
/// Persist a job result's findings against its target: general findings
/// (dedup'd by fingerprint) and DAST findings. Best-effort — a persistence hiccup
/// is logged, not surfaced to the runner (its result is already recorded).
async fn persist_findings(db: &Database, target_id: &str, result: &JobResult) {
for finding in &result.findings {
let exists = db
.findings()
.find_one(doc! { "fingerprint": &finding.fingerprint })
.await
.ok()
.flatten()
.is_some();
if !exists {
if let Err(e) = db.findings().insert_one(finding).await {
tracing::warn!(target_id, error = %e, "werkbank: persist finding failed");
}
}
}
for finding in &result.dast_findings {
if let Err(e) = db.dast_findings().insert_one(finding).await {
tracing::warn!(target_id, error = %e, "werkbank: persist DAST finding failed");
}
}
tracing::info!(
target_id,
findings = result.findings.len(),
dast = result.dast_findings.len(),
"werkbank: persisted runner results"
);
}
/// Resolve the tenant-scoped database for a request.
async fn tenant_db(
agent: &crate::agent::ComplianceAgent,
tenant: &str,
) -> Result<Database, StatusCode> {
agent.db_pool.for_tenant_id(tenant).await.map_err(internal)
}
/// Map any internal error to a 500.
fn internal<E: std::fmt::Display>(e: E) -> StatusCode {
tracing::error!("werkbank endpoint error: {e}");
StatusCode::INTERNAL_SERVER_ERROR
}
/// Length-checked, constant-time-ish token comparison.
fn constant_time_eq(a: &str, b: &str) -> bool {
if a.len() != b.len() {
return false;
}
let mut diff = 0u8;
for (x, y) in a.bytes().zip(b.bytes()) {
diff |= x ^ y;
}
diff == 0
}
#[cfg(test)]
mod tests {
use super::constant_time_eq;
#[test]
fn token_compare() {
assert!(constant_time_eq("secret", "secret"));
assert!(!constant_time_eq("secret", "secrex"));
assert!(!constant_time_eq("secret", "secretx"));
assert!(!constant_time_eq("", "x"));
}
}
+5 -14
View File
@@ -6,25 +6,12 @@ use crate::api::handlers;
pub fn build_router() -> Router {
Router::new()
.route("/api/v1/health", get(handlers::health))
.route("/api/v1/oscal/assess", post(handlers::oscal::assess_target))
.route("/api/v1/stats/overview", get(handlers::stats_overview))
.route(
"/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))
.route(
"/api/v1/repositories/{id}/scan",
post(handlers::trigger_scan),
)
.route(
"/api/v1/repositories/{id}",
delete(handlers::delete_repository).patch(handlers::update_repository),
)
.route(
"/api/v1/repositories/{id}/webhook-config",
get(handlers::get_webhook_config),
)
// Unified onboarding targets (#131).
.route(
"/api/v1/targets",
@@ -40,6 +27,10 @@ pub fn build_router() -> Router {
"/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),
+40 -2
View File
@@ -1,10 +1,10 @@
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;
use axum::routing::{delete, get};
use axum::routing::{delete, get, post};
use axum::{middleware, Extension, Router};
use tokio::sync::RwLock;
use tower_http::cors::CorsLayer;
@@ -72,8 +72,46 @@ pub async fn start_api_server(agent: ComplianceAgent, port: u16) -> Result<(), A
Router::new()
};
// Werkbank runner API. Like admin, only mounted when its bearer token is
// configured; runners authenticate with WERKBANK_RUNNER_TOKEN (not a JWT).
let werkbank_router: Router = if agent.config.werkbank_runner_token.is_some() {
tracing::info!(
"Werkbank runner API enabled — /api/v1/werkbank/jobs/* behind WERKBANK_RUNNER_TOKEN"
);
Router::new()
.route(
"/api/v1/werkbank/jobs/lease",
post(handlers::werkbank_jobs::lease),
)
.route(
"/api/v1/werkbank/jobs/heartbeat",
post(handlers::werkbank_jobs::heartbeat),
)
.route(
"/api/v1/werkbank/jobs/complete",
post(handlers::werkbank_jobs::complete),
)
.route(
"/api/v1/werkbank/jobs/enqueue",
post(handlers::werkbank_jobs::enqueue),
)
.route(
"/api/v1/werkbank/artifacts/{hash}",
get(handlers::werkbank_jobs::serve_artifact),
)
.layer(middleware::from_fn(
handlers::werkbank_jobs::require_runner_token,
))
} else {
Router::new()
};
let mut app = routes::build_router()
.merge(admin_router)
.merge(werkbank_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())
+43 -6
View File
@@ -1,3 +1,4 @@
use compliance_core::config::{BreakpilotConfig, PlcRuntimeConfig};
use compliance_core::AgentConfig;
use secrecy::SecretString;
@@ -47,12 +48,6 @@ pub fn load_config() -> Result<AgentConfig, AgentError> {
.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()),
// Defaults ON: the unified onboarded-target pipeline is now the primary
// path (no legacy `repositories` data in production). Set
// `UNIFIED_PIPELINE=0` to fall back to the legacy repository pipeline.
unified_pipeline: env_var_opt("UNIFIED_PIPELINE")
.map(|v| v == "1" || v.eq_ignore_ascii_case("true"))
.unwrap_or(true),
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"),
@@ -69,5 +64,47 @@ 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(),
werkbank_runner_token: env_secret_opt("WERKBANK_RUNNER_TOKEN"),
breakpilot: load_breakpilot_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),
}
}
/// Assemble the breakpilot OSCAL-catalog source from env, defaulting the snapshot
/// directory. A missing `BREAKPILOT_BASE_URL` leaves the controls provider off.
fn load_breakpilot_config() -> BreakpilotConfig {
let d = BreakpilotConfig::default();
BreakpilotConfig {
base_url: env_var_opt("BREAKPILOT_BASE_URL"),
token: env_secret_opt("BREAKPILOT_TOKEN"),
snapshot_dir: env_var_opt("BREAKPILOT_SNAPSHOT_DIR").unwrap_or(d.snapshot_dir),
semantic_mapping: env_var_opt("BREAKPILOT_SEMANTIC_MAPPING")
.map(|v| v == "1" || v.eq_ignore_ascii_case("true"))
.unwrap_or(d.semantic_mapping),
grounded_control_checks: env_var_opt("BREAKPILOT_GROUNDED_CHECKS")
.map(|v| v == "1" || v.eq_ignore_ascii_case("true"))
.unwrap_or(d.grounded_control_checks),
}
}
+114
View File
@@ -0,0 +1,114 @@
//! The grounded control checker: judge each candidate region for a control, then
//! keep only the verdicts that survive the grounding gate.
//!
//! Generic over [`ControlJudge`] so tests drive it with a deterministic stub —
//! the whole recognize → ground path is then exercised without an LLM. With the
//! real judge, determinism comes from temperature 0 plus the gate.
use compliance_core::control_check::{ground, CandidateRegion, ControlCheckSpec};
use compliance_core::models::Finding;
use super::judge::ControlJudge;
/// Runs a [`ControlJudge`] over candidate regions and grounds the results.
pub struct GroundedControlChecker<J> {
judge: J,
}
impl<J: ControlJudge> GroundedControlChecker<J> {
pub fn new(judge: J) -> Self {
Self { judge }
}
/// Judge every candidate region for `spec` and return the grounded findings.
/// A verdict that doesn't quote real code in its region is dropped by
/// [`ground`], so nothing fabricated reaches the caller.
pub async fn check(
&self,
spec: &ControlCheckSpec,
regions: &[CandidateRegion],
repo_id: &str,
) -> Vec<Finding> {
let mut findings = Vec::new();
for region in regions {
let verdict = self.judge.judge(spec, region).await;
if let Some(finding) = ground(spec, region, &verdict, repo_id) {
findings.push(finding);
}
}
findings
}
}
#[cfg(test)]
mod tests {
use super::*;
use compliance_core::control_check::LlmVerdict;
use compliance_core::models::finding::Severity;
/// Deterministic stub: returns a fixed verdict for every region, so the
/// recognize → ground composition is tested without an LLM.
struct StubJudge {
verdict: LlmVerdict,
}
impl ControlJudge for StubJudge {
async fn judge(&self, _spec: &ControlCheckSpec, _region: &CandidateRegion) -> LlmVerdict {
self.verdict.clone()
}
}
fn spec() -> ControlCheckSpec {
ControlCheckSpec {
control_id: "cra-ai-8".into(),
title: "No default passwords".into(),
requirement: "No default credentials".into(),
default_cwe: Some("CWE-798".into()),
severity: Severity::High,
}
}
fn region(content: &str) -> CandidateRegion {
CandidateRegion {
file: "src/auth.py".into(),
start_line: 1,
content: content.into(),
}
}
#[tokio::test]
async fn keeps_grounded_and_drops_ungrounded() {
let checker = GroundedControlChecker::new(StubJudge {
verdict: LlmVerdict {
violates: true,
snippet: "PASSWORD = \"admin\"".into(),
cwe: None,
confidence: 0.9,
},
});
let regions = vec![
region("x = 1\nPASSWORD = \"admin\"\n"), // quotes real code → grounded
region("totally unrelated code\n"), // snippet absent → dropped
];
let findings = checker.check(&spec(), &regions, "repo").await;
assert_eq!(findings.len(), 1);
assert_eq!(findings[0].control_refs, vec!["cra-ai-8".to_string()]);
assert_eq!(findings[0].line_number, Some(2));
}
#[tokio::test]
async fn non_violation_yields_nothing() {
let checker = GroundedControlChecker::new(StubJudge {
verdict: LlmVerdict {
violates: false,
snippet: String::new(),
cwe: None,
confidence: 0.0,
},
});
let findings = checker
.check(&spec(), &[region("PASSWORD = \"admin\"\n")], "repo")
.await;
assert!(findings.is_empty());
}
}
+245
View File
@@ -0,0 +1,245 @@
//! In-memory embedding index over the control corpus, for region → control
//! retrieval.
//!
//! At master-control scale (~13.6k) findings can't be mapped by CWE (the master
//! controls carry none), so we map by *similarity*: embed each control's
//! requirement text once, then for a code region pull the top-K nearest controls
//! to hand to the grounded judge. This is the retrieval half of the semantic path.
use std::path::Path;
use serde::{Deserialize, Serialize};
use sha2::{Digest, Sha256};
use compliance_core::control_check::ControlCheckSpec;
use compliance_core::error::CoreError;
use crate::llm::LlmClient;
/// A control spec paired with its requirement-text embedding.
pub struct ControlIndex {
entries: Vec<(ControlCheckSpec, Vec<f64>)>,
}
/// On-disk form of the index: the corpus identity hash plus every spec+embedding.
/// The hash lets a later scan reuse the embeddings only if the corpus is unchanged.
#[derive(Serialize, Deserialize)]
struct PersistedIndex {
corpus_hash: String,
entries: Vec<PersistedEntry>,
}
#[derive(Serialize, Deserialize)]
struct PersistedEntry {
spec: ControlCheckSpec,
embedding: Vec<f64>,
}
/// Stable hash of the corpus identity (each control's id + requirement text, in
/// order). Same catalog → same hash → the cached embeddings are reused instead of
/// re-embedding the whole corpus.
fn corpus_hash(specs: &[ControlCheckSpec]) -> String {
let mut hasher = Sha256::new();
for s in specs {
hasher.update(s.control_id.as_bytes());
hasher.update([0u8]);
hasher.update(s.requirement.as_bytes());
hasher.update([0u8]);
}
format!("{:x}", hasher.finalize())
}
impl ControlIndex {
/// Build directly from precomputed embeddings (used by tests + callers that
/// already embedded the corpus).
pub fn from_embeddings(entries: Vec<(ControlCheckSpec, Vec<f64>)>) -> Self {
Self { entries }
}
/// Load the index from `cache_path` if it still matches the current corpus,
/// otherwise embed the corpus and persist it there. This turns the per-scan
/// re-embed of the whole (~13.6k) master-control corpus into a one-time cost
/// that survives across scans; the cache self-invalidates when the catalog
/// changes (its [`corpus_hash`] no longer matches).
pub async fn load_or_build(
llm: &LlmClient,
specs: Vec<ControlCheckSpec>,
cache_path: &Path,
) -> Result<Self, CoreError> {
let hash = corpus_hash(&specs);
if let Some(index) = Self::load_cache(cache_path, &hash).await {
tracing::debug!(
controls = index.len(),
"reusing cached control embedding index"
);
return Ok(index);
}
let index = Self::build(llm, specs).await?;
if let Err(e) = index.write_cache(cache_path, &hash).await {
tracing::warn!(error = %e, "failed to persist control embedding index");
}
Ok(index)
}
/// Read a persisted index, returning it only if its corpus hash matches.
async fn load_cache(path: &Path, hash: &str) -> Option<Self> {
let raw = tokio::fs::read(path).await.ok()?;
let persisted: PersistedIndex = serde_json::from_slice(&raw).ok()?;
if persisted.corpus_hash != hash {
return None;
}
Some(Self {
entries: persisted
.entries
.into_iter()
.map(|e| (e.spec, e.embedding))
.collect(),
})
}
/// Persist the index atomically (temp file + rename) keyed by corpus hash.
async fn write_cache(&self, path: &Path, hash: &str) -> Result<(), CoreError> {
if let Some(parent) = path.parent() {
tokio::fs::create_dir_all(parent).await?;
}
let persisted = PersistedIndex {
corpus_hash: hash.to_string(),
entries: self
.entries
.iter()
.map(|(spec, emb)| PersistedEntry {
spec: spec.clone(),
embedding: emb.clone(),
})
.collect(),
};
let raw = serde_json::to_vec(&persisted)?;
let tmp = path.with_extension("json.tmp");
tokio::fs::write(&tmp, &raw).await?;
tokio::fs::rename(&tmp, path).await?;
Ok(())
}
/// Build by embedding each control's requirement text.
pub async fn build(llm: &LlmClient, specs: Vec<ControlCheckSpec>) -> Result<Self, CoreError> {
if specs.is_empty() {
return Ok(Self {
entries: Vec::new(),
});
}
let texts: Vec<String> = specs.iter().map(|s| s.requirement.clone()).collect();
let embeddings = llm
.embed(texts)
.await
.map_err(|e| CoreError::Llm(e.to_string()))?;
Ok(Self {
entries: specs.into_iter().zip(embeddings).collect(),
})
}
pub fn len(&self) -> usize {
self.entries.len()
}
pub fn is_empty(&self) -> bool {
self.entries.is_empty()
}
/// The top-`k` control specs whose embedding is nearest (cosine) to `query`.
pub fn nearest(&self, query: &[f64], k: usize) -> Vec<ControlCheckSpec> {
let mut scored: Vec<(f64, &ControlCheckSpec)> = self
.entries
.iter()
.map(|(spec, emb)| (cosine(query, emb), spec))
.collect();
scored.sort_by(|a, b| b.0.total_cmp(&a.0));
scored.into_iter().take(k).map(|(_, s)| s.clone()).collect()
}
}
/// Cosine similarity; 0.0 for length-mismatched, empty, or zero vectors.
fn cosine(a: &[f64], b: &[f64]) -> f64 {
if a.len() != b.len() || a.is_empty() {
return 0.0;
}
let dot: f64 = a.iter().zip(b).map(|(x, y)| x * y).sum();
let na: f64 = a.iter().map(|x| x * x).sum();
let nb: f64 = b.iter().map(|x| x * x).sum();
if na == 0.0 || nb == 0.0 {
return 0.0;
}
dot / (na.sqrt() * nb.sqrt())
}
#[cfg(test)]
mod tests {
use super::*;
use compliance_core::models::finding::Severity;
fn spec(id: &str) -> ControlCheckSpec {
ControlCheckSpec {
control_id: id.into(),
title: id.into(),
requirement: id.into(),
default_cwe: None,
severity: Severity::Medium,
}
}
#[test]
fn nearest_ranks_by_cosine() {
let index = ControlIndex::from_embeddings(vec![
(spec("a"), vec![1.0, 0.0]),
(spec("b"), vec![0.0, 1.0]),
(spec("c"), vec![0.7, 0.7]),
]);
let hits = index.nearest(&[0.9, 0.1], 2);
assert_eq!(hits.len(), 2);
assert_eq!(hits[0].control_id, "a"); // closest to [0.9,0.1]
}
#[test]
fn cosine_edges_are_zero() {
assert_eq!(cosine(&[1.0], &[1.0, 2.0]), 0.0); // length mismatch
assert_eq!(cosine(&[0.0, 0.0], &[1.0, 1.0]), 0.0); // zero vector
assert!((cosine(&[1.0, 0.0], &[1.0, 0.0]) - 1.0).abs() < 1e-9); // identical
}
#[test]
fn corpus_hash_is_stable_and_identity_sensitive() {
let a = corpus_hash(&[spec("x"), spec("y")]);
assert_eq!(a, corpus_hash(&[spec("x"), spec("y")])); // same corpus → same hash
assert_ne!(a, corpus_hash(&[spec("y"), spec("x")])); // reorder → different
assert_ne!(a, corpus_hash(&[spec("x")])); // fewer controls → different
}
#[tokio::test]
#[allow(clippy::unwrap_used)]
async fn cache_round_trips_and_misses_on_corpus_change() {
let dir = std::env::temp_dir().join(format!("cidx-{}", uuid::Uuid::new_v4()));
let path = dir.join("control-index.json");
let specs = [spec("a"), spec("b")];
let hash = corpus_hash(&specs);
let index = ControlIndex::from_embeddings(vec![
(spec("a"), vec![1.0, 0.0]),
(spec("b"), vec![0.0, 1.0]),
]);
index.write_cache(&path, &hash).await.unwrap();
// matching corpus hash → hit
let loaded = ControlIndex::load_cache(&path, &hash).await.unwrap();
assert_eq!(loaded.len(), 2);
assert_eq!(loaded.nearest(&[0.9, 0.1], 1)[0].control_id, "a");
// corpus changed → miss (forces a rebuild)
assert!(ControlIndex::load_cache(&path, "differenthash")
.await
.is_none());
// absent file → miss, not an error
assert!(
ControlIndex::load_cache(dir.join("nope.json").as_path(), &hash)
.await
.is_none()
);
let _ = std::fs::remove_dir_all(&dir);
}
}
+167
View File
@@ -0,0 +1,167 @@
//! The "recognize" stage: judge whether a code region violates a control.
//!
//! Behind the [`ControlJudge`] trait so the grounded checker can be driven by a
//! deterministic stub in tests. The real [`LlmControlJudge`] runs the model at
//! temperature 0 with a closed prompt — it must quote the offending code VERBATIM,
//! and everything it returns is then re-checked by the grounding gate
//! ([`compliance_core::control_check::ground`]). The judge is allowed to be
//! smart; it is never trusted.
use std::sync::Arc;
use serde::Deserialize;
use compliance_core::control_check::{CandidateRegion, ControlCheckSpec, LlmVerdict};
use crate::llm::LlmClient;
/// Prompt/logic version — part of the verdict cache key, bump on any change here.
pub const PROMPT_VERSION: &str = "control-judge-v1";
const SYSTEM_PROMPT: &str = "You are a precise security & compliance code auditor. \
You are given ONE compliance control (a requirement) and ONE code region. Decide \
ONLY whether the code region VIOLATES the control. Rules: (1) Judge only the code \
shown — never assume code that is not present. (2) If and only if it violates, copy \
the EXACT offending code VERBATIM into `snippet`, character-for-character from the \
region — do not paraphrase, reformat, or reconstruct it. (3) If it does not clearly \
violate, set violates=false and leave snippet empty. (4) Prefer false over guessing. \
Respond with STRICT JSON only, no prose: \
{\"violates\": bool, \"snippet\": \"<verbatim code or empty>\", \"cwe\": \"CWE-NNN or null\", \"confidence\": 0.0-1.0}";
/// Judges one (control, region). Async-in-trait so a stub can drive tests.
#[allow(async_fn_in_trait)]
pub trait ControlJudge: Send + Sync {
async fn judge(&self, spec: &ControlCheckSpec, region: &CandidateRegion) -> LlmVerdict;
}
/// The real judge: the LLM at temperature 0 with the closed, verbatim-snippet prompt.
pub struct LlmControlJudge {
llm: Arc<LlmClient>,
}
impl LlmControlJudge {
pub fn new(llm: Arc<LlmClient>) -> Self {
Self { llm }
}
}
impl ControlJudge for LlmControlJudge {
async fn judge(&self, spec: &ControlCheckSpec, region: &CandidateRegion) -> LlmVerdict {
let user = build_user_prompt(spec, region);
match self.llm.chat(SYSTEM_PROMPT, &user, Some(0.0)).await {
Ok(response) => parse_verdict(&response),
Err(e) => {
// Fail closed: a transient model error yields no finding, never a
// fabricated one.
tracing::warn!(control = %spec.control_id, error = %e, "control judge call failed");
no_violation()
}
}
}
}
fn build_user_prompt(spec: &ControlCheckSpec, region: &CandidateRegion) -> String {
format!(
"CONTROL {id}{title}\nRequirement: {req}\n\nCODE ({file}, first line = {line}):\n```\n{code}\n```\n\nReturn the JSON verdict.",
id = spec.control_id,
title = spec.title,
req = spec.requirement,
file = region.file,
line = region.start_line,
code = region.content,
)
}
#[derive(Debug, Default, Deserialize)]
struct RawVerdict {
#[serde(default)]
violates: bool,
#[serde(default)]
snippet: String,
#[serde(default)]
cwe: Option<String>,
#[serde(default)]
confidence: f64,
}
/// Parse the model's JSON verdict, tolerant of ```json fencing. Any parse failure
/// degrades to a non-violation (never a fabricated finding).
fn parse_verdict(response: &str) -> LlmVerdict {
let cleaned = response
.trim()
.trim_start_matches("```json")
.trim_start_matches("```")
.trim_end_matches("```")
.trim();
match serde_json::from_str::<RawVerdict>(cleaned) {
Ok(raw) => LlmVerdict {
violates: raw.violates,
snippet: raw.snippet,
cwe: raw.cwe.filter(|c| !c.trim().is_empty()),
confidence: raw.confidence,
},
Err(e) => {
tracing::debug!(error = %e, "failed to parse control verdict; treating as non-violation");
no_violation()
}
}
}
fn no_violation() -> LlmVerdict {
LlmVerdict {
violates: false,
snippet: String::new(),
cwe: None,
confidence: 0.0,
}
}
#[cfg(test)]
mod tests {
use super::*;
use compliance_core::models::finding::Severity;
fn spec() -> ControlCheckSpec {
ControlCheckSpec {
control_id: "cra-ai-8".into(),
title: "No default passwords".into(),
requirement: "Products must not ship default credentials".into(),
default_cwe: Some("CWE-798".into()),
severity: Severity::High,
}
}
#[test]
fn parses_plain_and_fenced_json() {
let plain = r#"{"violates": true, "snippet": "PASSWORD = \"x\"", "cwe": "CWE-798", "confidence": 0.9}"#;
let v = parse_verdict(plain);
assert!(v.violates);
assert_eq!(v.snippet, "PASSWORD = \"x\"");
assert_eq!(v.cwe.as_deref(), Some("CWE-798"));
let fenced = "```json\n{\"violates\": false, \"snippet\": \"\", \"cwe\": null, \"confidence\": 0.1}\n```";
assert!(!parse_verdict(fenced).violates);
}
#[test]
fn garbage_and_empty_cwe_are_safe() {
assert!(!parse_verdict("not json at all").violates); // fail closed
let no_cwe =
parse_verdict(r#"{"violates": true, "snippet": "x", "cwe": " ", "confidence": 0.5}"#);
assert!(no_cwe.cwe.is_none()); // blank CWE normalised away
}
#[test]
fn user_prompt_carries_control_and_code() {
let region = CandidateRegion {
file: "src/auth.py".into(),
start_line: 10,
content: "PASSWORD = \"admin\"".into(),
};
let p = build_user_prompt(&spec(), &region);
assert!(p.contains("cra-ai-8"));
assert!(p.contains("Products must not ship default credentials"));
assert!(p.contains("PASSWORD = \"admin\""));
assert!(p.contains("src/auth.py"));
}
}
+23
View File
@@ -0,0 +1,23 @@
//! Controls corpus providers.
//!
//! Implementations of [`compliance_core::traits::ControlsProvider`] that supply
//! the control corpus the mapping engine assesses findings against. Currently:
//! [`OscalControlsProvider`], which pulls breakpilot-compliance's OSCAL catalog
//! and snapshots it locally.
mod checker;
mod index;
mod judge;
mod oscal_provider;
mod scan_triage;
mod semantic;
mod surface;
mod triage;
pub use checker::GroundedControlChecker;
pub use index::ControlIndex;
pub use judge::{ControlJudge, LlmControlJudge, PROMPT_VERSION};
pub use oscal_provider::OscalControlsProvider;
pub use scan_triage::{grounded_surface_findings, semantic_stamp_findings, triage_repo_findings};
pub use semantic::SemanticControlChecker;
pub use triage::{ControlTriage, TriageOutcome};
@@ -0,0 +1,229 @@
//! Pull + snapshot [`ControlsProvider`] backed by breakpilot-compliance's OSCAL
//! catalog export.
//!
//! Fetches `GET {base}/api/compliance/v1/oscal/catalog?framework=<fw>`, snapshots
//! the exact bytes to disk (so scans are deterministic and keep working offline /
//! on-prem), and maps the catalog into the corpus controls the mapping engine
//! consumes. The producer owns the catalog; we own the assessment — this is the
//! ingest half of the loop.
use std::path::PathBuf;
use secrecy::{ExposeSecret, SecretString};
use compliance_core::error::CoreError;
use compliance_core::models::onboarding::ComplianceFramework;
use compliance_core::models::oscal::OscalDocument;
use compliance_core::traits::{Control, ControlQuery, ControlsProvider};
/// A [`ControlsProvider`] that pulls the OSCAL catalog from breakpilot-compliance
/// and snapshots it locally for deterministic / offline reuse.
pub struct OscalControlsProvider {
http: reqwest::Client,
base_url: String,
token: Option<SecretString>,
snapshot_dir: PathBuf,
}
impl OscalControlsProvider {
/// Create a provider. `base_url` is the breakpilot-compliance root (e.g.
/// `http://backend-compliance:8002`); `snapshot_dir` is where catalog
/// snapshots are written so a later scan can reuse them without the network.
pub fn new(
http: reqwest::Client,
base_url: impl Into<String>,
token: Option<SecretString>,
snapshot_dir: impl Into<PathBuf>,
) -> Self {
Self {
http,
base_url: base_url.into(),
token,
snapshot_dir: snapshot_dir.into(),
}
}
fn catalog_url(&self, framework: &str) -> String {
format!(
"{}/api/compliance/v1/oscal/catalog?framework={framework}",
self.base_url.trim_end_matches('/')
)
}
fn snapshot_path(&self, framework: &str) -> PathBuf {
self.snapshot_dir
.join(format!("oscal-catalog-{framework}.json"))
}
/// Fetch the raw catalog bytes for a framework token over HTTP.
async fn fetch_raw(&self, framework: &str) -> Result<Vec<u8>, CoreError> {
let mut req = self.http.get(self.catalog_url(framework));
if let Some(token) = &self.token {
req = req.bearer_auth(token.expose_secret());
}
let resp = req
.send()
.await
.map_err(|e| CoreError::Http(e.to_string()))?;
if !resp.status().is_success() {
return Err(CoreError::Http(format!(
"catalog fetch for {framework} returned HTTP {}",
resp.status()
)));
}
resp.bytes()
.await
.map(|b| b.to_vec())
.map_err(|e| CoreError::Http(e.to_string()))
}
/// Write a catalog snapshot atomically (temp file + rename).
async fn write_snapshot(&self, framework: &str, raw: &[u8]) -> Result<(), CoreError> {
tokio::fs::create_dir_all(&self.snapshot_dir).await?;
let path = self.snapshot_path(framework);
let tmp = path.with_extension("json.tmp");
tokio::fs::write(&tmp, raw).await?;
tokio::fs::rename(&tmp, &path).await?;
Ok(())
}
/// Read a previously written snapshot, if one exists.
async fn read_snapshot(&self, framework: &str) -> Result<Option<OscalDocument>, CoreError> {
match tokio::fs::read(self.snapshot_path(framework)).await {
Ok(raw) => Ok(Some(serde_json::from_slice(&raw)?)),
Err(e) if e.kind() == std::io::ErrorKind::NotFound => Ok(None),
Err(e) => Err(e.into()),
}
}
/// Load the catalog for a framework token: fetch fresh + snapshot the exact
/// bytes; on network failure, fall back to the last snapshot so scans run.
async fn load_token(&self, framework: &str) -> Result<OscalDocument, CoreError> {
match self.fetch_raw(framework).await {
Ok(raw) => {
let doc: OscalDocument = serde_json::from_slice(&raw)?;
if let Err(e) = self.write_snapshot(framework, &raw).await {
tracing::warn!(framework, error = %e, "failed to write OSCAL snapshot");
}
Ok(doc)
}
Err(fetch_err) => match self.read_snapshot(framework).await? {
Some(doc) => {
tracing::warn!(
framework, error = %fetch_err,
"OSCAL catalog fetch failed; falling back to snapshot"
);
Ok(doc)
}
None => Err(fetch_err),
},
}
}
/// Load the OSCAL catalog for a compliance framework.
pub async fn load(&self, framework: ComplianceFramework) -> Result<OscalDocument, CoreError> {
self.load_token(&framework.to_string()).await
}
/// Load the code-checkable master-controls catalog
/// (`?framework=master-controls`).
pub async fn load_master_controls(&self) -> Result<OscalDocument, CoreError> {
self.load_token("master-controls").await
}
}
/// Order controls whose title/text mention the query context first (stable), then
/// truncate to the requested limit. Naive relevance — refined when the assessment
/// layer lands.
fn rank_and_truncate(mut controls: Vec<Control>, context: &str, limit: usize) -> Vec<Control> {
if !context.is_empty() {
let needle = context.to_lowercase();
controls.sort_by_key(|c| {
let hit =
c.title.to_lowercase().contains(&needle) || c.text.to_lowercase().contains(&needle);
u8::from(!hit)
});
}
controls.truncate(limit);
controls
}
impl ControlsProvider for OscalControlsProvider {
fn name(&self) -> &str {
"breakpilot-oscal"
}
async fn controls(&self, query: &ControlQuery<'_>) -> Result<Vec<Control>, CoreError> {
let mut out: Vec<Control> = Vec::new();
for &framework in query.frameworks {
match self.load(framework).await {
Ok(doc) => out.extend(doc.to_controls()),
Err(e) => {
tracing::warn!(%framework, error = %e, "skipping framework: catalog unavailable")
}
}
}
Ok(rank_and_truncate(out, query.context, query.limit))
}
}
#[cfg(test)]
#[allow(clippy::unwrap_used)]
mod tests {
use super::*;
const MINI_CATALOG: &str = r#"{"catalog":{"uuid":"u","metadata":{"title":"T",
"version":"1.0.0","oscal-version":"1.1.2","props":[{"name":"framework","value":"cra"}]},
"groups":[{"id":"g","title":"G","controls":[{"id":"cra-ai-1","title":"MFA",
"props":[],"parts":[{"name":"statement","prose":"require mfa"}]}]}]}}"#;
fn provider(dir: &std::path::Path) -> OscalControlsProvider {
OscalControlsProvider::new(reqwest::Client::new(), "http://unused/", None, dir)
}
#[test]
fn builds_catalog_url_and_snapshot_path() {
let p = provider(std::path::Path::new("/snap"));
assert_eq!(
p.catalog_url("cra"),
"http://unused/api/compliance/v1/oscal/catalog?framework=cra"
);
assert_eq!(
p.snapshot_path("cra"),
std::path::Path::new("/snap/oscal-catalog-cra.json")
);
}
#[test]
fn ranks_context_hits_first_then_truncates() {
let mk = |id: &str, title: &str| Control {
id: id.into(),
framework: ComplianceFramework::Cra,
title: title.into(),
text: String::new(),
source: None,
};
let controls = vec![
mk("a", "logging policy"),
mk("b", "multi-factor auth"),
mk("c", "backup"),
];
let ranked = rank_and_truncate(controls, "auth", 2);
assert_eq!(ranked.len(), 2);
assert_eq!(ranked[0].id, "b"); // the "auth" hit floats to the top
}
#[tokio::test]
async fn snapshot_round_trip_and_offline_fallback() {
let dir = std::env::temp_dir().join(format!("oscal-test-{}", uuid::Uuid::new_v4()));
let p = provider(&dir);
assert!(p.read_snapshot("cra").await.unwrap().is_none());
p.write_snapshot("cra", MINI_CATALOG.as_bytes())
.await
.unwrap();
let doc = p.read_snapshot("cra").await.unwrap().unwrap();
assert_eq!(doc.to_controls().len(), 1);
assert_eq!(doc.framework(), Some(ComplianceFramework::Cra));
let _ = std::fs::remove_dir_all(&dir);
}
}
@@ -0,0 +1,291 @@
//! Scan-pipeline integration for control triage.
//!
//! After the deterministic tools have produced findings, this stamps each finding
//! with the compliance control(s) it's evidence for and marks control-level false
//! positives — using the ingested OSCAL catalog for control text, the
//! `control-map` LUT for the finding→control link, and the grounded LLM judge to
//! confirm. Skipped entirely unless breakpilot is configured.
use std::collections::HashMap;
use std::path::Path;
use std::sync::Arc;
use compliance_core::control_check::{CandidateRegion, ControlCheckSpec};
use compliance_core::models::finding::{Finding, FindingStatus, Severity};
use compliance_core::models::onboarding::ComplianceFramework;
use compliance_core::AgentConfig;
use control_map::ControlMap;
use super::surface;
use super::{
ControlIndex, ControlTriage, GroundedControlChecker, LlmControlJudge, OscalControlsProvider,
SemanticControlChecker, TriageOutcome,
};
use crate::llm::LlmClient;
/// Nearest master controls judged per code region in the semantic pass.
const SEMANTIC_TOP_K: usize = 5;
/// Lines of context to read on each side of a finding's line.
const REGION_WINDOW: usize = 6;
/// Triage every finding in `findings` against the CRA control map: stamp
/// `control_refs` on confirmed findings and flag control false positives. Returns
/// the number of findings tagged with at least one control.
pub async fn triage_repo_findings(
config: &AgentConfig,
llm: Arc<LlmClient>,
repo_path: &Path,
findings: &mut [Finding],
) -> usize {
let Some(base_url) = config.breakpilot.base_url.clone() else {
return 0; // control triage is opt-in via BREAKPILOT_BASE_URL
};
let provider = OscalControlsProvider::new(
reqwest::Client::new(),
base_url,
config.breakpilot.token.clone(),
&config.breakpilot.snapshot_dir,
);
let specs = build_specs(&provider).await;
if specs.is_empty() {
return 0;
}
let map = match ControlMap::cra() {
Ok(m) => m,
Err(e) => {
tracing::warn!(error = %e, "control map failed to load; skipping control triage");
return 0;
}
};
let triage = ControlTriage::new(LlmControlJudge::new(llm), map, specs);
let mut tagged = 0;
for finding in findings.iter_mut() {
let (Some(file), Some(line)) = (finding.file_path.clone(), finding.line_number) else {
continue;
};
let Some(region) = fetch_region(repo_path, &file, line) else {
continue;
};
match triage.triage(finding, &region).await {
TriageOutcome::Confirmed(controls) => {
finding.control_refs = controls;
tagged += 1;
}
TriageOutcome::FalsePositive => {
finding.status = FindingStatus::FalsePositive;
finding.triage_action = Some("control_false_positive".to_string());
}
TriageOutcome::Unmapped => {}
}
}
tagged
}
/// Build the control requirement specs (by id) from the ingested OSCAL catalog.
async fn build_specs(provider: &OscalControlsProvider) -> HashMap<String, ControlCheckSpec> {
let mut specs = HashMap::new();
match provider.load(ComplianceFramework::Cra).await {
Ok(doc) => {
for control in doc.to_controls() {
specs.insert(
control.id.clone(),
ControlCheckSpec {
control_id: control.id,
title: control.title,
requirement: control.text,
default_cwe: None,
severity: Severity::Medium,
},
);
}
}
Err(e) => tracing::warn!(error = %e, "could not load control catalog for triage"),
}
specs
}
/// Absence-based control pass (the grounded half of the hybrid coverage): for each
/// control with a [`surface`] definition, deterministically retrieve the code
/// surfaces it governs (login routes, logging setup, update/download code) and have
/// the grounded judge decide whether the control holds there. Returns net-new
/// findings, each already tagged with its control and grounded to a real snippet.
///
/// Gated: the orchestrator runs this only when `breakpilot.grounded_control_checks`
/// is set. Absence detection is the least deterministic path (the judge decides
/// presence/absence, not a syntactic pattern), so it stays off until tuned live.
pub async fn grounded_surface_findings(
config: &AgentConfig,
llm: Arc<LlmClient>,
repo_path: &Path,
repo_id: &str,
) -> Vec<Finding> {
let Some(base_url) = config.breakpilot.base_url.clone() else {
return Vec::new();
};
let provider = OscalControlsProvider::new(
reqwest::Client::new(),
base_url,
config.breakpilot.token.clone(),
&config.breakpilot.snapshot_dir,
);
let specs = build_specs(&provider).await;
if specs.is_empty() {
return Vec::new();
}
let checker = GroundedControlChecker::new(LlmControlJudge::new(llm));
let mut out = Vec::new();
for surf in surface::SURFACES {
let Some(spec) = specs.get(surf.control_id) else {
continue; // catalog doesn't carry this control
};
let regions = surface::retrieve(repo_path, surf.terms);
if regions.is_empty() {
continue;
}
out.extend(checker.check(spec, &regions, repo_id).await);
}
out
}
/// Read a window of lines around `line` (1-based) from `repo_path/file`.
fn fetch_region(repo_path: &Path, file: &str, line: u32) -> Option<CandidateRegion> {
let content = std::fs::read_to_string(repo_path.join(file)).ok()?;
let lines: Vec<&str> = content.lines().collect();
if lines.is_empty() {
return None;
}
let center = (line.saturating_sub(1) as usize).min(lines.len() - 1);
let start = center.saturating_sub(REGION_WINDOW);
let end = (center + REGION_WINDOW + 1).min(lines.len());
Some(CandidateRegion {
file: file.to_string(),
start_line: (start as u32) + 1,
content: lines[start..end].join("\n"),
})
}
/// Master-controls **semantic** pass: for each finding's code region, retrieve the
/// top-K nearest master controls by embedding, have the grounded judge confirm,
/// and stamp the confirmed control ids onto the finding — the scale path for the
/// ~13.6k master-control corpus (which has no CWE to LUT on). Returns the number
/// of findings that gained a master-control ref.
///
/// Gated: the orchestrator runs this only when `breakpilot.semantic_mapping` is
/// set (default off, flipped on once the master-controls catalog is live). The
/// control embedding index is built once and cached to `snapshot_dir` keyed by
/// corpus hash ([`ControlIndex::load_or_build`]), so only the first scan after a
/// catalog change pays the embedding cost.
pub async fn semantic_stamp_findings(
config: &AgentConfig,
llm: Arc<LlmClient>,
repo_path: &Path,
findings: &mut [Finding],
) -> usize {
let Some(base_url) = config.breakpilot.base_url.clone() else {
return 0;
};
let provider = OscalControlsProvider::new(
reqwest::Client::new(),
base_url,
config.breakpilot.token.clone(),
&config.breakpilot.snapshot_dir,
);
let doc = match provider.load_master_controls().await {
Ok(d) => d,
Err(e) => {
tracing::warn!(error = %e, "master-controls catalog unavailable; skipping semantic pass");
return 0;
}
};
let specs: Vec<ControlCheckSpec> = doc
.to_controls()
.into_iter()
.map(|c| ControlCheckSpec {
control_id: c.id,
title: c.title,
requirement: c.text,
default_cwe: None,
severity: Severity::Medium,
})
.collect();
let cache_path =
Path::new(&config.breakpilot.snapshot_dir).join("control-index-master-controls.json");
let index = match ControlIndex::load_or_build(&llm, specs, &cache_path).await {
Ok(i) if !i.is_empty() => i,
Ok(_) => return 0,
Err(e) => {
tracing::warn!(error = %e, "failed to embed master-controls corpus");
return 0;
}
};
let checker = SemanticControlChecker::new(LlmControlJudge::new(llm.clone()));
let mut tagged = 0;
for finding in findings.iter_mut() {
if finding.status == FindingStatus::FalsePositive {
continue;
}
let (Some(file), Some(line)) = (finding.file_path.clone(), finding.line_number) else {
continue;
};
let Some(region) = fetch_region(repo_path, &file, line) else {
continue;
};
let region_emb = match llm.embed(vec![region.content.clone()]).await {
Ok(mut embs) => match embs.pop() {
Some(v) => v,
None => continue,
},
Err(e) => {
tracing::warn!(error = %e, "region embed failed; skipping finding");
continue;
}
};
let confirmed = checker
.check(
&index,
&region,
&region_emb,
SEMANTIC_TOP_K,
&finding.repo_id,
)
.await;
let before = finding.control_refs.len();
for f in confirmed {
for cref in f.control_refs {
if !finding.control_refs.contains(&cref) {
finding.control_refs.push(cref);
}
}
}
if finding.control_refs.len() > before {
tagged += 1;
}
}
tagged
}
#[cfg(test)]
mod tests {
use super::*;
#[test]
fn fetch_region_windows_around_the_line() {
let dir = std::env::temp_dir().join(format!("triage-region-{}", uuid::Uuid::new_v4()));
std::fs::create_dir_all(&dir).unwrap();
let file = "a.py";
std::fs::write(dir.join(file), "l1\nl2\nl3\nSECRET=1\nl5\nl6\n").unwrap();
let r = fetch_region(&dir, file, 4).unwrap();
assert!(r.content.contains("SECRET=1"));
assert_eq!(r.start_line, 1); // window clamps to file start
let _ = std::fs::remove_dir_all(&dir);
}
#[test]
fn fetch_region_missing_file_is_none() {
assert!(fetch_region(Path::new("/nonexistent"), "nope.py", 1).is_none());
}
}
+119
View File
@@ -0,0 +1,119 @@
//! Semantic control mapping: retrieve the top-K controls nearest a code region,
//! then confirm each with the grounded judge.
//!
//! The `region → controls` direction (vs. the CWE-LUT's `finding → control`) is
//! what scales to the full master-control corpus: the LLM only ever judges a
//! handful of retrieved candidates, and every surviving verdict is still anchored
//! to real code by the grounding gate.
use compliance_core::control_check::{ground, CandidateRegion};
use compliance_core::models::Finding;
use super::index::ControlIndex;
use super::judge::ControlJudge;
/// Retrieve → judge → ground, generic over the judge so tests use a stub.
pub struct SemanticControlChecker<J> {
judge: J,
}
impl<J: ControlJudge> SemanticControlChecker<J> {
pub fn new(judge: J) -> Self {
Self { judge }
}
/// Map a code region to the controls it violates. `region_embedding` is the
/// region's embedding (the caller computes it via the LLM); the top-`k`
/// nearest controls in `index` are judged and grounded.
pub async fn check(
&self,
index: &ControlIndex,
region: &CandidateRegion,
region_embedding: &[f64],
k: usize,
repo_id: &str,
) -> Vec<Finding> {
let candidates = index.nearest(region_embedding, k);
let mut findings = Vec::new();
for spec in &candidates {
let verdict = self.judge.judge(spec, region).await;
if let Some(finding) = ground(spec, region, &verdict, repo_id) {
findings.push(finding);
}
}
findings
}
}
#[cfg(test)]
mod tests {
use super::*;
use compliance_core::control_check::{ControlCheckSpec, LlmVerdict};
use compliance_core::models::finding::Severity;
struct StubJudge {
verdict: LlmVerdict,
}
impl ControlJudge for StubJudge {
async fn judge(&self, _s: &ControlCheckSpec, _r: &CandidateRegion) -> LlmVerdict {
self.verdict.clone()
}
}
fn spec(id: &str) -> ControlCheckSpec {
ControlCheckSpec {
control_id: id.into(),
title: id.into(),
requirement: id.into(),
default_cwe: None,
severity: Severity::Medium,
}
}
#[tokio::test]
async fn retrieves_then_grounds_the_nearest_control() {
let index = ControlIndex::from_embeddings(vec![
(spec("mc-near"), vec![1.0, 0.0]),
(spec("mc-far"), vec![0.0, 1.0]),
]);
let checker = SemanticControlChecker::new(StubJudge {
verdict: LlmVerdict {
violates: true,
snippet: "PASSWORD = \"admin\"".into(),
cwe: None,
confidence: 0.9,
},
});
let region = CandidateRegion {
file: "src/auth.py".into(),
start_line: 1,
content: "PASSWORD = \"admin\"\n".into(),
};
// Query embedding nearest to mc-near; k=1 → only mc-near is judged.
let findings = checker
.check(&index, &region, &[0.95, 0.05], 1, "repo")
.await;
assert_eq!(findings.len(), 1);
assert_eq!(findings[0].control_refs, vec!["mc-near".to_string()]);
}
#[tokio::test]
async fn ungrounded_verdict_is_dropped() {
let index = ControlIndex::from_embeddings(vec![(spec("mc-near"), vec![1.0, 0.0])]);
let checker = SemanticControlChecker::new(StubJudge {
verdict: LlmVerdict {
violates: true,
snippet: "not in the region".into(),
cwe: None,
confidence: 0.9,
},
});
let region = CandidateRegion {
file: "f".into(),
start_line: 1,
content: "real code\n".into(),
};
let findings = checker.check(&index, &region, &[1.0, 0.0], 1, "repo").await;
assert!(findings.is_empty());
}
}
+246
View File
@@ -0,0 +1,246 @@
//! Surface retrieval for absence-based controls.
//!
//! Some CRA controls are violated by an *absence* — no rate limiting on login, no
//! security logging, no signature check on an update — so there's no offending
//! pattern for semgrep to match. Instead we deterministically locate the code
//! *surface* the control governs (a login route, a logging setup, update/download
//! code) by identifier/route terms, then hand each surface region to the grounded
//! judge, which decides whether the control is satisfied there. The resulting
//! finding grounds to the surface snippet, so nothing fabricated survives.
//!
//! Retrieval is intentionally cheap and bounded: keyword match + a fixed window,
//! capped per control to keep the downstream LLM cost predictable.
use std::path::Path;
use compliance_core::control_check::CandidateRegion;
/// An absence-based control and the case-insensitive terms that mark the code
/// surface it governs.
pub struct Surface {
pub control_id: &'static str,
pub terms: &'static [&'static str],
}
/// The absence-based CRA controls we retrieve surfaces for — the grounded half of
/// the hybrid coverage (the pattern-expressible half is custom semgrep rules).
pub const SURFACES: &[Surface] = &[
Surface {
control_id: "cra-ai-6", // Integritaetspruefung
terms: &[
"checksum",
"sha256",
"signature",
"hmac",
"integrity",
"verify",
],
},
Surface {
control_id: "cra-ai-11", // Brute-Force-Schutz
terms: &[
"login",
"signin",
"authenticate",
"/auth",
"password",
"ratelimit",
],
},
Surface {
control_id: "cra-ai-24", // Security-Logging
terms: &["login", "authorize", "permission", "role", "admin", "audit"],
},
Surface {
control_id: "cra-ai-27", // Log-Integritaet und -Aufbewahrung
terms: &["logging", "logger", "getlogger", "audit_log"],
},
Surface {
control_id: "cra-ai-28", // Sichere Update-Mechanismen
terms: &["update", "upgrade", "download", "firmware"],
},
Surface {
control_id: "cra-ai-29", // Update-Authentizitaet
terms: &["update", "signature", "verify", "pubkey", "certificate"],
},
Surface {
control_id: "cra-ai-30", // Update-Integritaet
terms: &["update", "checksum", "digest", "integrity", "verify"],
},
];
/// Source file extensions worth reading (skip binaries/assets/lockfiles).
const CODE_EXTS: &[&str] = &[
"py", "js", "ts", "tsx", "jsx", "go", "java", "rb", "php", "rs", "cs", "kt",
];
/// Directories never worth walking.
const SKIP_DIRS: &[&str] = &[
".git",
"node_modules",
"target",
"vendor",
".venv",
"__pycache__",
"dist",
"build",
];
/// Lines of context on each side of a hit.
const WINDOW: usize = 6;
/// Cap on regions per control, to bound downstream LLM calls.
const MAX_REGIONS_PER_CONTROL: usize = 8;
/// Skip files larger than this (generated/minified).
const MAX_FILE_BYTES: u64 = 512 * 1024;
/// Deterministically retrieve up to [`MAX_REGIONS_PER_CONTROL`] code regions in
/// `repo_path` whose lines mention any of `terms`. Hits close together within a
/// file are merged into one region; results are capped to bound LLM cost.
pub fn retrieve(repo_path: &Path, terms: &[&str]) -> Vec<CandidateRegion> {
let lowered: Vec<String> = terms.iter().map(|t| t.to_lowercase()).collect();
let mut regions = Vec::new();
for entry in walk(repo_path) {
if regions.len() >= MAX_REGIONS_PER_CONTROL {
break;
}
let path = entry.path();
if !has_code_ext(path) {
continue;
}
let Ok(meta) = entry.metadata() else { continue };
if !meta.is_file() || meta.len() > MAX_FILE_BYTES {
continue;
}
let Ok(content) = std::fs::read_to_string(path) else {
continue;
};
let rel = path
.strip_prefix(repo_path)
.unwrap_or(path)
.to_string_lossy()
.to_string();
let lines: Vec<&str> = content.lines().collect();
let hits: Vec<usize> = lines
.iter()
.enumerate()
.filter(|(_, line)| {
let ll = line.to_lowercase();
lowered.iter().any(|t| ll.contains(t.as_str()))
})
.map(|(i, _)| i)
.collect();
for center in merge_centers(&hits) {
if regions.len() >= MAX_REGIONS_PER_CONTROL {
break;
}
let start = center.saturating_sub(WINDOW);
let end = (center + WINDOW + 1).min(lines.len());
regions.push(CandidateRegion {
file: rel.clone(),
start_line: (start as u32) + 1,
content: lines[start..end].join("\n"),
});
}
}
regions
}
/// Collapse ascending hit indices that fall within one window into a single
/// representative center, so overlapping regions aren't judged repeatedly.
fn merge_centers(hits: &[usize]) -> Vec<usize> {
let mut out: Vec<usize> = Vec::new();
for &h in hits {
match out.last() {
Some(&last) if h.saturating_sub(last) <= WINDOW => {}
_ => out.push(h),
}
}
out
}
fn has_code_ext(path: &Path) -> bool {
path.extension()
.and_then(|e| e.to_str())
.is_some_and(|e| CODE_EXTS.contains(&e))
}
fn walk(root: &Path) -> Vec<walkdir::DirEntry> {
walkdir::WalkDir::new(root)
.into_iter()
.filter_entry(|e| {
let name = e.file_name().to_string_lossy();
!SKIP_DIRS.contains(&name.as_ref())
})
.filter_map(|e| e.ok())
.collect()
}
#[cfg(test)]
#[allow(clippy::unwrap_used)]
mod tests {
use super::*;
fn write(dir: &Path, rel: &str, body: &str) {
let p = dir.join(rel);
if let Some(parent) = p.parent() {
std::fs::create_dir_all(parent).unwrap();
}
std::fs::write(p, body).unwrap();
}
fn terms_for(control_id: &str) -> &'static [&'static str] {
SURFACES
.iter()
.find(|s| s.control_id == control_id)
.unwrap()
.terms
}
#[test]
fn surfaces_cover_the_absence_based_controls() {
assert_eq!(SURFACES.len(), 7);
for id in [
"cra-ai-6",
"cra-ai-11",
"cra-ai-24",
"cra-ai-27",
"cra-ai-28",
"cra-ai-29",
"cra-ai-30",
] {
assert!(SURFACES.iter().any(|s| s.control_id == id), "{id} missing");
}
}
#[test]
fn retrieves_matching_region_with_context() {
let dir = std::env::temp_dir().join(format!("surface-{}", uuid::Uuid::new_v4()));
std::fs::create_dir_all(&dir).unwrap();
write(
&dir,
"app/auth.py",
"import x\n\n\n\n\n\n\ndef login(u, p):\n return check(u, p)\n",
);
let regions = retrieve(&dir, terms_for("cra-ai-11"));
assert_eq!(regions.len(), 1);
assert!(regions[0].content.contains("def login"));
assert_eq!(regions[0].file, "app/auth.py");
let _ = std::fs::remove_dir_all(&dir);
}
#[test]
fn skips_non_code_and_vendored() {
let dir = std::env::temp_dir().join(format!("surface-{}", uuid::Uuid::new_v4()));
std::fs::create_dir_all(&dir).unwrap();
write(&dir, "README.md", "login and password and audit\n"); // not code ext
write(&dir, "node_modules/pkg/index.js", "function login() {}\n"); // vendored
assert!(retrieve(&dir, terms_for("cra-ai-11")).is_empty());
let _ = std::fs::remove_dir_all(&dir);
}
#[test]
fn merges_adjacent_hits_into_one_region() {
// Two hits one line apart collapse to a single center/region.
assert_eq!(merge_centers(&[10, 11, 30]), vec![10, 30]);
assert_eq!(merge_centers(&[]), Vec::<usize>::new());
assert_eq!(merge_centers(&[5]), vec![5]);
}
}
+234
View File
@@ -0,0 +1,234 @@
//! Triage step: confirm/refute a deterministic tool finding against the controls
//! it maps to (via the `control-map` LUT), grounding the judgment.
//!
//! This is where the LLM finally enters — as a **false-positive filter over tool
//! output**, never as the detector (the ZeroFalse / IRIS pattern). A tool
//! (semgrep, gitleaks, syft/osv) detects deterministically; `controls_for(tool,
//! cwe)` attaches the finding to the control(s) it's evidence for; the grounded
//! judge then confirms or refutes each, and only judgments anchored to real code
//! survive.
use std::collections::HashMap;
use compliance_core::control_check::{ground, CandidateRegion, ControlCheckSpec};
use compliance_core::models::Finding;
use control_map::ControlMap;
use super::judge::ControlJudge;
/// What triage decided for one tool finding.
#[derive(Debug, Clone, PartialEq, Eq)]
pub enum TriageOutcome {
/// The finding maps to no control in the LUT — keep it, untagged.
Unmapped,
/// Maps to controls and the grounded judge confirmed at least one — keep the
/// finding and tag it with these control ids.
Confirmed(Vec<String>),
/// Maps to controls but the judge grounded none — treat as a false positive.
FalsePositive,
}
/// Triages tool findings against the control map, confirming with a grounded judge.
pub struct ControlTriage<J> {
judge: J,
map: ControlMap,
/// Control requirement specs (by control id), built from the ingested catalog.
specs: HashMap<String, ControlCheckSpec>,
}
impl<J: ControlJudge> ControlTriage<J> {
pub fn new(judge: J, map: ControlMap, specs: HashMap<String, ControlCheckSpec>) -> Self {
Self { judge, map, specs }
}
/// Triage one tool finding. `region` is the code around the finding, used as
/// the grounding evidence for the judge.
pub async fn triage(&self, finding: &Finding, region: &CandidateRegion) -> TriageOutcome {
// Match by CWE (off-the-shelf findings) and/or rule id (our custom
// detectors, which carry no LUT-bound CWE). A finding with neither is
// simply unmapped.
let mapped = self.map.controls_for_finding(
&finding.scanner,
finding.cwe.as_deref(),
finding.rule_id.as_deref(),
);
if mapped.is_empty() {
return TriageOutcome::Unmapped;
}
let mut confirmed = Vec::new();
for entry in mapped {
let Some(spec) = self.specs.get(&entry.control) else {
continue;
};
let verdict = self.judge.judge(spec, region).await;
// The verdict only counts if it grounds to real code in the region.
if ground(spec, region, &verdict, &finding.repo_id).is_some() {
confirmed.push(entry.control.clone());
}
}
if confirmed.is_empty() {
TriageOutcome::FalsePositive
} else {
TriageOutcome::Confirmed(confirmed)
}
}
}
#[cfg(test)]
mod tests {
use super::*;
use compliance_core::control_check::LlmVerdict;
use compliance_core::models::finding::Severity;
use compliance_core::models::scan::ScanType;
struct StubJudge {
verdict: LlmVerdict,
}
impl ControlJudge for StubJudge {
async fn judge(&self, _s: &ControlCheckSpec, _r: &CandidateRegion) -> LlmVerdict {
self.verdict.clone()
}
}
fn specs() -> HashMap<String, ControlCheckSpec> {
let mut m = HashMap::new();
m.insert(
"cra-ai-8".to_string(),
ControlCheckSpec {
control_id: "cra-ai-8".into(),
title: "No default passwords".into(),
requirement: "No default credentials".into(),
default_cwe: Some("CWE-798".into()),
severity: Severity::High,
},
);
m
}
fn semgrep_finding(cwe: &str) -> Finding {
let mut f = Finding::new(
"repo".into(),
"fp1".into(),
"semgrep".into(),
ScanType::Sast,
"hardcoded credential".into(),
"desc".into(),
Severity::High,
);
f.cwe = Some(cwe.into());
f
}
fn region() -> CandidateRegion {
CandidateRegion {
file: "src/auth.py".into(),
start_line: 1,
content: "PASSWORD = \"admin123\"\n".into(),
}
}
#[tokio::test]
async fn confirmed_finding_is_tagged_with_control() {
let triage = ControlTriage::new(
StubJudge {
verdict: LlmVerdict {
violates: true,
snippet: "PASSWORD = \"admin123\"".into(),
cwe: None,
confidence: 0.9,
},
},
ControlMap::cra().unwrap(),
specs(),
);
let out = triage.triage(&semgrep_finding("CWE-798"), &region()).await;
assert_eq!(out, TriageOutcome::Confirmed(vec!["cra-ai-8".to_string()]));
}
#[tokio::test]
async fn refuted_mapped_finding_is_false_positive() {
// Maps to cra-ai-8, but the judge doesn't confirm (no violation) → FP.
let triage = ControlTriage::new(
StubJudge {
verdict: LlmVerdict {
violates: false,
snippet: String::new(),
cwe: None,
confidence: 0.1,
},
},
ControlMap::cra().unwrap(),
specs(),
);
let out = triage.triage(&semgrep_finding("CWE-798"), &region()).await;
assert_eq!(out, TriageOutcome::FalsePositive);
}
#[tokio::test]
async fn custom_rule_finding_without_cwe_is_confirmed() {
// A custom detector finding carries a rule id but no LUT-bound CWE; it must
// still map (by rule id) and confirm.
let mut specs = specs();
specs.insert(
"cra-ai-1".to_string(),
ControlCheckSpec {
control_id: "cra-ai-1".into(),
title: "Secure-by-Default".into(),
requirement: "Ship secure defaults".into(),
default_cwe: None,
severity: Severity::Medium,
},
);
let triage = ControlTriage::new(
StubJudge {
verdict: LlmVerdict {
violates: true,
snippet: "app.run(debug=True)".into(),
cwe: None,
confidence: 0.9,
},
},
ControlMap::cra().unwrap(),
specs,
);
let mut f = Finding::new(
"repo".into(),
"fp".into(),
"semgrep".into(),
ScanType::Sast,
"flask debug".into(),
"desc".into(),
Severity::Medium,
);
f.rule_id = Some("tmp.x.cra-ai-1-flask-debug-enabled".into()); // no cwe
let region = CandidateRegion {
file: "app.py".into(),
start_line: 1,
content: "app.run(debug=True)\n".into(),
};
let out = triage.triage(&f, &region).await;
assert_eq!(out, TriageOutcome::Confirmed(vec!["cra-ai-1".to_string()]));
}
#[tokio::test]
async fn unmapped_cwe_is_left_untagged() {
let triage = ControlTriage::new(
StubJudge {
verdict: LlmVerdict {
violates: true,
snippet: "PASSWORD = \"admin123\"".into(),
cwe: None,
confidence: 0.9,
},
},
ControlMap::cra().unwrap(),
specs(),
);
let out = triage
.triage(&semgrep_finding("CWE-99999"), &region())
.await;
assert_eq!(out, TriageOutcome::Unmapped);
}
}
+34 -14
View File
@@ -249,16 +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(
@@ -475,14 +465,38 @@ impl Database {
)
.await?;
// werkbank_jobs: unique job id (idempotent enqueue by job id)
self.werkbank_jobs()
.create_index(
IndexModel::builder()
.keys(doc! { "job.id": 1 })
.options(IndexOptions::builder().unique(true).build())
.build(),
)
.await?;
// werkbank_jobs: lease query — oldest queued job for an executor
self.werkbank_jobs()
.create_index(
IndexModel::builder()
.keys(doc! { "status": 1, "job.executor": 1, "created_at": 1 })
.build(),
)
.await?;
// werkbank_jobs: visibility-timeout sweep of expired leases
self.werkbank_jobs()
.create_index(
IndexModel::builder()
.keys(doc! { "status": 1, "lease_expires_at": 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")
}
@@ -577,6 +591,12 @@ impl Database {
self.inner.collection("pentest_messages")
}
/// The Werkbank job queue (WB-02): declarative dynamic-execution jobs the
/// control plane enqueues and runners lease.
pub fn werkbank_jobs(&self) -> Collection<compliance_core::models::werkbank::JobRecord> {
self.inner.collection("werkbank_jobs")
}
#[allow(dead_code)]
pub fn raw_collection(&self, name: &str) -> Collection<mongodb::bson::Document> {
self.inner.collection(name)
+3
View File
@@ -27,6 +27,9 @@ pub enum AgentError {
#[error("Configuration error: {0}")]
Config(String),
#[error("Dynamic-execution error: {0}")]
Exec(#[from] werkbank_exec::ExecError),
#[error("{0}")]
Other(String),
}
+24
View File
@@ -32,6 +32,30 @@ pub fn hash_file(path: &Path) -> Result<(String, u64), AgentError> {
Ok((hex::encode(hasher.finalize()), total))
}
/// Store raw bytes in the content-addressed blob store under `base`, returning
/// the SHA-256 digest. Used to stash a small derived artifact (e.g. the extracted
/// PLC program source) so a Werkbank runner can fetch it by hash. Idempotent.
pub fn store_bytes(base: &Path, bytes: &[u8]) -> Result<String, AgentError> {
let sha = hex::encode(Sha256::digest(bytes));
let dir = base.join("blobs").join(&sha[0..2]);
fs::create_dir_all(&dir)?;
let dest = dir.join(&sha);
if !dest.exists() {
fs::write(&dest, bytes)?;
}
Ok(sha)
}
/// Read a blob's bytes by its SHA-256 digest. Rejects a non-hex/wrong-length hash
/// so a request can't traverse outside the blob store.
pub fn read_blob(base: &Path, sha: &str) -> Result<Vec<u8>, AgentError> {
if sha.len() != 64 || !sha.bytes().all(|b| b.is_ascii_hexdigit()) {
return Err(AgentError::Other(format!("invalid content hash '{sha}'")));
}
let path = base.join("blobs").join(&sha[0..2]).join(sha);
Ok(fs::read(path)?)
}
/// 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> {
+86 -4
View File
@@ -6,7 +6,7 @@
//! is also the reconciliation key against sibling products (a firmware sha256
//! matches tramiton's `Artifact.sha256`).
mod blob;
pub(crate) mod blob;
use std::collections::HashMap;
use std::path::{Path, PathBuf};
@@ -162,14 +162,27 @@ fn ingest_blob(
match blob::extract_zip(&stored, &dest) {
Ok(()) => dest,
Err(e) => {
// Not a zip (e.g. a tar.gz source archive) — keep the blob and
// note it so later stages can decide what to do.
// 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",
));
stored.clone()
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 {
@@ -186,6 +199,27 @@ fn ingest_blob(
})
}
/// 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 {
@@ -331,4 +365,52 @@ mod tests {
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 -1
View File
@@ -4,11 +4,11 @@ pub mod agent;
pub mod api;
pub mod classify;
pub mod config;
pub mod controls;
pub mod database;
pub mod error;
pub mod ingest;
pub mod llm;
pub mod migrate;
pub mod pentest;
pub mod pipeline;
pub mod rag;
@@ -17,3 +17,4 @@ pub mod ssh;
#[allow(dead_code)]
pub mod trackers;
pub mod webhooks;
pub mod werkbank;
+1 -54
View File
@@ -1,50 +1,4 @@
use compliance_agent::{agent, api, config, database, migrate, scheduler, ssh, webhooks};
/// Run the `migrate onboarding` subcommand and exit. Backfills (or reverts) the
/// unified `onboarded_targets` collection per tenant.
///
/// Usage: `compliance-agent migrate onboarding [--all | --tenant <id>] [--dry-run] [--revert]`
async fn run_migration(
args: &[String],
pool: &database::DatabasePool,
) -> Result<(), compliance_agent::error::AgentError> {
if args.get(2).map(String::as_str) != Some("onboarding") {
eprintln!(
"usage: compliance-agent migrate onboarding [--all | --tenant <id>] [--dry-run] [--revert]"
);
std::process::exit(2);
}
let has = |flag: &str| args.iter().any(|a| a == flag);
let dry_run = has("--dry-run");
let revert = has("--revert");
let tenant = args
.iter()
.position(|a| a == "--tenant")
.and_then(|i| args.get(i + 1))
.cloned();
let tenants: Vec<String> = if has("--all") {
pool.list_tenant_ids().await?
} else if let Some(t) = tenant {
vec![t]
} else {
eprintln!("specify --all or --tenant <id>");
std::process::exit(2);
};
for tenant_id in tenants {
let db = pool.for_tenant_id(&tenant_id).await?;
if revert {
migrate::onboarding::revert(&db).await?;
println!("[{tenant_id}] reverted onboarding backfill");
} else {
let report = migrate::onboarding::backfill_onboarded_targets(&db, dry_run).await?;
let prefix = if dry_run { "(dry-run) " } else { "" };
println!("[{tenant_id}] {prefix}{report:?}");
}
}
Ok(())
}
use compliance_agent::{agent, api, config, database, scheduler, ssh, webhooks};
#[tokio::main]
async fn main() -> Result<(), Box<dyn std::error::Error>> {
@@ -77,13 +31,6 @@ async fn main() -> Result<(), Box<dyn std::error::Error>> {
let db_pool =
database::DatabasePool::connect(&config.mongodb_uri, &config.mongodb_database).await?;
// One-shot subcommands run and exit without starting the servers.
let args: Vec<String> = std::env::args().collect();
if args.get(1).map(String::as_str) == Some("migrate") {
run_migration(&args, &db_pool).await?;
return Ok(());
}
let agent = agent::ComplianceAgent::new(config.clone(), db_pool);
tracing::info!("Starting scheduler...");
-8
View File
@@ -1,8 +0,0 @@
//! One-time data migrations.
//!
//! Currently just the onboarding backfill ([`onboarding`]), which folds the
//! legacy `repositories` and `dast_targets` collections into the unified
//! `onboarded_targets` collection, preserving `_id` so every downstream record
//! keyed by `repo_id` / `target_id` keeps resolving.
pub mod onboarding;
-406
View File
@@ -1,406 +0,0 @@
//! Backfill: legacy `repositories` + `dast_targets` → `onboarded_targets`.
//!
//! The transforms here are **id-preserving**: an [`OnboardedTarget`] keeps the
//! same `_id` as the `TrackedRepository` / `DastTarget` it came from, so every
//! downstream collection keyed by that hex id (findings, sbom, scan_runs,
//! graph, dast_*, pentest_*) keeps resolving with zero row rewrites, and
//! existing webhook URLs keep working. The mapping functions are pure and unit
//! tested; the DB orchestration (idempotent per-tenant backfill + revert) is a
//! thin driver over them.
use compliance_core::models::{
Artifact, ArtifactKind, DastTarget, DastTargetType, GitArtifactConfig, IssueTrackerConfig,
OnboardedTarget, TargetType, TrackedRepository, WebArtifactConfig,
};
use futures_util::TryStreamExt;
use mongodb::bson::{doc, Document};
use crate::database::Database;
use crate::error::AgentError;
/// Marker id in `schema_migrations` recording that the backfill has run.
const MIGRATION_MARKER: &str = "onboarding_backfill_v1";
/// Summary of a backfill run.
#[derive(Debug, Clone, Default, PartialEq, Eq)]
pub struct MigrationReport {
/// Repositories turned into onboarded targets.
pub repos_migrated: u64,
/// DAST targets folded into an existing (repo-linked) target as a LiveUrl.
pub dast_targets_folded: u64,
/// DAST targets with no repo link, migrated as standalone targets.
pub dast_targets_standalone: u64,
/// Records skipped because a target with that `_id` already existed.
pub skipped_existing: u64,
}
/// Map a legacy `DastTargetType` to a unified [`TargetType`]. REST/GraphQL APIs
/// are backend services; a browser app is a web app.
fn target_type_for_dast(kind: &DastTargetType) -> TargetType {
match kind {
DastTargetType::WebApp => TargetType::WebApp,
DastTargetType::RestApi | DastTargetType::GraphQl => TargetType::BackendService,
}
}
/// Build the LiveUrl artifact for a DAST target (its base URL + crawl config +
/// auth). Shared by fold-in and standalone migration.
pub fn dast_to_artifact(dast: &DastTarget) -> Artifact {
let mut artifact = Artifact::live_url(dast.base_url.clone());
artifact.web = Some(WebArtifactConfig {
target_kind: dast.target_type.clone(),
excluded_paths: dast.excluded_paths.clone(),
max_crawl_depth: dast.max_crawl_depth,
rate_limit: dast.rate_limit,
allow_destructive: dast.allow_destructive,
});
artifact.auth = dast.auth_config.clone().map(Into::into);
artifact
}
/// Map a `TrackedRepository` to an onboarded target, preserving `_id`. The git
/// remote becomes a `GitRepo` artifact carrying the repo's branch, watermark,
/// and auth; tracker config folds into `scan_config`.
///
/// `target_type` is a safe default (`BackendService`) — the classifier can
/// refine it later; `classification` is left `None` (unconfirmed).
pub fn repo_to_target(repo: &TrackedRepository) -> OnboardedTarget {
let mut target = OnboardedTarget::new(repo.name.clone(), TargetType::BackendService);
target.id = repo.id;
let mut artifact = Artifact::git_repo(repo.git_url.clone(), repo.default_branch.clone());
artifact.git = Some(GitArtifactConfig {
default_branch: repo.default_branch.clone(),
last_scanned_commit: repo.last_scanned_commit.clone(),
local_path: repo.local_path.clone(),
});
if repo.auth_token.is_some() || repo.auth_username.is_some() {
artifact.auth = Some(compliance_core::models::ArtifactAuth {
method: "token".to_string(),
username: repo.auth_username.clone(),
secret: repo.auth_token.clone(),
..Default::default()
});
}
target.artifacts.push(artifact);
if repo.tracker_type.is_some() {
target.scan_config.issue_tracker = Some(IssueTrackerConfig {
tracker_type: repo.tracker_type.clone(),
owner: repo.tracker_owner.clone(),
repo: repo.tracker_repo.clone(),
token: repo.tracker_token.clone(),
});
}
target.scan_schedule = repo.scan_schedule.clone();
target.webhook_enabled = repo.webhook_enabled;
target.webhook_secret = repo.webhook_secret.clone();
target.findings_count = repo.findings_count;
target.created_at = repo.created_at;
target.updated_at = repo.updated_at;
target
}
/// Append a DAST target's LiveUrl artifact onto an existing (repo-derived)
/// target. If the repo default was `BackendService` but the DAST target is a
/// browser web app, promote the type to `WebApp`.
pub fn fold_dast_into_target(target: &mut OnboardedTarget, dast: &DastTarget) {
if matches!(dast.target_type, DastTargetType::WebApp)
&& target.target_type == TargetType::BackendService
{
target.target_type = TargetType::WebApp;
}
if !target.has(ArtifactKind::LiveUrl) {
target.artifacts.push(dast_to_artifact(dast));
}
}
/// Map a repo-less DAST target to a standalone onboarded target, preserving `_id`.
pub fn dast_to_standalone_target(dast: &DastTarget) -> OnboardedTarget {
let mut target =
OnboardedTarget::new(dast.name.clone(), target_type_for_dast(&dast.target_type));
target.id = dast.id;
target.artifacts.push(dast_to_artifact(dast));
target.created_at = dast.created_at;
target.updated_at = dast.updated_at;
target
}
/// Whether the onboarding backfill has already been applied to this database.
pub async fn already_applied(db: &Database) -> Result<bool, AgentError> {
let found = db
.collection_named::<Document>("schema_migrations")
.find_one(doc! { "_id": MIGRATION_MARKER })
.await?;
Ok(found.is_some())
}
/// Backfill `onboarded_targets` from `repositories` + `dast_targets` for one
/// tenant database.
///
/// Id-preserving and **idempotent**: targets that already exist (by `_id`) are
/// skipped, so re-running is safe. With `dry_run`, computes the report without
/// writing. The legacy collections are never deleted; the only mutation outside
/// `onboarded_targets` is the history relink of folded DAST targets, which is
/// logged so [`revert`] can undo it.
pub async fn backfill_onboarded_targets(
db: &Database,
dry_run: bool,
) -> Result<MigrationReport, AgentError> {
let mut report = MigrationReport::default();
// 1. repositories -> onboarded_targets (preserve _id, skip existing).
let mut repos = db.repositories().find(doc! {}).await?;
while let Some(repo) = repos.try_next().await? {
let Some(id) = repo.id else { continue };
if db
.onboarded_targets()
.find_one(doc! { "_id": id })
.await?
.is_some()
{
report.skipped_existing += 1;
continue;
}
if !dry_run {
db.onboarded_targets()
.insert_one(repo_to_target(&repo))
.await?;
}
report.repos_migrated += 1;
}
// 2. dast_targets -> fold into the linked repo target, or migrate standalone.
let mut dasts = db.dast_targets().find(doc! {}).await?;
while let Some(dast) = dasts.try_next().await? {
let Some(dast_id) = dast.id else { continue };
let repo_oid = dast
.repo_id
.as_deref()
.and_then(|r| mongodb::bson::oid::ObjectId::parse_str(r).ok());
let linked = match repo_oid {
Some(oid) => db.onboarded_targets().find_one(doc! { "_id": oid }).await?,
None => None,
};
match (linked, repo_oid) {
// Fold into an existing repo-derived target.
(Some(mut target), Some(oid)) => {
if target.has(ArtifactKind::LiveUrl) {
report.skipped_existing += 1; // already folded on a prior run
continue;
}
fold_dast_into_target(&mut target, &dast);
if !dry_run {
db.onboarded_targets()
.replace_one(doc! { "_id": oid }, &target)
.await?;
relink_history(db, &dast_id.to_hex(), &oid.to_hex()).await?;
}
report.dast_targets_folded += 1;
}
// No linked repo target: migrate as a standalone target (keeps _id).
_ => {
if db
.onboarded_targets()
.find_one(doc! { "_id": dast_id })
.await?
.is_some()
{
report.skipped_existing += 1;
continue;
}
if !dry_run {
db.onboarded_targets()
.insert_one(dast_to_standalone_target(&dast))
.await?;
}
report.dast_targets_standalone += 1;
}
}
}
if !dry_run {
db.collection_named::<Document>("schema_migrations")
.update_one(
doc! { "_id": MIGRATION_MARKER },
doc! { "$set": { "applied_at": mongodb::bson::DateTime::now() } },
)
.upsert(true)
.await?;
}
Ok(report)
}
/// Relink DAST scan runs and pentest sessions from the old DAST target id to the
/// unified target id, logging each move so [`revert`] can undo it.
///
/// Note: if multiple DAST targets fold into the same repo target, revert
/// restores only the last-logged mapping — a rare edge. The source collections
/// (`repositories`, `dast_targets`) are never deleted, so no data is lost.
async fn relink_history(db: &Database, old_id: &str, new_id: &str) -> Result<(), AgentError> {
db.dast_scan_runs()
.update_many(
doc! { "target_id": old_id },
doc! { "$set": { "target_id": new_id } },
)
.await?;
db.pentest_sessions()
.update_many(
doc! { "target_id": old_id },
doc! { "$set": { "target_id": new_id } },
)
.await?;
db.collection_named::<Document>("onboarding_migration_log")
.insert_one(doc! { "old_target_id": old_id, "new_target_id": new_id })
.await?;
Ok(())
}
/// Undo the backfill: replay the relink log in reverse, drop `onboarded_targets`
/// and the log, and clear the marker. The legacy collections are untouched, so
/// this restores the pre-migration state.
pub async fn revert(db: &Database) -> Result<(), AgentError> {
let log = db.collection_named::<Document>("onboarding_migration_log");
let mut cursor = log.find(doc! {}).await?;
while let Some(entry) = cursor.try_next().await? {
if let (Ok(old), Ok(new)) = (
entry.get_str("old_target_id"),
entry.get_str("new_target_id"),
) {
db.dast_scan_runs()
.update_many(
doc! { "target_id": new },
doc! { "$set": { "target_id": old } },
)
.await?;
db.pentest_sessions()
.update_many(
doc! { "target_id": new },
doc! { "$set": { "target_id": old } },
)
.await?;
}
}
db.onboarded_targets().drop().await?;
log.drop().await?;
db.collection_named::<Document>("schema_migrations")
.delete_one(doc! { "_id": MIGRATION_MARKER })
.await?;
Ok(())
}
#[cfg(test)]
#[allow(clippy::expect_used, clippy::unwrap_used)]
mod tests {
use super::*;
use compliance_core::models::{DastAuthConfig, TrackerType};
fn repo() -> TrackedRepository {
let mut r = TrackedRepository::new("acme".to_string(), "https://git/acme.git".to_string());
r.id = Some(mongodb::bson::oid::ObjectId::new());
r.default_branch = "develop".to_string();
r.last_scanned_commit = Some("abc123".to_string());
r.auth_token = Some("pat".to_string());
r.auth_username = Some("bob".to_string());
r.tracker_type = Some(TrackerType::Gitea);
r.tracker_owner = Some("acme".to_string());
r.findings_count = 7;
r
}
fn dast(repo_id: Option<String>, kind: DastTargetType) -> DastTarget {
let mut d = DastTarget::new(
"acme-web".to_string(),
"https://acme.example.com".to_string(),
kind,
);
d.id = Some(mongodb::bson::oid::ObjectId::new());
d.repo_id = repo_id;
d.max_crawl_depth = 5;
d.auth_config = Some(DastAuthConfig {
method: "bearer".to_string(),
login_url: None,
username: None,
password: None,
token: Some("tok".to_string()),
headers: None,
});
d
}
#[test]
fn repo_maps_preserving_id_and_git_artifact() {
let r = repo();
let t = repo_to_target(&r);
assert_eq!(t.id, r.id); // id preserved
assert_eq!(t.findings_count, 7);
assert_eq!(t.scan_schedule, r.scan_schedule);
let git = t.code_artifact().expect("git artifact");
assert_eq!(git.kind, ArtifactKind::GitRepo);
assert_eq!(git.source_ref, "https://git/acme.git");
let gc = git.git.as_ref().expect("git config");
assert_eq!(gc.default_branch, "develop");
assert_eq!(gc.last_scanned_commit.as_deref(), Some("abc123"));
let auth = git.auth.as_ref().expect("auth");
assert_eq!(auth.secret.as_deref(), Some("pat"));
assert_eq!(auth.username.as_deref(), Some("bob"));
assert_eq!(
t.scan_config
.issue_tracker
.as_ref()
.and_then(|it| it.tracker_type.clone()),
Some(TrackerType::Gitea)
);
}
#[test]
fn standalone_dast_maps_preserving_id_and_live_url() {
let d = dast(None, DastTargetType::WebApp);
let t = dast_to_standalone_target(&d);
assert_eq!(t.id, d.id);
assert_eq!(t.target_type, TargetType::WebApp);
let url = t.live_url().expect("live url");
assert_eq!(url.source_ref, "https://acme.example.com");
let web = url.web.as_ref().expect("web config");
assert_eq!(web.max_crawl_depth, 5);
assert_eq!(
url.auth.as_ref().and_then(|a| a.secret.clone()),
Some("tok".to_string())
);
}
#[test]
fn rest_api_dast_maps_to_backend_service() {
let d = dast(None, DastTargetType::RestApi);
assert_eq!(
dast_to_standalone_target(&d).target_type,
TargetType::BackendService
);
}
#[test]
fn fold_adds_live_url_and_promotes_webapp() {
let mut t = repo_to_target(&repo());
assert_eq!(t.target_type, TargetType::BackendService);
fold_dast_into_target(&mut t, &dast(Some("x".to_string()), DastTargetType::WebApp));
assert_eq!(t.target_type, TargetType::WebApp); // promoted
assert!(t.has(ArtifactKind::LiveUrl));
assert!(t.has(ArtifactKind::GitRepo));
}
#[test]
fn fold_is_idempotent_on_live_url() {
let mut t = repo_to_target(&repo());
let d = dast(Some("x".to_string()), DastTargetType::WebApp);
fold_dast_into_target(&mut t, &d);
fold_dast_into_target(&mut t, &d);
let live_urls = t
.artifacts
.iter()
.filter(|a| a.kind == ArtifactKind::LiveUrl)
.count();
assert_eq!(live_urls, 1);
}
}
+3 -1
View File
@@ -342,7 +342,9 @@ mod tests {
pentest_imap_password: None,
admin_api_token: None,
tenant_registry_url: None,
unified_pipeline: false,
plc_runtime: compliance_core::PlcRuntimeConfig::default(),
werkbank_runner_token: None,
breakpilot: compliance_core::config::BreakpilotConfig::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));
}
}
+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");
}
}
@@ -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> {
+2
View File
@@ -10,7 +10,9 @@ 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;
+492 -184
View File
@@ -16,6 +16,7 @@ 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;
@@ -51,72 +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
@@ -130,7 +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
@@ -279,6 +215,68 @@ impl PipelineOrchestrator {
.await;
tracing::info!("[{repo_id}] Triaged: {triaged} findings passed confidence threshold");
// Stage 5b: control triage — stamp findings with the compliance control(s)
// they're evidence for and flag control false positives (grounded LLM over
// deterministic tool output). No-op unless breakpilot is configured.
self.update_phase(scan_run_id, "control_triage").await;
let tagged = crate::controls::triage_repo_findings(
&self.config,
self.llm.clone(),
&repo_path,
&mut all_findings,
)
.await;
if tagged > 0 {
tracing::info!("[{repo_id}] Control triage tagged {tagged} findings with control refs");
}
// Stage 5c: semantic control mapping — scale path for the master-controls
// corpus (no CWE to LUT on): embed each finding's region, retrieve the
// nearest master controls, grounded-judge, and stamp confirmed refs. Gated
// (default off) as the corpus embedding + per-finding judging is the heavy
// path; enabled once verified live against a deployed master-controls catalog.
if self.config.breakpilot.semantic_mapping {
self.update_phase(scan_run_id, "semantic_control_mapping")
.await;
let sem = crate::controls::semantic_stamp_findings(
&self.config,
self.llm.clone(),
&repo_path,
&mut all_findings,
)
.await;
if sem > 0 {
tracing::info!(
"[{repo_id}] Semantic mapping tagged {sem} findings with master-control refs"
);
}
}
// Stage 5d: grounded surface checks — the absence-based controls (no
// rate limiting, no security logging, no update-signature check) have no
// syntactic pattern to match, so we retrieve the code surface each governs
// and let the grounded judge decide whether it holds, producing net-new
// findings already tagged + grounded. Gated (default off): absence
// detection is the least deterministic path, kept off until tuned live.
if self.config.breakpilot.grounded_control_checks {
self.update_phase(scan_run_id, "grounded_control_checks")
.await;
let grounded = crate::controls::grounded_surface_findings(
&self.config,
self.llm.clone(),
&repo_path,
&repo_id,
)
.await;
if !grounded.is_empty() {
tracing::info!(
"[{repo_id}] Grounded surface checks raised {} control findings",
grounded.len()
);
all_findings.extend(grounded);
}
}
// Dedup against existing findings and insert new ones
let mut new_count = 0u32;
let mut new_findings: Vec<Finding> = Vec::new();
@@ -323,67 +321,12 @@ 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)
.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! {
"$setOnInsert": mongodb::bson::to_bson(&notification).unwrap_or_default()
};
if let Ok(result) = self
.db
.cve_notifications()
.update_one(notif_filter, notif_update)
.upsert(true)
.await
{
if result.upserted_id.is_some() {
new_notif_count += 1;
}
}
}
if new_notif_count > 0 {
tracing::info!("[{repo_id}] Created {new_notif_count} CVE notification(s)");
}
// Persist CVE alerts and create notifications (shared with the PLC path).
let new_notif_count = self
.persist_cve_alerts(&repo_id, &repo.name, &cve_alerts)
.await?;
if new_notif_count > 0 {
tracing::info!("[{repo_id}] Created {new_notif_count} CVE notification(s)");
}
// Stage 6: Issue Creation
@@ -396,20 +339,9 @@ impl PipelineOrchestrator {
tracing::warn!("[{repo_id}] Issue creation failed: {e}");
}
// Stage 7: Update repository
self.db
.repositories()
.update_one(
doc! { "_id": repo.id },
doc! {
"$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");
@@ -524,33 +456,440 @@ impl PipelineOrchestrator {
// 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 = repo_view_from_target(target, code);
let new_count = self.run_pipeline(&repo, scan_run_id).await?;
self.finalize_target(target, &repo, new_count).await?;
Ok(new_count)
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"
);
Ok(0)
}
None => {
// No code to scan. Firmware/PLC/mobile static scanners land in
// #128/#129/#130; DAST for a running URL still works when a
// DastTarget row exists (migrated targets).
// 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 only"
"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(0)
}
}
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())?;
werkbank_exec::plc::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 = werkbank_exec::plc::http_client()?;
let provisioner = werkbank_exec::plc::DockerSoftPlc::new(self.config.plc_runtime.clone());
let outcome = werkbank_exec::plc::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 = werkbank_exec::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,
@@ -703,7 +1042,7 @@ impl PipelineOrchestrator {
async fn finalize_target(
&self,
target: &OnboardedTarget,
repo: &TrackedRepository,
repo: &RepoView,
new_count: u32,
) -> Result<(), AgentError> {
let oid = match target.id {
@@ -751,37 +1090,6 @@ impl PipelineOrchestrator {
}
}
/// Build a legacy `TrackedRepository` view from an onboarded target's code
/// artifact, so the unified pipeline can reuse the existing repo pipeline. The
/// inverse of the migration's `repo_to_target`. `_id` is preserved so findings
/// and DAST lookups resolve against the same key.
fn repo_view_from_target(target: &OnboardedTarget, code: &Artifact) -> TrackedRepository {
let mut repo = TrackedRepository::new(target.name.clone(), code.source_ref.clone());
repo.id = target.id;
if let Some(git) = &code.git {
repo.default_branch = git.default_branch.clone();
repo.last_scanned_commit = git.last_scanned_commit.clone();
repo.local_path = git.local_path.clone();
}
if let Some(auth) = &code.auth {
repo.auth_token = auth.secret.clone();
repo.auth_username = auth.username.clone();
}
if let Some(it) = &target.scan_config.issue_tracker {
repo.tracker_type = it.tracker_type.clone();
repo.tracker_owner = it.owner.clone();
repo.tracker_repo = it.repo.clone();
repo.tracker_token = it.token.clone();
}
repo.scan_schedule = target.scan_schedule.clone();
repo.webhook_enabled = target.webhook_enabled;
repo.webhook_secret = target.webhook_secret.clone();
repo.findings_count = target.findings_count;
repo.created_at = target.created_at;
repo.updated_at = target.updated_at;
repo
}
/// Extract the scheme + host from a git URL.
/// e.g. "https://gitea.example.com/owner/repo.git" -> "https://gitea.example.com"
/// e.g. "ssh://git@gitea.example.com:22/owner/repo.git" -> "https://gitea.example.com"
@@ -840,7 +1148,7 @@ mod tests {
target.artifacts.push(artifact);
let code = target.code_artifact().expect("code artifact");
let repo = repo_view_from_target(&target, code);
let repo = RepoView::from_target(&target, code);
assert_eq!(repo.id, target.id); // preserved
assert_eq!(repo.git_url, "https://git/acme.git");
+20 -1
View File
@@ -75,10 +75,16 @@ pub fn build_scan_plan(target: &OnboardedTarget) -> ScanPlan {
}
/// Resolve the artifact a scan consumes. A "code" requirement (represented by
/// `GitRepo`) is satisfied by a git repo *or* a source archive.
/// `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()),
}
@@ -100,6 +106,7 @@ fn phase_for(scan: ScanType) -> ScanPhase {
ScanType::PlcControlLogic => ScanPhase::PlcAnalysis,
ScanType::MobileStatic => ScanPhase::MobileStatic,
ScanType::ContainerScan => ScanPhase::ContainerScan,
ScanType::IcsProbe => ScanPhase::IcsProbe,
}
}
@@ -174,6 +181,18 @@ mod tests {
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")]);
+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
}
+234
View File
@@ -0,0 +1,234 @@
//! 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 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");
}
}
+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
}
}
+70 -29
View File
@@ -1,4 +1,4 @@
use std::path::Path;
use std::path::{Path, PathBuf};
use compliance_core::models::{Finding, ScanType, Severity};
use compliance_core::traits::{ScanOutput, Scanner};
@@ -6,6 +6,30 @@ use compliance_core::CoreError;
use crate::pipeline::dedup;
/// Custom CRA-control detectors bundled into the binary and staged to a temp file
/// at scan time so semgrep can `--config` them alongside the auto ruleset. These
/// cover controls no off-the-shelf rule digs out (secure defaults, weak password
/// hashing, insecure session cookies, weak data-at-rest ciphers); each rule id is
/// keyed back to its control by the `control-map` LUT.
const CRA_RULES: &str = include_str!("../../rules/cra_semgrep.yaml");
/// Write the bundled CRA rules to a stable temp path (atomic: unique tmp +
/// rename). Returns `None` on failure — the scan then runs with auto rules only.
async fn stage_cra_rules() -> Option<PathBuf> {
let dir = std::env::temp_dir();
let path = dir.join("compliance-cra-semgrep.yaml");
let tmp = dir.join(format!("compliance-cra-semgrep.{}.tmp", std::process::id()));
if let Err(e) = tokio::fs::write(&tmp, CRA_RULES).await {
tracing::warn!(error = %e, "failed to stage custom CRA semgrep rules; using auto rules only");
return None;
}
if let Err(e) = tokio::fs::rename(&tmp, &path).await {
tracing::warn!(error = %e, "failed to stage custom CRA semgrep rules; using auto rules only");
return None;
}
Some(path)
}
pub struct SemgrepScanner;
impl Scanner for SemgrepScanner {
@@ -19,30 +43,26 @@ impl Scanner for SemgrepScanner {
#[tracing::instrument(skip_all)]
async fn scan(&self, repo_path: &Path, repo_id: &str) -> Result<ScanOutput, CoreError> {
let output = tokio::time::timeout(
std::time::Duration::from_secs(600),
tokio::process::Command::new("semgrep")
.args([
"--config=auto",
"--json",
"--quiet",
"--max-memory",
"500",
"--jobs",
"1",
])
.arg(repo_path)
.output(),
)
.await
.map_err(|_| CoreError::Scanner {
scanner: "semgrep".to_string(),
source: "timed out after 10 minutes".into(),
})?
.map_err(|e| CoreError::Scanner {
scanner: "semgrep".to_string(),
source: Box::new(e),
})?;
let cra_rules = stage_cra_rules().await;
let mut command = tokio::process::Command::new("semgrep");
command.arg("--config=auto");
if let Some(path) = &cra_rules {
command.arg(format!("--config={}", path.display()));
}
command
.args(["--json", "--quiet", "--max-memory", "500", "--jobs", "1"])
.arg(repo_path);
let output = tokio::time::timeout(std::time::Duration::from_secs(600), command.output())
.await
.map_err(|_| CoreError::Scanner {
scanner: "semgrep".to_string(),
source: "timed out after 10 minutes".into(),
})?
.map_err(|e| CoreError::Scanner {
scanner: "semgrep".to_string(),
source: Box::new(e),
})?;
if !output.status.success() && output.stdout.is_empty() {
let stderr = String::from_utf8_lossy(&output.stderr);
@@ -82,10 +102,7 @@ impl Scanner for SemgrepScanner {
finding.file_path = Some(r.path);
finding.line_number = Some(r.start.line);
finding.code_snippet = Some(r.extra.lines);
finding.cwe = r
.extra
.metadata
.and_then(|m| m.get("cwe").and_then(|v| v.as_str()).map(|s| s.to_string()));
finding.cwe = r.extra.metadata.as_ref().and_then(extract_cwe);
finding
})
.collect();
@@ -124,10 +141,34 @@ struct SemgrepExtra {
metadata: Option<serde_json::Value>,
}
/// semgrep emits `metadata.cwe` as a list of strings like
/// `"CWE-798: Use of Hard-coded Credentials"` (occasionally a bare string). Take
/// the first entry and normalise it to just the `CWE-NNN` id.
fn extract_cwe(metadata: &serde_json::Value) -> Option<String> {
let raw = metadata.get("cwe")?;
let text = match raw {
serde_json::Value::Array(items) => items.first()?.as_str()?,
serde_json::Value::String(s) => s.as_str(),
_ => return None,
};
let id = text.split(':').next().unwrap_or(text).trim();
(!id.is_empty()).then(|| id.to_string())
}
#[cfg(test)]
mod tests {
use super::*;
#[test]
fn extract_cwe_handles_list_and_normalises() {
let md = serde_json::json!({"cwe": ["CWE-798: Use of Hard-coded Credentials"]});
assert_eq!(extract_cwe(&md).as_deref(), Some("CWE-798"));
let bare = serde_json::json!({"cwe": "CWE-89"});
assert_eq!(extract_cwe(&bare).as_deref(), Some("CWE-89"));
let none = serde_json::json!({"severity": "ERROR"});
assert_eq!(extract_cwe(&none), None);
}
#[test]
fn deserialize_semgrep_output() {
let json = r#"{
+1 -1
View File
@@ -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
{
+10
View File
@@ -0,0 +1,10 @@
//! Werkbank control-plane: the dynamic-execution job queue.
//!
//! The control plane enqueues declarative [`Job`](compliance_core::models::werkbank::Job)s
//! and Werkbank runners lease, run, and complete them. [`queue::JobQueue`] is the
//! Mongo-backed queue behind that flow (WB-02); the runner-facing HTTP transport
//! and the runner itself land in later stories.
pub mod queue;
pub use queue::{JobQueue, SweepOutcome};
+309
View File
@@ -0,0 +1,309 @@
//! The Mongo-backed Werkbank job queue (WB-02).
//!
//! A pull queue: the control plane [`enqueue`](JobQueue::enqueue)s jobs; a runner
//! [`lease`](JobQueue::lease)s the oldest queued job it can run (matched by
//! executor + labels), [`heartbeat`](JobQueue::heartbeat)s while it works, and
//! [`complete`](JobQueue::complete)s it. Leases carry a visibility timeout: if a
//! runner dies mid-job its heartbeats stop, the lease expires, and
//! [`sweep_expired`](JobQueue::sweep_expired) returns the job to `queued` (or
//! `expired` once it has been retried too many times).
//!
//! All state transitions are single atomic Mongo updates guarded by the lease
//! token, so two runners can never both own a job. Every operation takes an
//! explicit `now` so the queue's time-dependent behaviour is deterministically
//! testable.
use std::time::Duration;
use chrono::{DateTime, Utc};
use mongodb::bson::{doc, Bson, DateTime as BsonDateTime};
use mongodb::error::{ErrorKind, WriteFailure};
use mongodb::options::ReturnDocument;
use mongodb::Collection;
use compliance_core::models::werkbank::{
Executor, HeartbeatAck, Job, JobRecord, JobResult, JobStatus, LeasedJob,
};
use crate::database::Database;
use crate::error::AgentError;
/// The non-terminal states a job can be swept or cancelled from.
const ACTIVE_STATES: [&str; 2] = ["leased", "running"];
/// Every terminal state (no further transitions).
const TERMINAL_STATES: [&str; 4] = ["succeeded", "failed", "expired", "cancelled"];
/// What a visibility-timeout sweep did.
#[derive(Debug, Clone, Copy, Default, PartialEq, Eq)]
pub struct SweepOutcome {
/// Expired-lease jobs returned to `queued` for another runner.
pub requeued: u64,
/// Jobs that had exhausted their attempts and were marked `expired`.
pub expired: u64,
}
/// The Mongo-backed job queue.
pub struct JobQueue {
coll: Collection<JobRecord>,
}
impl JobQueue {
/// Build a queue over a tenant database's `werkbank_jobs` collection.
pub fn new(db: &Database) -> Self {
Self {
coll: db.werkbank_jobs(),
}
}
/// Enqueue a job. Idempotent by job id: a job that is already present is a
/// no-op. Returns `true` if this call inserted it, `false` if it existed.
pub async fn enqueue(&self, job: Job, now: DateTime<Utc>) -> Result<bool, AgentError> {
let record = JobRecord::queued(job, now);
match self.coll.insert_one(&record).await {
Ok(_) => Ok(true),
Err(e) if is_duplicate_key(&e) => Ok(false),
Err(e) => Err(e.into()),
}
}
/// Atomically lease the oldest `queued` job this runner can run — matched by
/// executor and by labels (every label the job requires must be one the
/// runner advertises). Returns the job plus a lease token, or `None` if
/// nothing is runnable.
pub async fn lease(
&self,
runner_id: &str,
executor: Executor,
runner_labels: &[String],
lease_ttl: Duration,
now: DateTime<Utc>,
) -> Result<Option<LeasedJob>, AgentError> {
let token = uuid::Uuid::new_v4().to_string();
let expires = bson_dt(now + ttl(lease_ttl));
let executor_bson = mongodb::bson::to_bson(&executor).unwrap_or(Bson::Null);
let filter = doc! {
"status": "queued",
"cancel_requested": { "$ne": true },
"job.executor": executor_bson,
// Every label the job requires must be in the runner's set — i.e. the
// job has no label that is not offered by the runner. Absent/empty
// job labels match any runner.
"job.labels": { "$not": { "$elemMatch": { "$nin": runner_labels.to_vec() } } },
};
let update = doc! {
"$set": {
"status": "leased",
"lease_token": &token,
"leased_by": runner_id,
"lease_expires_at": expires,
"heartbeat_at": bson_dt(now),
"updated_at": bson_dt(now),
},
"$inc": { "attempts": 1 },
};
let record = self
.coll
.find_one_and_update(filter, update)
.sort(doc! { "created_at": 1 }) // FIFO
.return_document(ReturnDocument::After)
.await?;
Ok(record.map(|r| LeasedJob {
job: r.job,
lease_token: token,
}))
}
/// Extend a lease and report whether the job has been asked to cancel.
/// Transitions the job to `running` on the first heartbeat. Returns `None`
/// when the lease is no longer valid (token mismatch, or the job is already
/// terminal) — the runner should then abandon the work.
pub async fn heartbeat(
&self,
job_id: &str,
lease_token: &str,
lease_ttl: Duration,
now: DateTime<Utc>,
) -> Result<Option<HeartbeatAck>, AgentError> {
let filter = doc! {
"job.id": job_id,
"lease_token": lease_token,
"status": { "$in": ACTIVE_STATES.to_vec() },
};
let update = doc! {
"$set": {
"status": "running",
"lease_expires_at": bson_dt(now + ttl(lease_ttl)),
"heartbeat_at": bson_dt(now),
"updated_at": bson_dt(now),
},
};
let record = self
.coll
.find_one_and_update(filter, update)
.return_document(ReturnDocument::After)
.await?;
Ok(record.map(|r| HeartbeatAck {
cancelled: r.cancel_requested,
}))
}
/// Record a job's terminal result. Guarded by the lease token and only from
/// an active (`leased`/`running`) state, so it is idempotent — a duplicate or
/// late submission after the job already finished matches nothing. Returns
/// `true` if this call recorded the result.
pub async fn complete(
&self,
job_id: &str,
lease_token: &str,
result: &JobResult,
now: DateTime<Utc>,
) -> Result<bool, AgentError> {
let status = result.status.unwrap_or(JobStatus::Failed);
let status_bson = mongodb::bson::to_bson(&status).unwrap_or(Bson::String("failed".into()));
let result_bson =
mongodb::bson::to_bson(result).map_err(|e| AgentError::Other(e.to_string()))?;
let filter = doc! {
"job.id": job_id,
"lease_token": lease_token,
"status": { "$in": ACTIVE_STATES.to_vec() },
};
let update = doc! {
"$set": {
"status": status_bson,
"result": result_bson,
"lease_token": Bson::Null,
"lease_expires_at": Bson::Null,
"updated_at": bson_dt(now),
},
};
let res = self.coll.update_one(filter, update).await?;
Ok(res.modified_count == 1)
}
/// Request cancellation of a job. A still-`queued` job is cancelled outright;
/// an in-flight one is flagged so the runner sees it on its next heartbeat and
/// tears down. Returns `true` if a non-terminal job matched.
pub async fn cancel(&self, job_id: &str, now: DateTime<Utc>) -> Result<bool, AgentError> {
let filter = doc! {
"job.id": job_id,
"status": { "$nin": TERMINAL_STATES.to_vec() },
};
// Pipeline update: flag cancellation, and if still queued flip straight to
// cancelled (nothing is running it).
let pipeline = vec![doc! {
"$set": {
"cancel_requested": true,
"status": {
"$cond": [ { "$eq": ["$status", "queued"] }, "cancelled", "$status" ]
},
"updated_at": bson_dt(now),
}
}];
let res = self.coll.update_one(filter, pipeline).await?;
Ok(res.matched_count == 1)
}
/// Sweep leases whose visibility timeout has elapsed: return them to `queued`
/// for another runner, or mark them `expired` once they have been leased
/// `max_attempts` times. This is what makes a crashed runner's job recover.
pub async fn sweep_expired(
&self,
now: DateTime<Utc>,
max_attempts: u32,
// (kept explicit rather than a const so callers can tune retry policy)
) -> Result<SweepOutcome, AgentError> {
let now_bson = bson_dt(now);
let max = i64::from(max_attempts);
let requeue = self
.coll
.update_many(
doc! {
"status": { "$in": ACTIVE_STATES.to_vec() },
"lease_expires_at": { "$lt": &now_bson },
"attempts": { "$lt": max },
},
doc! { "$set": {
"status": "queued",
"lease_token": Bson::Null,
"leased_by": Bson::Null,
"lease_expires_at": Bson::Null,
"updated_at": &now_bson,
} },
)
.await?;
let expire = self
.coll
.update_many(
doc! {
"status": { "$in": ACTIVE_STATES.to_vec() },
"lease_expires_at": { "$lt": &now_bson },
"attempts": { "$gte": max },
},
doc! { "$set": {
"status": "expired",
"lease_token": Bson::Null,
"lease_expires_at": Bson::Null,
"updated_at": &now_bson,
} },
)
.await?;
Ok(SweepOutcome {
requeued: requeue.modified_count,
expired: expire.modified_count,
})
}
/// Fetch a job record by job id (inspection / control-plane reads).
pub async fn get(&self, job_id: &str) -> Result<Option<JobRecord>, AgentError> {
Ok(self.coll.find_one(doc! { "job.id": job_id }).await?)
}
}
/// A `chrono::Duration` for a lease TTL, saturating rather than panicking on an
/// absurd input (`chrono::Duration::seconds` panics past its internal bound).
fn ttl(d: Duration) -> chrono::Duration {
let secs = i64::try_from(d.as_secs()).unwrap_or(i64::MAX);
chrono::Duration::try_seconds(secs).unwrap_or(chrono::Duration::MAX)
}
/// A chrono instant as a BSON date (so Mongo stores/compares it as a real date).
fn bson_dt(dt: DateTime<Utc>) -> BsonDateTime {
BsonDateTime::from_chrono(dt)
}
/// Whether a Mongo error is a duplicate-key (E11000) violation — a job with this
/// id is already enqueued.
fn is_duplicate_key(e: &mongodb::error::Error) -> bool {
match &*e.kind {
ErrorKind::Write(WriteFailure::WriteError(we)) => we.code == 11000,
_ => false,
}
}
#[cfg(test)]
mod tests {
use super::*;
#[test]
fn ttl_saturates_and_converts() {
assert_eq!(ttl(Duration::from_secs(30)), chrono::Duration::seconds(30));
// An absurd TTL saturates instead of panicking.
assert_eq!(ttl(Duration::from_secs(u64::MAX)), chrono::Duration::MAX);
}
#[test]
fn state_constants_are_disjoint() {
for s in ACTIVE_STATES {
assert!(
!TERMINAL_STATES.contains(&s),
"{s} cannot be both active and terminal"
);
}
}
}
+54 -39
View File
@@ -2,6 +2,10 @@
//
// Spins up the agent API server on a random port with an isolated test
// database. Each test gets a fresh database that is dropped on cleanup.
//
// Included via `mod common;` in several test binaries; not every binary uses
// every helper, so allow dead code here.
#![allow(dead_code)]
use std::sync::Arc;
@@ -11,6 +15,55 @@ use compliance_agent::database::DatabasePool;
use compliance_core::AgentConfig;
use secrecy::SecretString;
/// The runner bearer token wired into the test config.
pub const TEST_RUNNER_TOKEN: &str = "test-runner-token";
/// A minimal dev [`AgentConfig`] for tests: unauthenticated (no Keycloak), the
/// Werkbank runner API enabled with [`TEST_RUNNER_TOKEN`].
pub fn dev_config(mongodb_uri: String, db_name: String) -> AgentConfig {
AgentConfig {
mongodb_uri,
mongodb_database: db_name,
litellm_url: std::env::var("TEST_LITELLM_URL")
.unwrap_or_else(|_| "http://localhost:4000".into()),
litellm_api_key: SecretString::from(String::new()),
litellm_model: "gpt-4o".into(),
litellm_embed_model: "text-embedding-3-small".into(),
agent_port: 0, // not used — we bind ourselves
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,
gitlab_url: None,
gitlab_token: None,
gitlab_webhook_secret: None,
jira_url: None,
jira_email: None,
jira_api_token: None,
jira_project_key: None,
searxng_url: None,
nvd_api_key: None,
keycloak_url: None,
keycloak_realm: None,
keycloak_admin_username: None,
keycloak_admin_password: None,
pentest_verification_email: None,
pentest_imap_host: None,
pentest_imap_port: None,
pentest_imap_tls: false,
pentest_imap_username: None,
pentest_imap_password: None,
admin_api_token: None,
tenant_registry_url: None,
plc_runtime: compliance_core::PlcRuntimeConfig::default(),
werkbank_runner_token: Some(SecretString::from(TEST_RUNNER_TOKEN.to_string())),
breakpilot: compliance_core::config::BreakpilotConfig::default(),
}
}
/// A running test server with a unique database.
pub struct TestServer {
pub base_url: String,
@@ -33,45 +86,7 @@ impl TestServer {
.await
.expect("Failed to build DatabasePool");
let config = AgentConfig {
mongodb_uri: mongodb_uri.clone(),
mongodb_database: db_name.clone(),
litellm_url: std::env::var("TEST_LITELLM_URL")
.unwrap_or_else(|_| "http://localhost:4000".into()),
litellm_api_key: SecretString::from(String::new()),
litellm_model: "gpt-4o".into(),
litellm_embed_model: "text-embedding-3-small".into(),
agent_port: 0, // not used — we bind ourselves
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,
gitlab_url: None,
gitlab_token: None,
gitlab_webhook_secret: None,
jira_url: None,
jira_email: None,
jira_api_token: None,
jira_project_key: None,
searxng_url: None,
nvd_api_key: None,
keycloak_url: None,
keycloak_realm: None,
keycloak_admin_username: None,
keycloak_admin_password: None,
pentest_verification_email: None,
pentest_imap_host: None,
pentest_imap_port: None,
pentest_imap_tls: false,
pentest_imap_username: None,
pentest_imap_password: None,
admin_api_token: None,
tenant_registry_url: None,
unified_pipeline: false,
};
let config = dev_config(mongodb_uri.clone(), db_name.clone());
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);
@@ -3,5 +3,4 @@ mod dast;
mod findings;
mod health;
mod onboarding;
mod repositories;
mod stats;
@@ -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;
@@ -1,156 +0,0 @@
// Integration tests for the onboarding backfill migration.
//
// Requires MongoDB (set TEST_MONGODB_URI if not at the default).
// Not run in CI (which is `--lib` only) — run locally:
// cargo test -p compliance-agent --test e2e migration
use compliance_agent::database::{Database, DatabasePool};
use compliance_agent::migrate::onboarding;
use compliance_core::models::{
ArtifactKind, DastTarget, DastTargetType, TargetType, TrackedRepository,
};
use mongodb::bson::{doc, Document};
async fn fresh_db() -> (DatabasePool, String, Database) {
let uri = std::env::var("TEST_MONGODB_URI")
.unwrap_or_else(|_| "mongodb://root:example@localhost:27017/?authSource=admin".into());
// Prefix must fit the pool's 30-char cap (`<prefix>_<32 hex>` <= 63).
let prefix = format!("t_{}", &uuid::Uuid::new_v4().simple().to_string()[..16]);
let pool = DatabasePool::connect(&uri, &prefix)
.await
.expect("connect mongo");
let db = pool.for_tenant_id("t1").await.expect("tenant db");
(pool, prefix, db)
}
async fn cleanup(pool: &DatabasePool, prefix: &str) {
if let Ok(names) = pool.client().list_database_names().await {
for n in names {
if n.starts_with(prefix) {
pool.client().database(&n).drop().await.ok();
}
}
}
}
#[tokio::test]
async fn backfill_folds_relinks_is_idempotent_and_reversible() {
let (pool, prefix, db) = fresh_db().await;
// Seed a repo.
let repo = TrackedRepository::new("acme".into(), "https://git/acme.git".into());
let repo_id = db
.repositories()
.insert_one(repo)
.await
.expect("insert repo")
.inserted_id
.as_object_id()
.expect("repo oid");
// A DAST target linked to the repo (folds + promotes to WebApp + relinks).
let mut linked = DastTarget::new(
"acme-web".into(),
"https://acme.example.com".into(),
DastTargetType::WebApp,
);
linked.repo_id = Some(repo_id.to_hex());
let linked_id = db
.dast_targets()
.insert_one(linked)
.await
.expect("insert linked dast")
.inserted_id
.as_object_id()
.expect("linked oid");
// A repo-less DAST target (standalone).
let standalone = DastTarget::new(
"acme-api".into(),
"https://api.acme.com".into(),
DastTargetType::RestApi,
);
let standalone_id = db
.dast_targets()
.insert_one(standalone)
.await
.expect("insert standalone dast")
.inserted_id
.as_object_id()
.expect("standalone oid");
// A DAST scan run pointing at the linked target — should be relinked to the repo.
db.collection_named::<Document>("dast_scan_runs")
.insert_one(doc! { "target_id": linked_id.to_hex(), "status": "completed" })
.await
.expect("insert dast run");
// --- Backfill ---
assert!(!onboarding::already_applied(&db).await.unwrap());
let report = onboarding::backfill_onboarded_targets(&db, false)
.await
.expect("backfill");
assert_eq!(report.repos_migrated, 1);
assert_eq!(report.dast_targets_folded, 1);
assert_eq!(report.dast_targets_standalone, 1);
assert!(onboarding::already_applied(&db).await.unwrap());
// Repo target: preserved _id, has git + folded live-url, promoted to WebApp.
let repo_target = db
.onboarded_targets()
.find_one(doc! { "_id": repo_id })
.await
.unwrap()
.expect("repo target");
assert!(repo_target.has(ArtifactKind::GitRepo));
assert!(repo_target.has(ArtifactKind::LiveUrl));
assert_eq!(repo_target.target_type, TargetType::WebApp);
// Standalone target: preserved _id, live-url, backend service.
let standalone_target = db
.onboarded_targets()
.find_one(doc! { "_id": standalone_id })
.await
.unwrap()
.expect("standalone target");
assert!(standalone_target.has(ArtifactKind::LiveUrl));
assert_eq!(standalone_target.target_type, TargetType::BackendService);
// The DAST run was relinked from the old dast id to the repo (unified) id.
let run = db
.collection_named::<Document>("dast_scan_runs")
.find_one(doc! {})
.await
.unwrap()
.expect("run");
assert_eq!(run.get_str("target_id").unwrap(), repo_id.to_hex());
// --- Idempotent: re-run migrates nothing new ---
let again = onboarding::backfill_onboarded_targets(&db, false)
.await
.expect("backfill again");
assert_eq!(again.repos_migrated, 0);
assert_eq!(again.dast_targets_folded, 0);
assert_eq!(again.dast_targets_standalone, 0);
assert!(again.skipped_existing >= 2);
// --- Revert: onboarded targets gone, relink undone, marker cleared ---
onboarding::revert(&db).await.expect("revert");
assert_eq!(
db.onboarded_targets()
.count_documents(doc! {})
.await
.unwrap(),
0
);
let run_after = db
.collection_named::<Document>("dast_scan_runs")
.find_one(doc! {})
.await
.unwrap()
.expect("run");
assert_eq!(run_after.get_str("target_id").unwrap(), linked_id.to_hex());
assert!(!onboarding::already_applied(&db).await.unwrap());
cleanup(&pool, &prefix).await;
}
@@ -7,4 +7,3 @@
// Or nightly: (via CI with MongoDB service container)
mod api;
mod migration;
+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");
+291
View File
@@ -0,0 +1,291 @@
//! Integration tests for the Werkbank runner endpoints (WB-05).
//!
//! Drives the real HTTP handlers (lease/heartbeat/complete) against a live Mongo:
//! a runner leases a seeded job, completes it, and the result's findings are
//! persisted against the job's target. Also checks the bearer-token gate. Skips
//! cleanly when no Mongo is reachable.
#![allow(clippy::expect_used, clippy::unwrap_used)]
mod common;
use std::sync::Arc;
use axum::routing::{get, post};
use axum::{middleware, Extension, Router};
use compliance_agent::agent::ComplianceAgent;
use compliance_agent::api::handlers::werkbank_jobs;
use compliance_agent::database::DatabasePool;
use compliance_agent::werkbank::JobQueue;
use compliance_core::models::werkbank::{InputRef, Job, JobResult, JobStatus, LeasedJob};
use compliance_core::models::{
Artifact, Finding, OnboardedTarget, PlcFormat, ScanType, Severity, TargetType,
};
use common::{dev_config, TEST_RUNNER_TOKEN};
const TENANT: &str = "dev";
/// A running werkbank API on a random port, or `None` if no Mongo.
struct Harness {
base_url: String,
client: reqwest::Client,
pool: DatabasePool,
db_name: String,
}
async fn start() -> Option<Harness> {
let uri = std::env::var("TEST_MONGODB_URI")
.unwrap_or_else(|_| "mongodb://root:example@localhost:27017/?authSource=admin".into());
let db_name = format!("wba_{}", &uuid::Uuid::new_v4().simple().to_string()[..12]);
let pool = match DatabasePool::connect(&uri, &db_name).await {
Ok(p) => p,
Err(_) => {
eprintln!("SKIP werkbank_api: no MongoDB reachable at {uri}");
return None;
}
};
// Touch the tenant DB so indexes are ensured before the queue is used.
pool.for_tenant_id(TENANT).await.expect("tenant db");
let agent = ComplianceAgent::new(dev_config(uri, db_name.clone()), pool.clone());
let app = Router::new()
.route("/api/v1/werkbank/jobs/lease", post(werkbank_jobs::lease))
.route(
"/api/v1/werkbank/jobs/heartbeat",
post(werkbank_jobs::heartbeat),
)
.route(
"/api/v1/werkbank/jobs/complete",
post(werkbank_jobs::complete),
)
.route(
"/api/v1/werkbank/jobs/enqueue",
post(werkbank_jobs::enqueue),
)
.route(
"/api/v1/werkbank/artifacts/{hash}",
get(werkbank_jobs::serve_artifact),
)
.layer(middleware::from_fn(werkbank_jobs::require_runner_token))
.layer(Extension(Arc::new(agent)));
let listener = tokio::net::TcpListener::bind("127.0.0.1:0").await.unwrap();
let port = listener.local_addr().unwrap().port();
tokio::spawn(async move {
axum::serve(listener, app).await.ok();
});
Some(Harness {
base_url: format!("http://127.0.0.1:{port}"),
client: reqwest::Client::new(),
pool,
db_name,
})
}
impl Harness {
fn post(
&self,
path: &str,
token: Option<&str>,
body: serde_json::Value,
) -> reqwest::RequestBuilder {
let mut r = self
.client
.post(format!("{}{path}", self.base_url))
.json(&body);
if let Some(t) = token {
r = r.bearer_auth(t);
}
r
}
async fn cleanup(&self) {
let _ = self
.pool
.client()
.database(&format!("{}_{TENANT}", self.db_name))
.drop()
.await;
}
}
fn finding_for(target: &str, fp: &str) -> Finding {
let mut f = Finding::new(
target.to_string(),
fp.to_string(),
"ics-probe".to_string(),
ScanType::IcsProbe,
"Modbus exposed".to_string(),
"unauthenticated".to_string(),
Severity::Critical,
);
f.rule_id = Some("ics-modbus-exposed".to_string());
f
}
#[tokio::test]
async fn lease_complete_persists_findings_against_the_target() {
let Some(h) = start().await else { return };
let db = h.pool.for_tenant_id(TENANT).await.unwrap();
let queue = JobQueue::new(&db);
// Seed a queued job.
let job = Job::plc_provision("job-1", TENANT, "target-1", InputRef::blob("sha256:x"), 180);
assert!(queue.enqueue(job, chrono::Utc::now()).await.unwrap());
// Lease it over HTTP.
let resp = h
.post(
"/api/v1/werkbank/jobs/lease",
Some(TEST_RUNNER_TOKEN),
serde_json::json!({
"tenant": TENANT, "runner_id": "r1", "executor": "docker",
"labels": [], "lease_ttl_secs": 60
}),
)
.send()
.await
.unwrap();
assert_eq!(resp.status(), 200, "lease should return a job");
let leased: LeasedJob = resp.json().await.unwrap();
assert_eq!(leased.job.id, "job-1");
// Complete it with a finding.
let mut result = JobResult::succeeded("job-1");
result.findings = vec![finding_for("target-1", "fp-abc")];
let resp = h
.post(
"/api/v1/werkbank/jobs/complete",
Some(TEST_RUNNER_TOKEN),
serde_json::json!({
"tenant": TENANT, "job_id": "job-1",
"lease_token": leased.lease_token, "result": result
}),
)
.send()
.await
.unwrap();
assert_eq!(resp.status(), 200);
assert!(resp.json::<serde_json::Value>().await.unwrap()["recorded"]
.as_bool()
.unwrap());
// The job is now succeeded, and the finding was persisted to the target.
assert_eq!(
queue.get("job-1").await.unwrap().unwrap().status,
JobStatus::Succeeded
);
let stored = db
.findings()
.find_one(mongodb::bson::doc! { "fingerprint": "fp-abc" })
.await
.unwrap();
assert!(stored.is_some(), "finding should be persisted");
h.cleanup().await;
}
#[tokio::test]
async fn enqueue_extracts_program_stores_a_blob_and_serves_it() {
let Some(h) = start().await else { return };
let db = h.pool.for_tenant_id(TENANT).await.unwrap();
// A PlcSps target with a single complete ST program uploaded.
let dir = std::env::temp_dir().join(format!("wbq-prog-{}", uuid::Uuid::new_v4()));
std::fs::create_dir_all(&dir).unwrap();
let st = dir.join("main.st");
std::fs::write(
&st,
"PROGRAM Main\nEND_PROGRAM\nCONFIGURATION C\n RESOURCE R\nEND_CONFIGURATION\n",
)
.unwrap();
let mut target = OnboardedTarget::new("plc".into(), TargetType::PlcSps);
let mut art = Artifact::plc_project("main.st", PlcFormat::StructuredText);
art.stored_path = Some(st.to_string_lossy().to_string());
target.artifacts.push(art);
let ins = db.onboarded_targets().insert_one(&target).await.unwrap();
let target_id = ins.inserted_id.as_object_id().unwrap().to_hex();
// Enqueue → a plc-provision job whose program is a content-addressed blob.
let resp = h
.post(
"/api/v1/werkbank/jobs/enqueue",
Some(TEST_RUNNER_TOKEN),
serde_json::json!({ "tenant": TENANT, "target_id": target_id }),
)
.send()
.await
.unwrap();
assert_eq!(resp.status(), 200, "enqueue should succeed");
let body: serde_json::Value = resp.json().await.unwrap();
let job_id = body["job_id"].as_str().unwrap().to_string();
let rec = JobQueue::new(&db).get(&job_id).await.unwrap().unwrap();
let hash = rec
.job
.inputs
.get("program")
.and_then(|i| i.blob.clone())
.expect("program blob");
// Serve the blob back and confirm it's the program source (what the runner
// would fetch).
let served = h
.client
.get(format!("{}/api/v1/werkbank/artifacts/{hash}", h.base_url))
.bearer_auth(TEST_RUNNER_TOKEN)
.send()
.await
.unwrap();
assert_eq!(served.status(), 200);
assert!(served.text().await.unwrap().contains("CONFIGURATION"));
h.cleanup().await;
let _ = std::fs::remove_dir_all(&dir);
}
#[tokio::test]
async fn empty_queue_leases_nothing() {
let Some(h) = start().await else { return };
let resp = h
.post(
"/api/v1/werkbank/jobs/lease",
Some(TEST_RUNNER_TOKEN),
serde_json::json!({
"tenant": TENANT, "runner_id": "r1", "executor": "docker",
"labels": [], "lease_ttl_secs": 60
}),
)
.send()
.await
.unwrap();
assert_eq!(resp.status(), 204, "no job → 204");
h.cleanup().await;
}
#[tokio::test]
async fn runner_endpoints_require_the_bearer_token() {
let Some(h) = start().await else { return };
let body = serde_json::json!({
"tenant": TENANT, "runner_id": "r1", "executor": "docker",
"labels": [], "lease_ttl_secs": 60
});
let no_token = h
.post("/api/v1/werkbank/jobs/lease", None, body.clone())
.send()
.await
.unwrap();
assert_eq!(no_token.status(), 401, "missing token → 401");
let bad_token = h
.post("/api/v1/werkbank/jobs/lease", Some("wrong"), body)
.send()
.await
.unwrap();
assert_eq!(bad_token.status(), 401, "wrong token → 401");
h.cleanup().await;
}
+258
View File
@@ -0,0 +1,258 @@
//! Integration tests for the Werkbank job queue (WB-02).
//!
//! Exercises the atomic lease/heartbeat/complete/sweep flow against a real
//! MongoDB — the guarantees (idempotent enqueue, single-owner lease, visibility
//! timeout) are Mongo-semantics-dependent and can't be unit-tested in isolation.
//! Skips cleanly when no Mongo is reachable (set `TEST_MONGODB_URI` to point at
//! one; defaults to the local dev cluster).
#![allow(clippy::expect_used, clippy::unwrap_used)]
use std::time::Duration;
use chrono::{DateTime, TimeZone, Utc};
use compliance_agent::database::Database;
use compliance_agent::werkbank::JobQueue;
use compliance_core::models::werkbank::{Executor, InputRef, Job, JobResult};
/// Connect + ensure indexes on a throwaway database, or `None` if no Mongo.
async fn setup() -> Option<(JobQueue, mongodb::Database)> {
let uri = std::env::var("TEST_MONGODB_URI")
.unwrap_or_else(|_| "mongodb://root:example@localhost:27017/?authSource=admin".into());
let db_name = format!("wbq_{}", &uuid::Uuid::new_v4().simple().to_string()[..12]);
let db = match Database::connect(&uri, &db_name).await {
Ok(d) => d,
Err(_) => {
eprintln!("SKIP werkbank_queue: no MongoDB reachable at {uri}");
return None;
}
};
db.ensure_indexes().await.expect("ensure indexes");
let queue = JobQueue::new(&db);
Some((queue, db.inner().clone()))
}
fn base_time() -> DateTime<Utc> {
Utc.timestamp_opt(1_700_000_000, 0).unwrap()
}
fn job(id: &str) -> Job {
Job::plc_provision(id, "acme", "target-1", InputRef::blob("sha256:abc"), 180)
}
fn job_with_labels(id: &str, labels: &[&str]) -> Job {
let mut j = job(id);
j.labels = labels.iter().map(|s| s.to_string()).collect();
j
}
macro_rules! skip_if_no_mongo {
() => {
match setup().await {
Some(v) => v,
None => return,
}
};
}
#[tokio::test]
async fn enqueue_is_idempotent() {
let (q, db) = skip_if_no_mongo!();
let now = base_time();
assert!(q.enqueue(job("j1"), now).await.expect("enqueue"));
// Same id again — no duplicate row, reports "already present".
assert!(!q.enqueue(job("j1"), now).await.expect("enqueue2"));
let rec = q.get("j1").await.expect("get").expect("exists");
assert_eq!(
rec.status,
compliance_core::models::werkbank::JobStatus::Queued
);
assert_eq!(rec.attempts, 0);
db.drop().await.ok();
}
#[tokio::test]
async fn lease_matches_executor_and_labels_and_is_fifo() {
let (q, db) = skip_if_no_mongo!();
let t0 = base_time();
// Two docker jobs (j_old older than j_new) + one requiring a kvm label.
q.enqueue(job("j_old"), t0).await.unwrap();
q.enqueue(job("j_new"), t0 + chrono::Duration::seconds(5))
.await
.unwrap();
q.enqueue(job_with_labels("j_kvm", &["kvm=true"]), t0)
.await
.unwrap();
// Wrong executor: a shell runner leases nothing.
assert!(q
.lease("r-shell", Executor::Shell, &[], Duration::from_secs(30), t0)
.await
.unwrap()
.is_none());
// A docker runner without the kvm label gets the oldest label-free job (FIFO).
let leased = q
.lease("r1", Executor::Docker, &[], Duration::from_secs(30), t0)
.await
.unwrap()
.expect("leased");
assert_eq!(leased.job.id, "j_old", "oldest matching job first");
assert!(!leased.lease_token.is_empty());
// The kvm job stays unleased for that runner (missing label)...
let none = q
.lease("r1", Executor::Docker, &[], Duration::from_secs(30), t0)
.await
.unwrap()
.expect("next");
assert_eq!(none.job.id, "j_new", "label-free job, not the kvm one");
// ...but a runner advertising kvm can take it.
let kvm = q
.lease(
"r2",
Executor::Docker,
&["kvm=true".to_string(), "arch=amd64".to_string()],
Duration::from_secs(30),
t0,
)
.await
.unwrap()
.expect("kvm leased");
assert_eq!(kvm.job.id, "j_kvm");
// A leased job increments attempts and is no longer queued.
let rec = q.get("j_old").await.unwrap().unwrap();
assert_eq!(rec.attempts, 1);
assert_eq!(rec.leased_by.as_deref(), Some("r1"));
db.drop().await.ok();
}
#[tokio::test]
async fn heartbeat_extends_lease_and_surfaces_cancel() {
let (q, db) = skip_if_no_mongo!();
let now = base_time();
q.enqueue(job("j1"), now).await.unwrap();
let leased = q
.lease("r1", Executor::Docker, &[], Duration::from_secs(30), now)
.await
.unwrap()
.unwrap();
// A valid heartbeat moves it to running and reports not-cancelled.
let ack = q
.heartbeat("j1", &leased.lease_token, Duration::from_secs(30), now)
.await
.unwrap()
.expect("valid lease");
assert!(!ack.cancelled);
assert_eq!(
q.get("j1").await.unwrap().unwrap().status,
compliance_core::models::werkbank::JobStatus::Running
);
// A wrong token is a lost lease.
assert!(q
.heartbeat("j1", "wrong-token", Duration::from_secs(30), now)
.await
.unwrap()
.is_none());
// Cancelling an in-flight job flags it; the next heartbeat reports cancelled.
assert!(q.cancel("j1", now).await.unwrap());
let ack = q
.heartbeat("j1", &leased.lease_token, Duration::from_secs(30), now)
.await
.unwrap()
.expect("still leased");
assert!(ack.cancelled);
db.drop().await.ok();
}
#[tokio::test]
async fn complete_is_idempotent_and_token_guarded() {
let (q, db) = skip_if_no_mongo!();
let now = base_time();
q.enqueue(job("j1"), now).await.unwrap();
let leased = q
.lease("r1", Executor::Docker, &[], Duration::from_secs(30), now)
.await
.unwrap()
.unwrap();
// Wrong token cannot complete.
let mut result = JobResult::succeeded("j1");
result.findings = Vec::new();
assert!(!q.complete("j1", "nope", &result, now).await.unwrap());
// The lease holder completes it once...
assert!(q
.complete("j1", &leased.lease_token, &result, now)
.await
.unwrap());
let rec = q.get("j1").await.unwrap().unwrap();
assert_eq!(
rec.status,
compliance_core::models::werkbank::JobStatus::Succeeded
);
assert!(rec.result.is_some());
assert!(rec.lease_token.is_none(), "lease cleared on completion");
// ...and a second (duplicate) completion is a no-op.
assert!(!q
.complete("j1", &leased.lease_token, &result, now)
.await
.unwrap());
db.drop().await.ok();
}
#[tokio::test]
async fn sweep_requeues_expired_then_expires_after_max_attempts() {
let (q, db) = skip_if_no_mongo!();
let t0 = base_time();
q.enqueue(job("j1"), t0).await.unwrap();
// Lease #1 with a 10s TTL; then time jumps past expiry.
q.lease("r1", Executor::Docker, &[], Duration::from_secs(10), t0)
.await
.unwrap()
.unwrap();
let past = t0 + chrono::Duration::seconds(60);
// attempts=1 < max=2 → requeued.
let swept = q.sweep_expired(past, 2).await.unwrap();
assert_eq!(swept.requeued, 1);
assert_eq!(swept.expired, 0);
assert_eq!(
q.get("j1").await.unwrap().unwrap().status,
compliance_core::models::werkbank::JobStatus::Queued
);
// Lease #2 (attempts=2), let it expire again → now expired (>= max).
q.lease("r2", Executor::Docker, &[], Duration::from_secs(10), past)
.await
.unwrap()
.unwrap();
let later = past + chrono::Duration::seconds(60);
let swept = q.sweep_expired(later, 2).await.unwrap();
assert_eq!(swept.requeued, 0);
assert_eq!(swept.expired, 1);
assert_eq!(
q.get("j1").await.unwrap().unwrap().status,
compliance_core::models::werkbank::JobStatus::Expired
);
db.drop().await.ok();
}
+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"
+5 -5
View File
@@ -64,11 +64,11 @@ struct Claims {
const PUBLIC_ENDPOINTS: &[&str] = &["/api/v1/health"];
/// Path prefixes that bypass JWT validation. The admin sub-router
/// (`/api/v1/admin/*`) has its own static-bearer middleware and must
/// not be routed through the customer-JWT path — a Keycloak token
/// always carries a single tenant_id and would semantically conflict
/// with cross-tenant admin operations.
const PUBLIC_PREFIXES: &[&str] = &["/api/v1/admin/"];
/// (`/api/v1/admin/*`) and the Werkbank runner API (`/api/v1/werkbank/*`)
/// have their own static-bearer middleware and must not be routed through the
/// customer-JWT path — a Keycloak token always carries a single tenant_id and
/// would semantically conflict with these cross-tenant / machine operations.
const PUBLIC_PREFIXES: &[&str] = &["/api/v1/admin/", "/api/v1/werkbank/"];
/// Middleware that validates Bearer JWT tokens against Keycloak's JWKS
/// and attaches a `TenantContext` extension on success.
+95 -5
View File
@@ -49,11 +49,101 @@ 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>,
/// When true, `run_scan` dispatches to the unified `run_target` pipeline
/// (reads `onboarded_targets`) instead of the legacy repository pipeline.
/// Env `UNIFIED_PIPELINE`. Defaults on; set `UNIFIED_PIPELINE=0` to use the
/// legacy repository pipeline.
pub unified_pipeline: bool,
/// 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,
/// Static bearer for the Werkbank runner endpoints
/// (`/api/v1/werkbank/jobs/*`). Machine auth for runners leasing/completing
/// jobs — NOT a Keycloak JWT, since a runner acts across tenants. When
/// `None`, those endpoints are not mounted at all.
pub werkbank_runner_token: Option<SecretString>,
/// Source for the OSCAL control catalog pulled from breakpilot-compliance
/// (drives the [`crate::traits::ControlsProvider`]). Disabled when
/// `base_url` is `None`.
pub breakpilot: BreakpilotConfig,
}
/// Where to pull the OSCAL control catalog from breakpilot-compliance, and where
/// to snapshot it for deterministic / offline reuse.
#[derive(Debug, Clone)]
pub struct BreakpilotConfig {
/// Backend base URL (e.g. `http://backend-compliance:8002`). `None` disables
/// the OSCAL controls provider.
pub base_url: Option<String>,
/// Optional bearer token for the catalog endpoint.
pub token: Option<SecretString>,
/// Directory for catalog snapshots.
pub snapshot_dir: String,
/// Enable the master-controls **semantic** mapping pass (embed regions,
/// retrieve nearest controls, grounded-judge). Off by default: it is the
/// scale path and stays gated until verified live against a deployed
/// master-controls catalog.
pub semantic_mapping: bool,
/// Enable the **grounded surface** pass for absence-based controls (retrieve
/// the code surface a control governs, judge whether it holds). Off by
/// default: absence detection is the least deterministic path and stays gated
/// until tuned against live scans.
pub grounded_control_checks: bool,
}
impl Default for BreakpilotConfig {
fn default() -> Self {
Self {
base_url: None,
token: None,
snapshot_dir: "/data/compliance-scanner/oscal".to_string(),
semantic_mapping: false,
grounded_control_checks: false,
}
}
}
/// 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)]
+205
View File
@@ -0,0 +1,205 @@
//! Grounded control-driven checking.
//!
//! Turns a *text* control into findings via an LLM used as a **pattern-recognizer**
//! whose output is grounded to real code — so a hallucinated finding cannot
//! survive. Determinism is structural, not a prompt plea:
//!
//! 1. the LLM only ever judges *retrieved* regions — it can't invent findings in
//! code it never saw;
//! 2. a verdict becomes a finding only if its quoted snippet appears **verbatim**
//! in the region, and the line is recomputed from that match — the model's own
//! line number is never trusted ([`ground`]);
//! 3. verdicts are cached by content hash ([`cache_key`]) so re-scans reproduce.
//!
//! The LLM supplies cross-language / cross-stack pattern recognition; this module
//! supplies the determinism.
use serde::{Deserialize, Serialize};
use sha2::{Digest, Sha256};
use crate::models::finding::{Finding, Severity};
use crate::models::scan::ScanType;
/// A control rendered as a check the LLM judges code against.
#[derive(Debug, Clone, Serialize, Deserialize)]
pub struct ControlCheckSpec {
/// Stable control id, e.g. `"cra-ai-8"`.
pub control_id: String,
/// Short control title (used in the finding title).
pub title: String,
/// The requirement text the LLM judges against (control objective/statement).
pub requirement: String,
/// CWE to fall back to when the model doesn't supply one.
pub default_cwe: Option<String>,
/// Severity for findings raised from this control.
pub severity: Severity,
}
/// A retrieved code region the LLM judges — never the whole repo.
#[derive(Debug, Clone)]
pub struct CandidateRegion {
/// Repo-relative path.
pub file: String,
/// 1-based line number of the region's first line in `file`.
pub start_line: u32,
/// The region's source text.
pub content: String,
}
/// The LLM's structured verdict for one (control, region). `snippet` is the
/// verbatim code the model claims proves the violation — it is the anchor the
/// grounding gate checks.
#[derive(Debug, Clone)]
pub struct LlmVerdict {
pub violates: bool,
pub snippet: String,
pub cwe: Option<String>,
pub confidence: f64,
}
/// The grounding gate. A verdict becomes a [`Finding`] only if it claims a
/// violation AND its quoted `snippet` appears verbatim in `region.content`; the
/// finding's line is computed from the match, so a fabricated or mis-located
/// snippet is dropped. Pure — no LLM, no I/O.
pub fn ground(
spec: &ControlCheckSpec,
region: &CandidateRegion,
verdict: &LlmVerdict,
repo_id: &str,
) -> Option<Finding> {
if !verdict.violates {
return None;
}
let snippet = verdict.snippet.trim();
if snippet.is_empty() {
return None;
}
// Grounding: the quoted snippet must literally exist in the retrieved region.
let pos = region.content.find(snippet)?;
// Recompute the real line from the match — never trust the model's number.
let newlines_before = region.content[..pos].matches('\n').count();
let line = region.start_line + newlines_before as u32;
let mut finding = Finding::new(
repo_id.to_string(),
control_finding_fingerprint(&spec.control_id, &region.file, snippet),
"control-check".to_string(),
ScanType::CodeReview,
format!("{}: {}", spec.control_id, spec.title),
format!(
"Control {} appears violated ({}) at {}:{line}",
spec.control_id, spec.requirement, region.file
),
spec.severity.clone(),
);
finding.cwe = verdict.cwe.clone().or_else(|| spec.default_cwe.clone());
finding.file_path = Some(region.file.clone());
finding.line_number = Some(line);
finding.code_snippet = Some(snippet.to_string());
finding.confidence = Some(verdict.confidence);
// Carry the control reference on the finding.
finding.control_refs = vec![spec.control_id.clone()];
Some(finding)
}
/// Deterministic cache key for a (control, region, model, prompt-version) verdict
/// so identical inputs reproduce the same verdict without another LLM call.
pub fn cache_key(
control_id: &str,
region_content: &str,
model: &str,
prompt_version: &str,
) -> String {
hash_parts(&[control_id, region_content, model, prompt_version])
}
fn control_finding_fingerprint(control_id: &str, file: &str, snippet: &str) -> String {
hash_parts(&[control_id, file, snippet])
}
fn hash_parts(parts: &[&str]) -> String {
let mut hasher = Sha256::new();
for part in parts {
hasher.update(part.as_bytes());
hasher.update([0u8]); // domain separator between parts
}
hex::encode(hasher.finalize())
}
#[cfg(test)]
mod tests {
use super::*;
fn spec() -> ControlCheckSpec {
ControlCheckSpec {
control_id: "cra-ai-8".into(),
title: "No default passwords".into(),
requirement: "Products must not ship default credentials".into(),
default_cwe: Some("CWE-798".into()),
severity: Severity::High,
}
}
fn region() -> CandidateRegion {
CandidateRegion {
file: "src/auth.py".into(),
start_line: 10,
content: "def login():\n PASSWORD = \"admin123\"\n return PASSWORD\n".into(),
}
}
#[test]
fn grounds_real_snippet_with_recomputed_line() {
let v = LlmVerdict {
violates: true,
snippet: "PASSWORD = \"admin123\"".into(),
cwe: None,
confidence: 0.9,
};
let f = ground(&spec(), &region(), &v, "repo").expect("should ground");
assert_eq!(f.line_number, Some(11)); // 2nd line of a region starting at 10
assert_eq!(f.cwe.as_deref(), Some("CWE-798")); // fell back to the spec default
assert_eq!(f.control_refs, vec!["cra-ai-8".to_string()]); // control ref carried
assert_eq!(f.file_path.as_deref(), Some("src/auth.py"));
assert_eq!(f.code_snippet.as_deref(), Some("PASSWORD = \"admin123\""));
}
#[test]
fn drops_fabricated_snippet_not_in_region() {
let v = LlmVerdict {
violates: true,
snippet: "SECRET = \"totally-made-up\"".into(),
cwe: None,
confidence: 0.99,
};
assert!(ground(&spec(), &region(), &v, "repo").is_none());
}
#[test]
fn drops_non_violation_and_empty_snippet() {
let no = LlmVerdict {
violates: false,
snippet: "PASSWORD = \"admin123\"".into(),
cwe: None,
confidence: 0.9,
};
assert!(ground(&spec(), &region(), &no, "repo").is_none());
let empty = LlmVerdict {
violates: true,
snippet: " ".into(),
cwe: None,
confidence: 0.9,
};
assert!(ground(&spec(), &region(), &empty, "repo").is_none());
}
#[test]
fn cache_key_and_fingerprint_are_deterministic() {
assert_eq!(cache_key("c", "x", "m", "v"), cache_key("c", "x", "m", "v"));
assert_ne!(cache_key("c", "x", "m", "v"), cache_key("c", "y", "m", "v"));
assert_eq!(
control_finding_fingerprint("c", "f", "s"),
control_finding_fingerprint("c", "f", "s")
);
}
}
+2 -1
View File
@@ -1,4 +1,5 @@
pub mod config;
pub mod control_check;
pub mod db;
pub mod error;
pub mod models;
@@ -13,6 +14,6 @@ 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};
+5
View File
@@ -76,6 +76,10 @@ pub struct Finding {
pub triage_rationale: Option<String>,
/// Developer feedback on finding quality
pub developer_feedback: Option<String>,
/// Compliance control ids this finding is evidence for (stamped by control
/// triage against the `control-map` LUT). Empty when unmapped.
#[serde(default)]
pub control_refs: Vec<String>,
#[serde(with = "super::serde_helpers::bson_datetime")]
pub created_at: DateTime<Utc>,
#[serde(with = "super::serde_helpers::bson_datetime")]
@@ -118,6 +122,7 @@ impl Finding {
triage_action: None,
triage_rationale: None,
developer_feedback: None,
control_refs: Vec::new(),
created_at: now,
updated_at: now,
}
+11 -1
View File
@@ -10,11 +10,14 @@ pub mod mcp;
pub mod mcp_token;
pub mod notification;
pub mod onboarding;
pub mod oscal;
pub mod oscal_assessment;
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};
@@ -38,12 +41,19 @@ pub use onboarding::{
GitArtifactConfig, IssueTrackerConfig, OnboardedTarget, PlcArtifactConfig, PlcFormat,
TargetScanConfig, TargetType, TargetTypeCandidate, WebArtifactConfig,
};
pub use oscal::OscalDocument;
pub use oscal_assessment::{assess, AssessmentResultsDoc, ControlLinker};
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::{
CompleteRequest, CompleteResponse, DastCollect, Executor, HeartbeatAck, HeartbeatRequest,
InputRef, Job, JobCollect, JobRecord, JobResult, JobRuntime, JobStatus, JobType, LeaseRequest,
LeasedJob,
};
+3
View File
@@ -202,6 +202,9 @@ pub enum PlcFormat {
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.
+250
View File
@@ -0,0 +1,250 @@
//! OSCAL 1.1 catalog types + mapping into the controls corpus.
//!
//! Deserialises the OSCAL catalog served by breakpilot-compliance
//! (`GET /api/compliance/v1/oscal/catalog`) and maps its controls into the
//! framework-agnostic [`crate::traits::Control`] that the mapping engine consumes.
//! Only the fields we use are modelled; unknown OSCAL fields are ignored so the
//! producer can add detail without breaking us.
//!
//! Scope boundary: this is the *catalog* (domain content). Assessment objectives
//! and scanner routing live in our assessment layer, not here — see
//! [`crate::traits::ControlsProvider`].
use serde::Deserialize;
use crate::models::onboarding::ComplianceFramework;
use crate::traits::Control as CorpusControl;
/// A parsed OSCAL catalog document (`{"catalog": {...}}`).
#[derive(Debug, Clone, Deserialize)]
pub struct OscalDocument {
pub catalog: Catalog,
}
/// An OSCAL catalog: metadata + a tree of control groups.
#[derive(Debug, Clone, Deserialize)]
pub struct Catalog {
pub uuid: String,
pub metadata: Metadata,
#[serde(default)]
pub groups: Vec<Group>,
#[serde(rename = "back-matter", default)]
pub back_matter: Option<BackMatter>,
}
/// Catalog metadata (title/version + provenance props).
#[derive(Debug, Clone, Deserialize)]
pub struct Metadata {
pub title: String,
pub version: String,
#[serde(rename = "oscal-version")]
pub oscal_version: String,
#[serde(default)]
pub props: Vec<Prop>,
}
/// A name/value property, optionally namespaced.
#[derive(Debug, Clone, Deserialize)]
pub struct Prop {
pub name: String,
pub value: String,
#[serde(default)]
pub ns: Option<String>,
}
/// A control group (may nest sub-groups and controls).
#[derive(Debug, Clone, Deserialize)]
pub struct Group {
#[serde(default)]
pub id: String,
#[serde(default)]
pub title: String,
#[serde(default)]
pub controls: Vec<Control>,
#[serde(default)]
pub groups: Vec<Group>,
}
/// An OSCAL control (may nest enhancement controls).
#[derive(Debug, Clone, Deserialize)]
pub struct Control {
pub id: String,
#[serde(default)]
pub title: String,
#[serde(default)]
pub props: Vec<Prop>,
#[serde(default)]
pub parts: Vec<Part>,
#[serde(default)]
pub links: Vec<Link>,
#[serde(default)]
pub controls: Vec<Control>,
}
/// A control part (e.g. the `statement`), may nest sub-parts.
#[derive(Debug, Clone, Deserialize)]
pub struct Part {
#[serde(default)]
pub name: String,
#[serde(default)]
pub prose: Option<String>,
#[serde(default)]
pub parts: Vec<Part>,
}
/// A link, e.g. a `reference` to a back-matter resource.
#[derive(Debug, Clone, Deserialize)]
pub struct Link {
pub href: String,
#[serde(default)]
pub rel: Option<String>,
}
/// Back-matter holding referenced resources (e.g. the CRA measures).
#[derive(Debug, Clone, Deserialize)]
pub struct BackMatter {
#[serde(default)]
pub resources: Vec<Resource>,
}
/// A back-matter resource referenced by control links.
#[derive(Debug, Clone, Deserialize)]
pub struct Resource {
pub uuid: String,
#[serde(default)]
pub title: Option<String>,
#[serde(default)]
pub description: Option<String>,
}
impl Metadata {
/// First prop value with the given name.
pub fn prop(&self, name: &str) -> Option<&str> {
self.props
.iter()
.find(|p| p.name == name)
.map(|p| p.value.as_str())
}
}
impl Control {
/// First prop value with the given name.
pub fn prop(&self, name: &str) -> Option<&str> {
self.props
.iter()
.find(|p| p.name == name)
.map(|p| p.value.as_str())
}
/// The control's `statement` prose, if present.
pub fn statement(&self) -> Option<&str> {
self.parts
.iter()
.find(|p| p.name == "statement")
.and_then(|p| p.prose.as_deref())
}
}
impl OscalDocument {
/// The framework this catalog declares (`metadata.props[name="framework"]`).
pub fn framework(&self) -> Option<ComplianceFramework> {
framework_from_str(self.catalog.metadata.prop("framework")?)
}
/// The catalog `content-hash` prop — consumers pin this to snapshot/detect drift.
pub fn content_hash(&self) -> Option<&str> {
self.catalog.metadata.prop("content-hash")
}
/// Flatten the catalog into the corpus controls the mapping engine consumes.
pub fn to_controls(&self) -> Vec<CorpusControl> {
let framework = self.framework().unwrap_or(ComplianceFramework::Cra);
let source_label = self.catalog.metadata.title.as_str();
let mut out = Vec::new();
for group in &self.catalog.groups {
collect_group(group, framework, source_label, &mut out);
}
out
}
}
/// Map an OSCAL framework token (e.g. `"cra"`) to [`ComplianceFramework`] via its
/// serde snake_case representation.
fn framework_from_str(raw: &str) -> Option<ComplianceFramework> {
serde_json::from_value(serde_json::Value::String(raw.to_string())).ok()
}
fn collect_group(
group: &Group,
framework: ComplianceFramework,
source_label: &str,
out: &mut Vec<CorpusControl>,
) {
for control in &group.controls {
collect_control(control, framework, source_label, out);
}
for sub in &group.groups {
collect_group(sub, framework, source_label, out);
}
}
fn collect_control(
control: &Control,
framework: ComplianceFramework,
source_label: &str,
out: &mut Vec<CorpusControl>,
) {
let source = match control.prop("annex-anchor") {
Some(anchor) => Some(format!("{source_label} · {anchor}")),
None => Some(source_label.to_string()),
};
out.push(CorpusControl {
id: control.id.clone(),
framework,
title: control.title.clone(),
text: control.statement().unwrap_or_default().to_string(),
source,
});
for enhancement in &control.controls {
collect_control(enhancement, framework, source_label, out);
}
}
#[cfg(test)]
#[allow(clippy::unwrap_used)]
mod tests {
use super::*;
const CATALOG: &str = include_str!("../../tests/data/cra_catalog.json");
fn parse() -> OscalDocument {
serde_json::from_str(CATALOG).unwrap()
}
#[test]
fn parses_full_catalog() {
let doc = parse();
assert_eq!(doc.catalog.metadata.oscal_version, "1.1.2");
assert!(!doc.catalog.groups.is_empty());
assert!(doc.catalog.back_matter.is_some());
}
#[test]
fn maps_all_controls_to_corpus() {
let doc = parse();
let controls = doc.to_controls();
assert_eq!(controls.len(), 40);
assert_eq!(doc.framework(), Some(ComplianceFramework::Cra));
let c8 = controls.iter().find(|c| c.id == "cra-ai-8").unwrap();
assert_eq!(c8.framework, ComplianceFramework::Cra);
assert!(!c8.title.is_empty());
assert!(!c8.text.is_empty(), "statement prose should map into text");
assert!(c8.source.as_deref().unwrap_or_default().contains("Annex I"));
}
#[test]
fn exposes_content_hash_for_snapshotting() {
assert_eq!(parse().content_hash().map(str::len), Some(64));
}
}
@@ -0,0 +1,424 @@
//! OSCAL 1.1 assessment-results — assess our findings against catalog controls.
//!
//! The catalog (domain content) comes from the producer; the **assessment** is
//! ours. This links compliance [`Finding`]s to catalog control-ids and emits a
//! standard OSCAL assessment-results document: an observation per linked finding,
//! and a per-control finding with a `not-satisfied` status. `reviewed-controls`
//! records the full catalog set we considered.
//!
//! Deterministic: stable `uuid5` ids; the caller supplies the assessment
//! timestamp. Pure — no DB, no network.
use std::collections::HashMap;
use chrono::{DateTime, Utc};
use serde::Serialize;
use uuid::Uuid;
use crate::models::finding::{Finding, FindingStatus};
const OSCAL_VERSION: &str = "1.1.2";
/// Same namespace as the catalog exporter, so ids are stable and correlatable.
const NAMESPACE: Uuid = Uuid::from_bytes([
0x6f, 0x1e, 0x7c, 0x2a, 0x3b, 0x4d, 0x5e, 0x6f, 0x8a, 0x9b, 0x0c, 0x1d, 0x2e, 0x3f, 0x4a, 0x5b,
]);
fn det_uuid(name: &str) -> String {
Uuid::new_v5(&NAMESPACE, name.as_bytes()).to_string()
}
/// Links findings to the catalog control-ids they provide evidence for.
pub struct ControlLinker {
cwe_to_controls: HashMap<u32, Vec<String>>,
}
impl ControlLinker {
/// Build a linker from an explicit CWE → control-id map.
pub fn new(cwe_to_controls: HashMap<u32, Vec<String>>) -> Self {
Self { cwe_to_controls }
}
/// Seed of CWE → CRA Annex I control mappings (mirrors breakpilot's
/// `_CWE_TO_REQ`; extend as scanner coverage grows).
pub fn cra_seed() -> Self {
let pairs: &[(u32, &str)] = &[
(798, "cra-ai-8"),
(259, "cra-ai-8"),
(1392, "cra-ai-8"),
(327, "cra-ai-13"),
(326, "cra-ai-13"),
(319, "cra-ai-15"),
(311, "cra-ai-15"),
(89, "cra-ai-20"),
(79, "cra-ai-20"),
(78, "cra-ai-20"),
(22, "cra-ai-20"),
];
let mut map: HashMap<u32, Vec<String>> = HashMap::new();
for (cwe, id) in pairs {
map.entry(*cwe).or_default().push((*id).to_string());
}
Self::new(map)
}
/// Parse a CWE token such as `"CWE-798"` or `"798"` into its number.
fn parse_cwe(raw: &str) -> Option<u32> {
raw.trim_start_matches(|c: char| !c.is_ascii_digit())
.split(|c: char| !c.is_ascii_digit())
.next()
.filter(|s| !s.is_empty())
.and_then(|s| s.parse().ok())
}
/// The control-ids a finding provides evidence for (via its CWE).
pub fn controls_for(&self, finding: &Finding) -> Vec<String> {
finding
.cwe
.as_deref()
.and_then(Self::parse_cwe)
.and_then(|cwe| self.cwe_to_controls.get(&cwe))
.cloned()
.unwrap_or_default()
}
}
/// Build a standard OSCAL assessment-results document from `findings`, using each
/// finding's stamped `control_refs` for control linkage. EVERY non-false-positive
/// finding is emitted as an observation — mapped findings additionally produce a
/// per-control `not-satisfied` finding; **unmapped findings are reported as-is**
/// (an observation carrying their CWE/tool/severity, with no control target) so
/// nothing is lost. `at` is the assessment timestamp.
pub fn assess(findings: &[Finding], at: DateTime<Utc>) -> AssessmentResultsDoc {
let ts = at.to_rfc3339();
let mut observations = Vec::new();
let mut obs_by_control: HashMap<String, Vec<String>> = HashMap::new();
let mut mapped = 0usize;
let mut unmapped = 0usize;
for finding in findings {
if finding.status == FindingStatus::FalsePositive {
continue; // flagged tool false positive — excluded from the report
}
let obs_uuid = det_uuid(&format!("obs:{}", finding.fingerprint));
let location = match (&finding.file_path, finding.line_number) {
(Some(f), Some(l)) => Some(format!("{f}:{l}")),
(Some(f), None) => Some(f.clone()),
_ => None,
};
let is_mapped = !finding.control_refs.is_empty();
if is_mapped {
mapped += 1;
} else {
unmapped += 1;
}
let mut props = vec![
ObsProp::new("tool", &finding.scanner),
ObsProp::new("severity", &finding.severity.to_string()),
ObsProp::new("mapping", if is_mapped { "mapped" } else { "unmapped" }),
];
if let Some(cwe) = &finding.cwe {
props.push(ObsProp::new("cwe", cwe));
}
observations.push(Observation {
uuid: obs_uuid.clone(),
title: finding.title.clone(),
description: finding.description.clone(),
methods: vec!["TEST".to_string()],
collected: ts.clone(),
props,
relevant_evidence: vec![RelevantEvidence {
href: location.map(|l| format!("file://{l}")),
description: format!("[{}] {}", finding.scanner, finding.title),
}],
});
for control_id in &finding.control_refs {
obs_by_control
.entry(control_id.clone())
.or_default()
.push(obs_uuid.clone());
}
}
let mut hit_controls: Vec<&String> = obs_by_control.keys().collect();
hit_controls.sort();
let ar_findings: Vec<ArFinding> = hit_controls
.iter()
.map(|control_id| ArFinding {
uuid: det_uuid(&format!("finding:{control_id}")),
title: format!("Findings affect {control_id}"),
target: FindingTarget {
target_type: "statement-id".to_string(),
target_id: format!("{control_id}_smt"),
status: TargetStatus {
state: "not-satisfied".to_string(),
},
},
related_observations: obs_by_control[*control_id]
.iter()
.map(|u| RelatedObservation {
observation_uuid: u.clone(),
})
.collect(),
})
.collect();
let include_controls: Vec<SelectControlById> = hit_controls
.iter()
.map(|c| SelectControlById {
control_id: (*c).clone(),
})
.collect();
let result = ArResult {
uuid: det_uuid("result:cra"),
title: "Automated code-compliance assessment".to_string(),
description: format!(
"{} observation(s): {mapped} control-linked, {unmapped} unmapped (as-is); {} control(s) affected",
observations.len(),
include_controls.len()
),
start: ts.clone(),
reviewed_controls: ReviewedControls {
control_selections: vec![ControlSelection { include_controls }],
},
observations,
findings: ar_findings,
};
AssessmentResultsDoc {
assessment_results: AssessmentResults {
uuid: det_uuid("assessment-results:cra"),
metadata: ArMetadata {
title: "Compliance scanner — OSCAL assessment results".to_string(),
last_modified: ts,
version: "1.0.0".to_string(),
oscal_version: OSCAL_VERSION.to_string(),
},
import_ap: ImportAp {
href: "#cra-annex-i".to_string(),
},
results: vec![result],
},
}
}
// ── OSCAL assessment-results document (serialise) ────────────────────────────
/// The root OSCAL assessment-results document.
#[derive(Debug, Clone, Serialize)]
pub struct AssessmentResultsDoc {
#[serde(rename = "assessment-results")]
pub assessment_results: AssessmentResults,
}
#[derive(Debug, Clone, Serialize)]
pub struct AssessmentResults {
pub uuid: String,
pub metadata: ArMetadata,
#[serde(rename = "import-ap")]
pub import_ap: ImportAp,
pub results: Vec<ArResult>,
}
#[derive(Debug, Clone, Serialize)]
pub struct ArMetadata {
pub title: String,
#[serde(rename = "last-modified")]
pub last_modified: String,
pub version: String,
#[serde(rename = "oscal-version")]
pub oscal_version: String,
}
#[derive(Debug, Clone, Serialize)]
pub struct ImportAp {
pub href: String,
}
#[derive(Debug, Clone, Serialize)]
pub struct ArResult {
pub uuid: String,
pub title: String,
pub description: String,
pub start: String,
#[serde(rename = "reviewed-controls")]
pub reviewed_controls: ReviewedControls,
#[serde(skip_serializing_if = "Vec::is_empty")]
pub observations: Vec<Observation>,
#[serde(skip_serializing_if = "Vec::is_empty")]
pub findings: Vec<ArFinding>,
}
#[derive(Debug, Clone, Serialize)]
pub struct ReviewedControls {
#[serde(rename = "control-selections")]
pub control_selections: Vec<ControlSelection>,
}
#[derive(Debug, Clone, Serialize)]
pub struct ControlSelection {
#[serde(rename = "include-controls", skip_serializing_if = "Vec::is_empty")]
pub include_controls: Vec<SelectControlById>,
}
#[derive(Debug, Clone, Serialize)]
pub struct SelectControlById {
#[serde(rename = "control-id")]
pub control_id: String,
}
#[derive(Debug, Clone, Serialize)]
pub struct Observation {
pub uuid: String,
pub title: String,
pub description: String,
pub methods: Vec<String>,
pub collected: String,
#[serde(skip_serializing_if = "Vec::is_empty")]
pub props: Vec<ObsProp>,
#[serde(rename = "relevant-evidence", skip_serializing_if = "Vec::is_empty")]
pub relevant_evidence: Vec<RelevantEvidence>,
}
/// A name/value observation property (cwe, tool, severity, mapping status). Lets an
/// unmapped finding be reported fully as-is.
#[derive(Debug, Clone, Serialize)]
pub struct ObsProp {
pub name: String,
pub value: String,
}
impl ObsProp {
fn new(name: &str, value: &str) -> Self {
Self {
name: name.to_string(),
value: value.to_string(),
}
}
}
#[derive(Debug, Clone, Serialize)]
pub struct RelevantEvidence {
#[serde(skip_serializing_if = "Option::is_none")]
pub href: Option<String>,
pub description: String,
}
#[derive(Debug, Clone, Serialize)]
pub struct ArFinding {
pub uuid: String,
pub title: String,
pub target: FindingTarget,
#[serde(rename = "related-observations", skip_serializing_if = "Vec::is_empty")]
pub related_observations: Vec<RelatedObservation>,
}
#[derive(Debug, Clone, Serialize)]
pub struct FindingTarget {
#[serde(rename = "type")]
pub target_type: String,
#[serde(rename = "target-id")]
pub target_id: String,
pub status: TargetStatus,
}
#[derive(Debug, Clone, Serialize)]
pub struct TargetStatus {
pub state: String,
}
#[derive(Debug, Clone, Serialize)]
pub struct RelatedObservation {
#[serde(rename = "observation-uuid")]
pub observation_uuid: String,
}
#[cfg(test)]
#[allow(clippy::unwrap_used)]
mod tests {
use super::*;
use crate::models::finding::Severity;
use crate::models::scan::ScanType;
fn finding(fp: &str, cwe: Option<&str>, refs: &[&str]) -> Finding {
let mut f = Finding::new(
"repo".into(),
fp.into(),
"semgrep".into(),
ScanType::Sast,
"hardcoded credential".into(),
"desc".into(),
Severity::High,
);
f.cwe = cwe.map(Into::into);
f.file_path = Some("src/auth.rs".into());
f.line_number = Some(42);
f.control_refs = refs.iter().map(|s| s.to_string()).collect();
f
}
fn at() -> DateTime<Utc> {
DateTime::parse_from_rfc3339("2026-07-20T00:00:00Z")
.unwrap()
.with_timezone(&Utc)
}
#[test]
fn mapped_finding_becomes_control_finding() {
let doc = assess(&[finding("f1", Some("CWE-798"), &["cra-ai-8"])], at());
let r = &doc.assessment_results.results[0];
assert_eq!(r.observations.len(), 1);
assert_eq!(r.findings.len(), 1);
assert_eq!(r.findings[0].target.target_id, "cra-ai-8_smt");
assert_eq!(r.findings[0].target.status.state, "not-satisfied");
assert_eq!(
r.reviewed_controls.control_selections[0]
.include_controls
.len(),
1
);
}
#[test]
fn unmapped_finding_is_reported_as_is() {
let doc = assess(&[finding("f1", Some("CWE-319"), &[])], at());
let r = &doc.assessment_results.results[0];
assert_eq!(r.observations.len(), 1); // still emitted...
assert!(r.findings.is_empty()); // ...but no control finding
assert!(r.reviewed_controls.control_selections[0]
.include_controls
.is_empty());
let props: Vec<(&str, &str)> = r.observations[0]
.props
.iter()
.map(|p| (p.name.as_str(), p.value.as_str()))
.collect();
assert!(props.contains(&("mapping", "unmapped")));
assert!(props.contains(&("cwe", "CWE-319")));
}
#[test]
fn false_positive_is_excluded() {
let mut f = finding("f1", Some("CWE-798"), &["cra-ai-8"]);
f.status = FindingStatus::FalsePositive;
let doc = assess(&[f], at());
assert!(doc.assessment_results.results[0].observations.is_empty());
}
#[test]
fn deterministic_and_valid_oscal() {
let mk = || {
vec![
finding("f1", Some("CWE-798"), &["cra-ai-8"]),
finding("f2", Some("CWE-319"), &[]),
]
};
let a = serde_json::to_string(&assess(&mk(), at())).unwrap();
let b = serde_json::to_string(&assess(&mk(), at())).unwrap();
assert_eq!(a, b);
assert!(a.contains("\"oscal-version\":\"1.1.2\""));
assert!(a.contains("\"not-satisfied\""));
assert!(a.contains("\"mapping\""));
}
}
+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,
}
}
}
+5
View File
@@ -24,6 +24,9 @@ pub enum ScanType {
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 {
@@ -43,6 +46,7 @@ impl std::fmt::Display for ScanType {
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"),
}
}
}
@@ -76,6 +80,7 @@ pub enum ScanPhase {
LlmTriage,
IssueCreation,
DastScanning,
IcsProbe,
Completed,
}
+514
View File
@@ -0,0 +1,514 @@
//! 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()
}
}
}
/// A queued job as persisted by the control plane (WB-02): the [`Job`] contract
/// plus the queue bookkeeping — status, lease ownership, attempt count, and the
/// eventual result. The runner never sees this record; on lease it receives a
/// [`LeasedJob`] (the job plus a token it presents to heartbeat/complete).
///
/// Timestamps persist as native BSON dates so the queue's range queries (lease
/// FIFO by `created_at`, visibility-timeout sweep by `lease_expires_at`) compare
/// correctly.
#[derive(Debug, Clone, Serialize, Deserialize)]
pub struct JobRecord {
/// The job to run.
pub job: Job,
/// Current queue state.
pub status: JobStatus,
/// The lease token held by the current runner (proves lease ownership).
#[serde(default, skip_serializing_if = "Option::is_none")]
pub lease_token: Option<String>,
/// Id of the runner holding the lease.
#[serde(default, skip_serializing_if = "Option::is_none")]
pub leased_by: Option<String>,
/// When the current lease expires — the visibility timeout after which a
/// crashed runner's job is swept back to `queued`.
#[serde(default, with = "super::serde_helpers::opt_bson_datetime")]
pub lease_expires_at: Option<DateTime<Utc>>,
/// Last heartbeat from the runner.
#[serde(default, with = "super::serde_helpers::opt_bson_datetime")]
pub heartbeat_at: Option<DateTime<Utc>>,
/// How many times the job has been leased (incremented on each lease).
#[serde(default)]
pub attempts: u32,
/// Set when the control plane requests cancellation; the runner sees it on
/// its next heartbeat and aborts.
#[serde(default)]
pub cancel_requested: bool,
/// The result, once the job reaches a terminal state.
#[serde(default, skip_serializing_if = "Option::is_none")]
pub result: Option<JobResult>,
/// When the job was enqueued.
#[serde(with = "super::serde_helpers::bson_datetime")]
pub created_at: DateTime<Utc>,
/// Last modification.
#[serde(with = "super::serde_helpers::bson_datetime")]
pub updated_at: DateTime<Utc>,
}
impl JobRecord {
/// A freshly-enqueued (`queued`) record for a job.
pub fn queued(job: Job, now: DateTime<Utc>) -> Self {
Self {
job,
status: JobStatus::Queued,
lease_token: None,
leased_by: None,
lease_expires_at: None,
heartbeat_at: None,
attempts: 0,
cancel_requested: false,
result: None,
created_at: now,
updated_at: now,
}
}
}
/// A job handed to a runner on lease: what to run plus the token the runner must
/// present to heartbeat and complete it.
#[derive(Debug, Clone, PartialEq, Eq, Serialize, Deserialize)]
pub struct LeasedJob {
/// The job to execute.
pub job: Job,
/// The lease token proving ownership (opaque to the runner).
pub lease_token: String,
}
/// The runner's view of a heartbeat: whether the control plane has asked the job
/// to stop. `None` from the queue means the lease was lost (token mismatch or the
/// job already terminal) and the runner should abandon the work.
#[derive(Debug, Clone, Copy, PartialEq, Eq, Serialize, Deserialize)]
pub struct HeartbeatAck {
/// The control plane requested cancellation — the runner should tear down.
pub cancelled: bool,
}
// --- Runner ↔ control-plane transport (the pull API wire types) ---------------
// Shared so the runner (client) and the control plane (server) agree on shapes.
/// Runner → control plane: lease the oldest runnable job for this runner.
#[derive(Debug, Clone, Serialize, Deserialize)]
pub struct LeaseRequest {
/// The tenant queue to lease from.
pub tenant: String,
/// The runner id (advertised for attribution).
pub runner_id: String,
/// The executor this runner provides.
pub executor: Executor,
/// The capability labels this runner advertises.
#[serde(default)]
pub labels: Vec<String>,
/// Requested lease lifetime (the visibility timeout), in seconds.
pub lease_ttl_secs: u64,
}
/// Runner → control plane: prove lease ownership and extend it.
#[derive(Debug, Clone, Serialize, Deserialize)]
pub struct HeartbeatRequest {
/// The tenant queue.
pub tenant: String,
/// The job being worked.
pub job_id: String,
/// The lease token from the [`LeasedJob`].
pub lease_token: String,
/// Lease lifetime to extend to, in seconds.
pub lease_ttl_secs: u64,
}
/// Runner → control plane: record a job's terminal result.
#[derive(Debug, Clone, Serialize, Deserialize)]
pub struct CompleteRequest {
/// The tenant queue.
pub tenant: String,
/// The job being completed.
pub job_id: String,
/// The lease token proving ownership.
pub lease_token: String,
/// The result to record.
pub result: JobResult,
}
/// Control plane → runner: whether the completion was recorded (false if the
/// lease was already lost — token mismatch or the job had become terminal).
#[derive(Debug, Clone, Copy, Serialize, Deserialize)]
pub struct CompleteResponse {
/// Whether the result was recorded.
pub recorded: bool,
}
#[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"));
}
}
+194 -17
View File
@@ -14,8 +14,12 @@ use crate::models::{ArtifactKind, OnboardedTarget, ScanType, TargetType};
pub enum ArtifactRequirement {
/// Source code — a git repo or a source archive.
Code,
/// A reachable running instance (live URL / endpoint).
/// 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).
@@ -134,7 +138,7 @@ fn sast_umbrella() -> Vec<ScanRule> {
/// 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, Mobile, Plc, RunningUrl};
use ArtifactRequirement::{Firmware, HttpUrl, Mobile, Plc, RunningUrl};
match target_type {
TargetType::WebApp | TargetType::BackendService => {
let mut r = sast_umbrella();
@@ -142,7 +146,7 @@ pub fn rules_for(target_type: TargetType) -> Vec<ScanRule> {
ScanType::Dast,
true,
"Dynamic scan of the running endpoint",
RunningUrl,
HttpUrl,
));
r
}
@@ -203,16 +207,62 @@ pub fn rules_for(target_type: TargetType) -> Vec<ScanRule> {
ScanType::Dast,
false,
"Dynamic scan of exposed network services (if any)",
RunningUrl,
HttpUrl,
));
r
}
TargetType::PlcSps => vec![ScanRule::new(
ScanType::PlcControlLogic,
true,
"Control-logic security rules over the PLC program",
Plc,
)],
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,
),
]
}
}
}
@@ -229,6 +279,9 @@ pub fn supports_pentest(target_type: TargetType) -> bool {
| 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
)
}
@@ -236,7 +289,9 @@ pub fn supports_pentest(target_type: TargetType) -> bool {
fn representative_kind(req: ArtifactRequirement) -> Option<ArtifactKind> {
match req {
ArtifactRequirement::Code => Some(ArtifactKind::GitRepo),
ArtifactRequirement::RunningUrl => Some(ArtifactKind::LiveUrl),
ArtifactRequirement::RunningUrl | ArtifactRequirement::HttpUrl => {
Some(ArtifactKind::LiveUrl)
}
ArtifactRequirement::Firmware => Some(ArtifactKind::FirmwareImage),
ArtifactRequirement::Plc => Some(ArtifactKind::PlcProject),
ArtifactRequirement::Mobile => Some(ArtifactKind::MobilePackage),
@@ -245,13 +300,29 @@ fn representative_kind(req: ArtifactRequirement) -> Option<ArtifactKind> {
}
}
/// 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),
ArtifactRequirement::Plc => target.has(ArtifactKind::PlcProject),
// 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,
@@ -268,6 +339,10 @@ pub fn applicable_scans(target: &OnboardedTarget) -> Vec<ScanOption> {
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"),
@@ -340,22 +415,124 @@ mod tests {
}
#[test]
fn plc_offers_only_control_logic() {
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);
assert_eq!(opts.len(), 1);
assert_eq!(opts[0].scan, ScanType::PlcControlLogic);
assert!(opts[0].default_on);
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::PlcSps));
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));
}
File diff suppressed because it is too large Load Diff
-2
View File
@@ -10,8 +10,6 @@ pub enum Route {
#[layout(AppShell)]
#[route("/")]
OverviewPage {},
#[route("/repositories")]
RepositoriesPage {},
#[route("/targets")]
TargetsPage {},
#[route("/onboard")]
@@ -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(),
}
@@ -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")
}
@@ -39,6 +39,67 @@ 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> {
@@ -77,6 +138,94 @@ pub async fn create_target(
.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> {
@@ -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("$oid")).and_then(|s| s.as_str()).unwrap_or_default().to_string();
let name = repo.get("name").and_then(|n| n.as_str()).unwrap_or_default().to_string();
let url = repo
.get("artifacts")
.and_then(|a| a.as_array())
.and_then(|arr| {
arr.iter().find(|a| {
a.get("kind").and_then(|k| k.as_str()) == Some("git_repo")
})
})
.and_then(|a| a.get("source_ref"))
.and_then(|s| s.as_str())
.unwrap_or_default()
.to_string();
let branch = repo
.get("artifacts")
.and_then(|a| a.as_array())
.and_then(|arr| {
arr.iter().find_map(|a| {
a.get("git")
.and_then(|g| g.get("default_branch"))
.and_then(|b| b.as_str())
})
})
.unwrap_or("main")
.to_string();
rsx! {
Link {
to: Route::ChatPage { repo_id },
+29 -25
View File
@@ -2,11 +2,11 @@ use dioxus::prelude::*;
use crate::app::Route;
use crate::components::page_header::PageHeader;
use crate::infrastructure::repositories::fetch_repositories;
use crate::infrastructure::onboarding::fetch_targets;
#[component]
pub fn GraphIndexPage() -> Element {
let repos = use_resource(|| async { fetch_repositories(1).await.ok() });
let repos = use_resource(|| async { fetch_targets().await.ok() });
rsx! {
PageHeader {
@@ -28,27 +28,34 @@ pub fn GraphIndexPage() -> Element {
div { class: "graph-index-grid",
for repo in repo_list {
{
let repo_id = repo.id.map(|id| id.to_hex()).unwrap_or_default();
let name = repo.name.clone();
let url = repo.git_url.clone();
let branch = repo.default_branch.clone();
let findings = repo.findings_count;
let repo_id = repo.get("_id").and_then(|o| o.get("$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}"
}
}
}
}
-2
View File
@@ -16,7 +16,6 @@ pub mod onboarding;
pub mod overview;
pub mod pentest_dashboard;
pub mod pentest_session;
pub mod repositories;
pub mod sbom;
pub mod targets;
@@ -38,6 +37,5 @@ 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;
+286 -32
View File
@@ -2,7 +2,8 @@ use dioxus::prelude::*;
use crate::components::page_header::PageHeader;
use crate::infrastructure::onboarding::{
create_target, detect_target, fetch_applicable_scans, trigger_target_scan, ArtifactInputDto,
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.
@@ -40,6 +41,23 @@ const ARTIFACT_KINDS: &[(&str, &str)] = &[
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 {
@@ -107,6 +125,10 @@ pub fn OnboardingPage() -> Element {
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);
@@ -115,10 +137,41 @@ pub fn OnboardingPage() -> Element {
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 can_advance_type = !name().trim().is_empty() && !target_type().trim().is_empty();
let has_artifacts = !artifacts().is_empty();
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 {
@@ -157,6 +210,11 @@ pub fn OnboardingPage() -> Element {
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;",
@@ -180,6 +238,36 @@ pub fn OnboardingPage() -> Element {
// ---- 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;",
@@ -192,41 +280,141 @@ pub fn OnboardingPage() -> Element {
}
}
}
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 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() == "git_repo" {
div { class: "form-group", style: "margin: 0;",
label { "Branch" }
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",
value: "{new_branch}",
oninput: move |e| new_branch.set(e.value()),
placeholder: "https://git.example.com/acme.git",
value: "{new_source}",
oninput: move |e| new_source.set(e.value()),
}
}
}
button {
class: "btn btn-secondary",
onclick: move |_| {
let kind = new_kind();
if !new_source().trim().is_empty() {
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());
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()),
}
}
},
"+ Add"
}
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"
}
}
}
@@ -292,6 +480,39 @@ pub fn OnboardingPage() -> Element {
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}" }
}
@@ -300,8 +521,21 @@ pub fn OnboardingPage() -> Element {
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(),
@@ -321,6 +555,8 @@ pub fn OnboardingPage() -> Element {
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);
@@ -359,6 +595,7 @@ pub fn OnboardingPage() -> Element {
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);
@@ -373,6 +610,23 @@ pub fn OnboardingPage() -> Element {
.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);
}
+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 },
@@ -1,428 +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 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: "Legacy git repositories. Onboard new targets from Targets / Onboard.",
}
// ── 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..." }
},
}
}
}
+206 -1
View File
@@ -12,9 +12,35 @@ 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,
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 {
@@ -106,6 +132,17 @@ pub fn TargetsPage() -> Element {
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! {
@@ -163,6 +200,145 @@ pub fn TargetsPage() -> Element {
}
}
// ── 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 {
@@ -223,8 +399,12 @@ pub fn TargetsPage() -> Element {
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}" } }
@@ -253,6 +433,31 @@ pub fn TargetsPage() -> Element {
},
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",
+12 -1
View File
@@ -4,7 +4,7 @@ use rmcp::{
use crate::auth::current_tenant_id;
use crate::database::{Database, DatabasePool};
use crate::tools::{dast, findings, pentest, sbom};
use crate::tools::{dast, findings, oscal, pentest, sbom};
pub struct ComplianceMcpServer {
pool: DatabasePool,
@@ -68,6 +68,17 @@ impl ComplianceMcpServer {
findings::findings_summary(&db, params).await
}
#[tool(
description = "Emit an OSCAL 1.1 assessment-results document for a repo's findings (mapped findings target their compliance controls; unmapped findings are reported as-is)"
)]
async fn oscal_assessment(
&self,
Parameters(params): Parameters<oscal::OscalAssessmentParams>,
) -> Result<CallToolResult, rmcp::ErrorData> {
let db = self.tenant_db()?;
oscal::oscal_assessment(&db, params).await
}
// ── SBOM ──────────────────────────────────────────────
#[tool(

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