Compare commits

..
Author SHA1 Message Date
Sharang ParnerkarandClaude Opus 4.7 324b137862 feat(m7.1): wire compliance-agent to compliance-core auth + status gate
CI / Check (pull_request) Successful in 8m14s
CI / Detect Changes (pull_request) Has been skipped
CI / Deploy Agent (pull_request) Has been skipped
CI / Deploy Dashboard (pull_request) Has been skipped
CI / Deploy Docs (pull_request) Has been skipped
CI / Deploy MCP (pull_request) Has been skipped
Supersedes #82.

Deletes the inline JWT middleware in compliance-agent (now stale —
missing JWKS refresh from #84 and tenant extraction from #83) and
imports require_jwt_auth, require_tenant_status, JwksState from
compliance_core::auth. Wires the status gate into the server's layer
stack: Extension(jwks_state) → require_jwt_auth → require_tenant_status
→ handler.

Adds the integration test from #82, retargeted to
compliance_core::auth::require_tenant_status.

Test plan
- cargo fmt --all clean
- cargo clippy --workspace --exclude compliance-dashboard -- -D warnings
  clean (matches baseline)
- cargo test -p compliance-core --lib — 7 tests pass
- cargo test -p compliance-agent --lib — 228 tests pass
- cargo test -p compliance-agent --test tenant_status_middleware —
  6 tests pass
- scripts/smoke.sh against live certifai KC — 15/15 cells pass
  (anon, bogus, active×2, trial, frozen, archived × {GET/health,
  GET/echo, POST/echo})

Caveats
- M7.1 only — status gate + claim extraction. Per-collection
  tenant_id scoping (M7.2) still pending; agent will still serve any
  Active/Trial tenant's data to any caller until the ~38 query
  call-sites use compliance_core::db::tenant_filter.

Co-Authored-By: Claude Opus 4.7 <noreply@anthropic.com>
2026-06-17 11:07:56 +02:00
129 changed files with 2469 additions and 14138 deletions
-13
View File
@@ -7,17 +7,4 @@ ignore = [
# not a realistic attack surface here. Revisit when mongodb bumps hickory.
"RUSTSEC-2026-0118", # NSEC3 loop, no fix available upstream
"RUSTSEC-2026-0119", # O(n²) name compression, fixed in hickory-proto >=0.26.1
# rmcp 0.16.0 — DNS rebinding in Streamable HTTP server transport (missing
# Host header validation). Patched in rmcp >= 1.4.0, which is a major API
# version jump from our pin; rmcp shipped 0.x → 1.x → 2.x in three months
# and the migration touches every tool handler + the auth middleware we
# just landed in #92. Threat model in our deployment: the MCP server is
# exposed at a public hostname (comp-mcp-dev.meghsakha.com) behind orca's
# TLS-terminating ingress with per-tenant bearer auth — the attack model
# (browser DNS-rebinding into localhost MCP server) doesn't directly apply.
# Defense-in-depth Host-header check is still a worthwhile follow-up.
# FOLLOW-UP: bump rmcp to 2.x in a dedicated PR (M7.3 follow-up, sized
# multi-hour due to API surface change).
"RUSTSEC-2026-0189",
]
+10 -67
View File
@@ -9,33 +9,15 @@ on:
env:
CARGO_TERM_COLOR: always
RUSTFLAGS: "-D warnings"
# Compile cache: sccache -> Hetzner S3 (breakpilot-sccache), runner-independent
# and persistent across CI runs (own key prefix). Reuses the shared cluster S3
# creds (same bucket as werkpilot). Requires repo secrets HETZNER_S3_ACCESS_KEY
# and HETZNER_S3_SECRET_KEY.
# sccache caches compilation artifacts within a job so that compiling
# both --features server and --features web shares common crate work.
RUSTC_WRAPPER: /usr/local/bin/sccache
SCCACHE_BUCKET: breakpilot-sccache
SCCACHE_ENDPOINT: https://nbg1.your-objectstorage.com
SCCACHE_REGION: auto
SCCACHE_S3_USE_SSL: "true"
SCCACHE_S3_KEY_PREFIX: compliance-scanner
AWS_ACCESS_KEY_ID: ${{ secrets.HETZNER_S3_ACCESS_KEY }}
AWS_SECRET_ACCESS_KEY: ${{ secrets.HETZNER_S3_SECRET_KEY }}
# compliance-agent depends on tramiton-core via git; use the system git so the
# credential rewrite below (see "Configure git auth ...") is honored on fetch.
CARGO_NET_GIT_FETCH_WITH_CLI: "true"
# Throttle cargo so a ~670-crate concurrent download burst doesn't 429 the
# Kellnr mirror: fewer concurrent connections (HTTP/1.1) + more retries.
CARGO_NET_RETRY: "10"
CARGO_HTTP_MULTIPLEXING: "false"
SCCACHE_DIR: /tmp/sccache
# Cancel superseded PR runs, but NEVER cancel main-branch runs — those build and
# deploy per-service images, and cancelling one merge's deploy when the next
# merge lands leaves a service un-deployed (as happened between two back-to-back
# merges). So cancel-in-progress only for pull_request events.
# Cancel in-progress runs for the same branch/PR
concurrency:
group: ${{ github.workflow }}-${{ github.ref }}
cancel-in-progress: ${{ github.event_name == 'pull_request' }}
cancel-in-progress: true
jobs:
# ---------------------------------------------------------------------------
@@ -54,44 +36,16 @@ jobs:
git remote add origin "${GITHUB_SERVER_URL}/${GITHUB_REPOSITORY}.git"
git fetch --depth=1 origin "${GITHUB_SHA}"
git checkout FETCH_HEAD
# Resolve crates.io deps through the self-hosted Kellnr mirror (cached,
# crates.io-independent). Git deps (tramiton-core) are unaffected — source
# replacement only applies to crates.io-sourced crates.
- name: Use Kellnr crates.io mirror
run: |
: "${CARGO_HOME:=/usr/local/cargo}"
mkdir -p "$CARGO_HOME"
{
echo '[source.crates-io]'
echo 'replace-with = "kellnr"'
echo '[registries.kellnr]'
echo 'index = "sparse+https://crates.meghsakha.com/api/v1/cratesio/"'
} >> "$CARGO_HOME/config.toml"
env:
RUSTC_WRAPPER: ""
- name: Install tools
run: |
rustup component add rustfmt clippy
curl -fsSL https://github.com/mozilla/sccache/releases/download/v0.10.0/sccache-v0.10.0-x86_64-unknown-linux-musl.tar.gz \
| tar xz --strip-components=1 -C /usr/local/bin/ sccache-v0.10.0-x86_64-unknown-linux-musl/sccache
curl -fsSL https://github.com/mozilla/sccache/releases/download/v0.9.1/sccache-v0.9.1-x86_64-unknown-linux-musl.tar.gz \
| tar xz --strip-components=1 -C /usr/local/bin/ sccache-v0.9.1-x86_64-unknown-linux-musl/sccache
chmod +x /usr/local/bin/sccache
cargo install cargo-audit --locked
env:
RUSTC_WRAPPER: ""
# compliance-agent has a git dependency on tramiton-core (a private repo on
# this Gitea instance). Rewrite its SSH URL to HTTPS + a PAT so the runner
# can fetch it. Requires the repo secret TRAMITON_FETCH_TOKEN (a Gitea PAT
# with read:repository, owned by a user with access to sharang/tramiton).
# (Honored on fetch because CARGO_NET_GIT_FETCH_WITH_CLI=true uses system git.)
- name: Configure git auth for private tramiton dependency
run: |
git config --global \
url."https://sharang:${{ secrets.TRAMITON_FETCH_TOKEN }}@gitea.meghsakha.com/".insteadOf \
"ssh://git@gitea.meghsakha.com:22222/"
env:
RUSTC_WRAPPER: ""
# Format (no compilation needed)
- name: Format
run: cargo fmt --all --check
@@ -194,18 +148,13 @@ jobs:
image: docker:27-cli
steps:
- name: Build, push and trigger orca redeploy
env:
# PAT for fetching the private tramiton-core git dependency during the
# image build (injected as a BuildKit secret, never baked into a layer).
TRAMITON_FETCH_TOKEN: ${{ secrets.TRAMITON_FETCH_TOKEN }}
run: |
apk add --no-cache git curl openssl
git init && git remote add origin "${GITHUB_SERVER_URL}/${GITHUB_REPOSITORY}.git"
git fetch --depth=1 origin "${GITHUB_SHA}" && git checkout FETCH_HEAD
IMAGE=registry.meghsakha.com/compliance-agent
echo "${{ secrets.REGISTRY_PASSWORD }}" | docker login registry.meghsakha.com -u "${{ secrets.REGISTRY_USERNAME }}" --password-stdin
DOCKER_BUILDKIT=1 docker build --secret id=tramiton_token,env=TRAMITON_FETCH_TOKEN \
-f Dockerfile.agent -t "$IMAGE:latest" -t "$IMAGE:${GITHUB_SHA}" .
docker build -f Dockerfile.agent -t "$IMAGE:latest" -t "$IMAGE:${GITHUB_SHA}" .
docker push "$IMAGE:latest" && docker push "$IMAGE:${GITHUB_SHA}"
PAYLOAD=$(printf '{"ref":"refs/heads/main","repository":{"full_name":"sharang/compliance-scanner-agent"},"head_commit":{"id":"%s","message":"deploy agent"}}' "${GITHUB_SHA}")
SIG=$(printf '%s' "$PAYLOAD" | openssl dgst -sha256 -hmac "${{ secrets.ORCA_WEBHOOK_SECRET }}" | awk '{print $2}')
@@ -220,16 +169,13 @@ jobs:
image: docker:27-cli
steps:
- name: Build, push and trigger orca redeploy
env:
TRAMITON_FETCH_TOKEN: ${{ secrets.TRAMITON_FETCH_TOKEN }}
run: |
apk add --no-cache git curl openssl
git init && git remote add origin "${GITHUB_SERVER_URL}/${GITHUB_REPOSITORY}.git"
git fetch --depth=1 origin "${GITHUB_SHA}" && git checkout FETCH_HEAD
IMAGE=registry.meghsakha.com/compliance-dashboard
echo "${{ secrets.REGISTRY_PASSWORD }}" | docker login registry.meghsakha.com -u "${{ secrets.REGISTRY_USERNAME }}" --password-stdin
DOCKER_BUILDKIT=1 docker build --secret id=tramiton_token,env=TRAMITON_FETCH_TOKEN \
-f Dockerfile.dashboard -t "$IMAGE:latest" -t "$IMAGE:${GITHUB_SHA}" .
docker build -f Dockerfile.dashboard -t "$IMAGE:latest" -t "$IMAGE:${GITHUB_SHA}" .
docker push "$IMAGE:latest" && docker push "$IMAGE:${GITHUB_SHA}"
PAYLOAD=$(printf '{"ref":"refs/heads/main","repository":{"full_name":"sharang/compliance-scanner-agent"},"head_commit":{"id":"%s","message":"deploy dashboard"}}' "${GITHUB_SHA}")
SIG=$(printf '%s' "$PAYLOAD" | openssl dgst -sha256 -hmac "${{ secrets.ORCA_WEBHOOK_SECRET }}" | awk '{print $2}')
@@ -265,16 +211,13 @@ jobs:
image: docker:27-cli
steps:
- name: Build, push and trigger orca redeploy
env:
TRAMITON_FETCH_TOKEN: ${{ secrets.TRAMITON_FETCH_TOKEN }}
run: |
apk add --no-cache git curl openssl
git init && git remote add origin "${GITHUB_SERVER_URL}/${GITHUB_REPOSITORY}.git"
git fetch --depth=1 origin "${GITHUB_SHA}" && git checkout FETCH_HEAD
IMAGE=registry.meghsakha.com/compliance-mcp
echo "${{ secrets.REGISTRY_PASSWORD }}" | docker login registry.meghsakha.com -u "${{ secrets.REGISTRY_USERNAME }}" --password-stdin
DOCKER_BUILDKIT=1 docker build --secret id=tramiton_token,env=TRAMITON_FETCH_TOKEN \
-f Dockerfile.mcp -t "$IMAGE:latest" -t "$IMAGE:${GITHUB_SHA}" .
docker build -f Dockerfile.mcp -t "$IMAGE:latest" -t "$IMAGE:${GITHUB_SHA}" .
docker push "$IMAGE:latest" && docker push "$IMAGE:${GITHUB_SHA}"
PAYLOAD=$(printf '{"ref":"refs/heads/main","repository":{"full_name":"sharang/compliance-scanner-agent"},"head_commit":{"id":"%s","message":"deploy mcp"}}' "${GITHUB_SHA}")
SIG=$(printf '%s' "$PAYLOAD" | openssl dgst -sha256 -hmac "${{ secrets.ORCA_WEBHOOK_SECRET }}" | awk '{print $2}')
Generated
+7 -120
View File
@@ -676,10 +676,8 @@ dependencies = [
"jsonwebtoken",
"mongodb",
"octocrab",
"rand 0.9.2",
"regex",
"reqwest",
"roxmltree",
"secrecy",
"serde",
"serde_json",
@@ -693,9 +691,6 @@ dependencies = [
"tower-http",
"tracing",
"tracing-subscriber",
"tramiton-core",
"tramiton-repro",
"tramiton-sbom",
"urlencoding",
"uuid",
"walkdir",
@@ -823,15 +818,12 @@ dependencies = [
"bson",
"chrono",
"compliance-core",
"dashmap",
"dotenvy",
"hex",
"mongodb",
"rmcp",
"schemars 1.2.1",
"serde",
"serde_json",
"sha2",
"thiserror 2.0.18",
"tokio",
"tower-http",
@@ -1122,9 +1114,9 @@ dependencies = [
[[package]]
name = "crossbeam-epoch"
version = "0.9.20"
version = "0.9.18"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "2d6914041f254d6e9176c01941b21115dcfb7089e55135a35411081bd106ef3f"
checksum = "5b82ac4a3c2ca9c3460964f020e1402edd5753411d7737aa39c3714ad1b5420e"
dependencies = [
"crossbeam-utils",
]
@@ -3770,15 +3762,6 @@ dependencies = [
"syn",
]
[[package]]
name = "object"
version = "0.36.7"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "62948e14d923ea95ea2c7c86c71013138b66525b86bdc08d2dcc262bdb497b87"
dependencies = [
"memchr",
]
[[package]]
name = "octocrab"
version = "0.44.1"
@@ -4210,7 +4193,7 @@ version = "3.4.0"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "219cb19e96be00ab2e37d6e299658a0cfa83e52429179969b0f0121b4ac46983"
dependencies = [
"toml_edit 0.23.10+spec-1.0.0",
"toml_edit",
]
[[package]]
@@ -4295,9 +4278,9 @@ dependencies = [
[[package]]
name = "quinn-proto"
version = "0.11.15"
version = "0.11.14"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "4fcb935c5bec503c2f0e306bdd3e58bb9029dcb14fa8d9ac76e3a5256ac0763e"
checksum = "434b42fec591c96ef50e21e886936e66d3cc3f737104fdb9b737c40ffb94c098"
dependencies = [
"bytes",
"getrandom 0.3.4",
@@ -4629,12 +4612,6 @@ 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"
@@ -5015,15 +4992,6 @@ dependencies = [
"syn",
]
[[package]]
name = "serde_spanned"
version = "0.6.9"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "bf41e0cfaf7226dca15e8197172c295a782857fcb97fad1808a166870dee75a3"
dependencies = [
"serde",
]
[[package]]
name = "serde_urlencoded"
version = "0.7.1"
@@ -5222,7 +5190,7 @@ version = "0.8.9"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "c1c97747dbf44bb1ca44a561ece23508e99cb592e862f22222dcf42f51d1e451"
dependencies = [
"heck 0.5.0",
"heck 0.4.1",
"proc-macro2",
"quote",
"syn",
@@ -5838,27 +5806,6 @@ dependencies = [
"tokio",
]
[[package]]
name = "toml"
version = "0.8.23"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "dc1beb996b9d83529a9e75c17a1686767d148d70663143c7854d8b4a09ced362"
dependencies = [
"serde",
"serde_spanned",
"toml_datetime 0.6.11",
"toml_edit 0.22.27",
]
[[package]]
name = "toml_datetime"
version = "0.6.11"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "22cddaf88f4fbc13c51aebbf5f8eceb5c7c5a9da2ac40a13519eb5b0a0e8f11c"
dependencies = [
"serde",
]
[[package]]
name = "toml_datetime"
version = "0.7.5+spec-1.1.0"
@@ -5868,20 +5815,6 @@ dependencies = [
"serde_core",
]
[[package]]
name = "toml_edit"
version = "0.22.27"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "41fe8c660ae4257887cf66394862d21dbca4a6ddd26f04a3560410406a2f819a"
dependencies = [
"indexmap 2.13.0",
"serde",
"serde_spanned",
"toml_datetime 0.6.11",
"toml_write",
"winnow",
]
[[package]]
name = "toml_edit"
version = "0.23.10+spec-1.0.0"
@@ -5889,7 +5822,7 @@ source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "84c8b9f757e028cee9fa244aea147aab2a9ec09d5325a9b01e0a49730c2b5269"
dependencies = [
"indexmap 2.13.0",
"toml_datetime 0.7.5+spec-1.1.0",
"toml_datetime",
"toml_parser",
"winnow",
]
@@ -5903,12 +5836,6 @@ dependencies = [
"winnow",
]
[[package]]
name = "toml_write"
version = "0.1.2"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "5d99f8c9a7727884afe522e9bd5edbfc91a3312b36a77b5fb8926e4c31a41801"
[[package]]
name = "tonic"
version = "0.12.3"
@@ -6155,46 +6082,6 @@ dependencies = [
"wasm-bindgen",
]
[[package]]
name = "tramiton-core"
version = "0.4.1"
source = "git+ssh://git@gitea.meghsakha.com:22222/sharang/tramiton.git?tag=v0.4.1#ae4fc1376279f9edb9882605b20877335e7ba8ba"
dependencies = [
"serde",
"tempfile",
"thiserror 1.0.69",
"toml",
"walkdir",
]
[[package]]
name = "tramiton-repro"
version = "0.4.1"
source = "git+ssh://git@gitea.meghsakha.com:22222/sharang/tramiton.git?tag=v0.4.1#ae4fc1376279f9edb9882605b20877335e7ba8ba"
dependencies = [
"serde",
"serde_json",
"sha2",
"tempfile",
"thiserror 1.0.69",
"toml",
"tramiton-core",
"walkdir",
]
[[package]]
name = "tramiton-sbom"
version = "0.4.1"
source = "git+ssh://git@gitea.meghsakha.com:22222/sharang/tramiton.git?tag=v0.4.1#ae4fc1376279f9edb9882605b20877335e7ba8ba"
dependencies = [
"object",
"serde",
"serde_json",
"sha2",
"tramiton-core",
"tramiton-repro",
]
[[package]]
name = "tree-sitter"
version = "0.24.7"
+1 -3
View File
@@ -23,7 +23,7 @@ tracing = "0.1"
tracing-subscriber = { version = "0.3", features = ["env-filter"] }
chrono = { version = "0.4", features = ["serde"] }
mongodb = { version = "3", features = ["rustls-tls", "compat-3-0-0"] }
reqwest = { version = "0.12", features = ["json", "rustls-tls", "multipart"], default-features = false }
reqwest = { version = "0.12", features = ["json", "rustls-tls"], default-features = false }
thiserror = "2"
sha2 = "0.10"
hex = "0.4"
@@ -34,5 +34,3 @@ zip = { version = "2", features = ["aes-crypto", "deflate"] }
dashmap = "6"
tokio-stream = { version = "0.1", features = ["sync"] }
aes-gcm = "0.10"
rand = "0.9"
base64 = "0.22"
+2 -41
View File
@@ -2,22 +2,7 @@ FROM rust:1.94-bookworm AS builder
WORKDIR /app
COPY . .
# compliance-agent depends on the private tramiton-core git repo. Authenticate
# the fetch with a PAT passed as a BuildKit secret (never baked into a layer).
# Build with: DOCKER_BUILDKIT=1 docker build --secret id=tramiton_token,env=TRAMITON_FETCH_TOKEN ...
RUN --mount=type=secret,id=tramiton_token \
if [ -s /run/secrets/tramiton_token ]; then \
git config --global \
url."https://sharang:$(cat /run/secrets/tramiton_token)@gitea.meghsakha.com/".insteadOf \
"ssh://git@gitea.meghsakha.com:22222/"; \
fi && \
CARGO_NET_GIT_FETCH_WITH_CLI=true cargo build --release -p compliance-agent
# A throwaway stage that packs a real nix store (store paths + the validity DB)
# into a compressed bootstrap tarball. Only the tarball is copied into the final
# image, so we don't carry a raw /nix copy layer.
FROM nixos/nix:latest AS nixseed
RUN tar -C / -czf /nix-bootstrap.tar.gz nix
RUN cargo build --release -p compliance-agent
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/*
@@ -46,30 +31,7 @@ RUN pip3 install --break-system-packages semgrep
# Install ruff for Python linting
RUN pip3 install --break-system-packages ruff
# Real nix for the tramiton reproducible-build firmware SBOM.
#
# nix-portable's proot fallback can't run here: user namespaces are blocked by
# the container's default seccomp/apparmor profile, and orca exposes no way to
# relax it. So ship a *real* nix and disable its build sandbox
# (`sandbox = false`) — a plain gcc/make firmware build needs no user namespace,
# so it runs fine under the locked-down profile with no proot involved.
#
# The store is shipped as a bootstrap tarball and seeded onto /nix at first
# start (see docker/agent-entrypoint.sh), so a persistent /nix volume survives
# redeploys. A missing/broken nix just falls back to the analysis-only SBOM.
COPY --from=nixseed /nix-bootstrap.tar.gz /opt/nix-bootstrap.tar.gz
ENV PATH="/nix/var/nix/profiles/default/bin:${PATH}"
RUN mkdir -p /etc/nix && printf '%s\n' \
'experimental-features = nix-command flakes' \
'sandbox = false' \
'build-users-group =' \
'substituters = https://cache.nixos.org' \
'trusted-public-keys = cache.nixos.org-1:6NCHdD59X431o0gWypbMrAURkbJ16ZPMQFGspcDShjY=' \
> /etc/nix/nix.conf
COPY --from=builder /app/target/release/compliance-agent /usr/local/bin/compliance-agent
COPY docker/agent-entrypoint.sh /usr/local/bin/agent-entrypoint.sh
RUN chmod +x /usr/local/bin/agent-entrypoint.sh
# Copy documentation for the help chat assistant
COPY --from=builder /app/README.md /app/README.md
@@ -81,6 +43,5 @@ RUN mkdir -p /data/compliance-scanner/ssh
EXPOSE 3001 3002
# Seeds /nix (fresh volume) from the bootstrap tarball, then runs the agent.
ENTRYPOINT ["/usr/local/bin/agent-entrypoint.sh"]
ENTRYPOINT ["compliance-agent"]
+1 -10
View File
@@ -7,16 +7,7 @@ ARG DOCS_URL=/docs
WORKDIR /app
COPY . .
ENV DOCS_URL=${DOCS_URL}
# compliance-agent (a workspace member) depends on the private tramiton-core git
# repo, so the workspace resolve needs it even to build the dashboard.
# Authenticate the fetch with a PAT passed as a BuildKit secret.
RUN --mount=type=secret,id=tramiton_token \
if [ -s /run/secrets/tramiton_token ]; then \
git config --global \
url."https://sharang:$(cat /run/secrets/tramiton_token)@gitea.meghsakha.com/".insteadOf \
"ssh://git@gitea.meghsakha.com:22222/"; \
fi && \
CARGO_NET_GIT_FETCH_WITH_CLI=true dx build --release --package compliance-dashboard
RUN dx build --release --package compliance-dashboard
FROM debian:bookworm-slim
RUN apt-get update && apt-get install -y ca-certificates libssl3 && rm -rf /var/lib/apt/lists/*
+1 -10
View File
@@ -2,16 +2,7 @@ FROM rust:1.94-bookworm AS builder
WORKDIR /app
COPY . .
# compliance-agent (a workspace member) depends on the private tramiton-core git
# repo, so the workspace resolve needs it even to build the mcp binary.
# Authenticate the fetch with a PAT passed as a BuildKit secret.
RUN --mount=type=secret,id=tramiton_token \
if [ -s /run/secrets/tramiton_token ]; then \
git config --global \
url."https://sharang:$(cat /run/secrets/tramiton_token)@gitea.meghsakha.com/".insteadOf \
"ssh://git@gitea.meghsakha.com:22222/"; \
fi && \
CARGO_NET_GIT_FETCH_WITH_CLI=true cargo build --release -p compliance-mcp
RUN cargo build --release -p compliance-mcp
FROM debian:bookworm-slim
RUN apt-get update && apt-get install -y ca-certificates libssl3 && rm -rf /var/lib/apt/lists/*
+2 -15
View File
@@ -10,16 +10,6 @@ workspace = true
compliance-core = { workspace = true, features = ["mongodb", "telemetry", "axum"] }
compliance-graph = { path = "../compliance-graph" }
compliance-dast = { path = "../compliance-dast" }
# Native firmware build/target detection for bare-metal & RTOS artifacts.
# Same-company IP, used directly (not via CLI) so the whole tramiton suite is
# available to the onboarding classifier. NOTE: CI must be able to fetch this
# private repo (see the git-auth step in .gitea/workflows/ci.yml).
tramiton-core = { git = "ssh://git@gitea.meghsakha.com:22222/sharang/tramiton.git", tag = "v0.4.1" }
# tramiton-repro drives the reproducible build (NixBackend seal_and_build) that
# yields a sealed lock; `libraries_from_inputs` is the analysis-only fallback.
tramiton-repro = { git = "ssh://git@gitea.meghsakha.com:22222/sharang/tramiton.git", tag = "v0.4.1" }
# tramiton-sbom renders the bill of materials from a sealed lock (+ binary SCA).
tramiton-sbom = { git = "ssh://git@gitea.meghsakha.com:22222/sharang/tramiton.git", tag = "v0.4.1" }
serde = { workspace = true }
serde_json = { workspace = true }
tokio = { workspace = true }
@@ -34,7 +24,7 @@ hex = { workspace = true }
uuid = { workspace = true }
secrecy = { workspace = true }
regex = { workspace = true }
axum = { version = "0.8", features = ["multipart"] }
axum = "0.8"
tower-http = { version = "0.6", features = ["cors", "trace", "set-header"] }
git2 = "0.20"
octocrab = "0.44"
@@ -42,8 +32,6 @@ 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"
@@ -54,7 +42,6 @@ tokio-tungstenite = { version = "0.26", features = ["rustls-tls-webpki-roots"] }
futures-core = "0.3"
dashmap = { workspace = true }
tokio-stream = { workspace = true }
rand = { workspace = true }
[dev-dependencies]
compliance-core = { workspace = true, features = ["mongodb", "axum"] }
@@ -65,5 +52,5 @@ tokio = { workspace = true }
mongodb = { workspace = true }
uuid = { workspace = true }
secrecy = { workspace = true }
axum = { version = "0.8", features = ["multipart"] }
axum = "0.8"
tower-http = { version = "0.6", features = ["cors"] }
+25 -41
View File
@@ -6,7 +6,7 @@ use tokio::sync::{broadcast, watch, Semaphore};
use compliance_core::models::pentest::PentestEvent;
use compliance_core::AgentConfig;
use crate::database::DatabasePool;
use crate::database::Database;
use crate::llm::LlmClient;
use crate::pipeline::orchestrator::PipelineOrchestrator;
@@ -16,10 +16,7 @@ const DEFAULT_MAX_CONCURRENT_SESSIONS: usize = 5;
#[derive(Clone)]
pub struct ComplianceAgent {
pub config: AgentConfig,
/// Per-tenant Mongo broker. Every code path must obtain a
/// tenant-scoped [`crate::database::Database`] from this pool —
/// there is no single shared database any more.
pub db_pool: DatabasePool,
pub db: Database,
pub llm: Arc<LlmClient>,
pub http: reqwest::Client,
/// Per-session broadcast senders for SSE streaming.
@@ -31,7 +28,7 @@ pub struct ComplianceAgent {
}
impl ComplianceAgent {
pub fn new(config: AgentConfig, db_pool: DatabasePool) -> Self {
pub fn new(config: AgentConfig, db: Database) -> Self {
let llm = Arc::new(LlmClient::new(
config.litellm_url.clone(),
config.litellm_api_key.clone(),
@@ -45,7 +42,7 @@ impl ComplianceAgent {
.unwrap_or_default();
Self {
config,
db_pool,
db,
llm,
http,
session_streams: Arc::new(DashMap::new()),
@@ -56,57 +53,44 @@ impl ComplianceAgent {
pub async fn run_scan(
&self,
tenant_id: &str,
repo_id: &str,
trigger: compliance_core::models::ScanTrigger,
) -> Result<(), crate::error::AgentError> {
let db = self.db_pool.for_tenant_id(tenant_id).await?;
let orchestrator =
PipelineOrchestrator::new(self.config.clone(), db, self.llm.clone(), self.http.clone());
orchestrator.run_target(repo_id, trigger).await
}
/// Alias for [`Self::run_scan`] — every scan runs the unified onboarded-target
/// pipeline. Kept as a distinct name for the `/targets/{id}/scan` endpoint's
/// intent.
pub async fn run_target_scan(
&self,
tenant_id: &str,
target_id: &str,
trigger: compliance_core::models::ScanTrigger,
) -> Result<(), crate::error::AgentError> {
let db = self.db_pool.for_tenant_id(tenant_id).await?;
let orchestrator =
PipelineOrchestrator::new(self.config.clone(), db, self.llm.clone(), self.http.clone());
orchestrator.run_target(target_id, trigger).await
let orchestrator = PipelineOrchestrator::new(
self.config.clone(),
self.db.clone(),
self.llm.clone(),
self.http.clone(),
);
orchestrator.run(repo_id, trigger).await
}
/// Run a PR review: scan the diff and post review comments.
pub async fn run_pr_review(
&self,
tenant_id: &str,
repo_id: &str,
pr_number: u64,
base_sha: &str,
head_sha: &str,
) -> Result<(), crate::error::AgentError> {
let db = self.db_pool.for_tenant_id(tenant_id).await?;
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 })
let repo = self
.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()))?
})
.await?
.ok_or_else(|| {
crate::error::AgentError::Other(format!("Target {repo_id} not found"))
crate::error::AgentError::Other(format!("Repository {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());
let orchestrator = PipelineOrchestrator::new(
self.config.clone(),
self.db.clone(),
self.llm.clone(),
self.http.clone(),
);
orchestrator
.run_pr_review(&repo, repo_id, pr_number, base_sha, head_sha)
.await
-115
View File
@@ -1,115 +0,0 @@
//! Cross-tenant admin endpoints (`/api/v1/admin/*`).
//!
//! Operator-only. Auth is a **static bearer token** (`ADMIN_API_TOKEN`
//! env on the agent) — explicitly NOT a Keycloak JWT, because the
//! whole point of these endpoints is to operate ACROSS tenants. A
//! customer JWT (which always carries a single tenant_id) has no
//! business mounting them.
//!
//! Routes are only registered when `ADMIN_API_TOKEN` is set. With no
//! token, the endpoints don't exist at all (404), which is a stronger
//! guarantee than "401 if you guess the path".
//!
//! Operations:
//! - `GET /api/v1/admin/tenants` — list tenant DBs
//! - `DELETE /api/v1/admin/tenants/{tenant_id}` — GDPR delete
//!
//! Tenant ids in URLs are passed as-is to `DatabasePool::drop_tenant`,
//! which sanitises them the same way it does for creation. Listing
//! returns the raw DB names from `list_tenant_db_names` — operators
//! can reverse-derive the tenant_id from the prefix.
use axum::extract::{Extension, Path, Request};
use axum::http::{header, StatusCode};
use axum::middleware::Next;
use axum::response::{IntoResponse, Response};
use axum::Json;
use secrecy::ExposeSecret;
use serde::Serialize;
use super::dto::AgentExt;
#[derive(Serialize)]
pub struct ListTenantDbsResponse {
pub tenant_db_names: Vec<String>,
}
#[tracing::instrument(skip_all)]
pub async fn list_tenant_dbs(
Extension(agent): AgentExt,
) -> Result<Json<ListTenantDbsResponse>, StatusCode> {
let names = agent.db_pool.list_tenant_db_names().await.map_err(|e| {
tracing::error!("admin: list_tenant_db_names failed: {e}");
StatusCode::INTERNAL_SERVER_ERROR
})?;
Ok(Json(ListTenantDbsResponse {
tenant_db_names: names,
}))
}
#[tracing::instrument(skip_all, fields(tenant_id = %tenant_id))]
pub async fn drop_tenant_db(
Extension(agent): AgentExt,
Path(tenant_id): Path<String>,
) -> Result<Json<serde_json::Value>, StatusCode> {
agent.db_pool.drop_tenant(&tenant_id).await.map_err(|e| {
tracing::error!("admin: drop_tenant failed: {e}");
StatusCode::INTERNAL_SERVER_ERROR
})?;
Ok(Json(serde_json::json!({ "status": "dropped" })))
}
/// Constant-time-ish comparison of the configured admin token against
/// the incoming bearer. Uses `subtle`-style byte equality so timing
/// attacks can't probe the token character by character.
fn tokens_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
}
/// Middleware enforcing the static `ADMIN_API_TOKEN`. Mounted only on
/// the admin sub-router, so this never runs on customer routes.
pub async fn require_admin_token(
Extension(agent): AgentExt,
request: Request,
next: Next,
) -> Response {
let Some(expected) = agent.config.admin_api_token.as_ref() else {
// Belt-and-braces — if the routes were somehow mounted without
// a token configured, refuse rather than no-op-pass.
return (StatusCode::NOT_FOUND, "admin 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(|s| s.trim());
let Some(presented) = presented.filter(|s| !s.is_empty()) else {
return (StatusCode::UNAUTHORIZED, "Missing bearer token").into_response();
};
if !tokens_eq(presented, expected.expose_secret()) {
return (StatusCode::UNAUTHORIZED, "Invalid admin token").into_response();
}
next.run(request).await
}
#[cfg(test)]
mod tests {
use super::*;
#[test]
fn tokens_eq_basic() {
assert!(tokens_eq("abc", "abc"));
assert!(!tokens_eq("abc", "abd"));
assert!(!tokens_eq("abc", "abcd"));
assert!(!tokens_eq("", "x"));
assert!(tokens_eq("", ""));
}
}
+28 -40
View File
@@ -7,13 +7,11 @@ use mongodb::bson::doc;
use compliance_core::models::chat::{ChatRequest, ChatResponse, SourceReference};
use compliance_core::models::embedding::EmbeddingBuildRun;
use compliance_core::tenant_ctx::TenantCtx;
use compliance_graph::graph::embedding_store::EmbeddingStore;
use crate::agent::ComplianceAgent;
use crate::rag::pipeline::RagPipeline;
use super::dto::tenant_db;
use super::ApiResponse;
type AgentExt = Extension<Arc<ComplianceAgent>>;
@@ -22,12 +20,10 @@ type AgentExt = Extension<Arc<ComplianceAgent>>;
#[tracing::instrument(skip_all, fields(repo_id = %repo_id))]
pub async fn chat(
Extension(agent): AgentExt,
tenant: TenantCtx,
Path(repo_id): Path<String>,
Json(req): Json<ChatRequest>,
) -> Result<Json<ApiResponse<ChatResponse>>, StatusCode> {
let db = tenant_db(&agent, &tenant).await?;
let pipeline = RagPipeline::new(agent.llm.clone(), db.inner());
let pipeline = RagPipeline::new(agent.llm.clone(), agent.db.inner());
// Step 1: Embed the user's message
let query_vectors = agent
@@ -137,16 +133,13 @@ pub async fn chat(
#[tracing::instrument(skip_all, fields(repo_id = %repo_id))]
pub async fn build_embeddings(
Extension(agent): AgentExt,
tenant: TenantCtx,
Path(repo_id): Path<String>,
) -> Result<Json<serde_json::Value>, StatusCode> {
// Resolve the tenant DB up front so we can move it into the spawn;
// the JWT/dev context isn't available inside detached tasks.
let db = tenant_db(&agent, &tenant).await?;
let agent_clone = (*agent).clone();
tokio::spawn(async move {
let repo = match db
.onboarded_targets()
let repo = match agent_clone
.db
.repositories()
.find_one(doc! { "_id": mongodb::bson::oid::ObjectId::parse_str(&repo_id).ok() })
.await
{
@@ -158,7 +151,8 @@ pub async fn build_embeddings(
};
// Get latest graph build
let build = match db
let build = match agent_clone
.db
.graph_builds()
.find_one(doc! { "repo_id": &repo_id })
.sort(doc! { "started_at": -1 })
@@ -177,39 +171,35 @@ pub async fn build_embeddings(
.unwrap_or_else(|| "unknown".to_string());
// Get nodes
let nodes: Vec<compliance_core::models::graph::CodeNode> =
match db.graph_nodes().find(doc! { "repo_id": &repo_id }).await {
Ok(cursor) => {
use futures_util::StreamExt;
let mut items = Vec::new();
let mut cursor = cursor;
while let Some(Ok(item)) = cursor.next().await {
items.push(item);
}
items
let nodes: Vec<compliance_core::models::graph::CodeNode> = match agent_clone
.db
.graph_nodes()
.find(doc! { "repo_id": &repo_id })
.await
{
Ok(cursor) => {
use futures_util::StreamExt;
let mut items = Vec::new();
let mut cursor = cursor;
while let Some(Ok(item)) = cursor.next().await {
items.push(item);
}
Err(e) => {
tracing::error!("[{repo_id}] Failed to fetch nodes: {e}");
return;
}
};
let code = match repo.code_artifact() {
Some(c) => c,
None => {
tracing::error!("Target {repo_id} has no code artifact for embedding build");
items
}
Err(e) => {
tracing::error!("[{repo_id}] Failed to fetch nodes: {e}");
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: view.auth_token.clone(),
auth_username: view.auth_username.clone(),
auth_token: repo.auth_token.clone(),
auth_username: repo.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(&view.git_url, &view.name) {
let repo_path = match git_ops.clone_or_fetch(&repo.git_url, &repo.name) {
Ok(p) => p,
Err(e) => {
tracing::error!("Failed to clone repo for embedding build: {e}");
@@ -217,7 +207,7 @@ pub async fn build_embeddings(
}
};
let pipeline = RagPipeline::new(agent_clone.llm.clone(), db.inner());
let pipeline = RagPipeline::new(agent_clone.llm.clone(), agent_clone.db.inner());
match pipeline
.build_embeddings(&repo_id, &repo_path, &graph_build_id, &nodes)
.await
@@ -244,11 +234,9 @@ pub async fn build_embeddings(
#[tracing::instrument(skip_all, fields(repo_id = %repo_id))]
pub async fn embedding_status(
Extension(agent): AgentExt,
tenant: TenantCtx,
Path(repo_id): Path<String>,
) -> Result<Json<ApiResponse<Option<EmbeddingBuildRun>>>, StatusCode> {
let db = tenant_db(&agent, &tenant).await?;
let store = EmbeddingStore::new(db.inner());
let store = EmbeddingStore::new(agent.db.inner());
let build = store.get_latest_build(&repo_id).await.map_err(|e| {
tracing::error!("Failed to get embedding status: {e}");
StatusCode::INTERNAL_SERVER_ERROR
+11 -20
View File
@@ -7,11 +7,9 @@ use mongodb::bson::doc;
use serde::Deserialize;
use compliance_core::models::dast::{DastFinding, DastScanRun, DastTarget, DastTargetType};
use compliance_core::tenant_ctx::TenantCtx;
use crate::agent::ComplianceAgent;
use super::dto::tenant_db;
use super::{collect_cursor_async, ApiResponse, PaginationParams};
type AgentExt = Extension<Arc<ComplianceAgent>>;
@@ -47,11 +45,9 @@ fn default_rate_limit() -> u32 {
#[tracing::instrument(skip_all)]
pub async fn list_targets(
Extension(agent): AgentExt,
tenant: TenantCtx,
Query(params): Query<PaginationParams>,
) -> Result<Json<ApiResponse<Vec<DastTarget>>>, StatusCode> {
let db = tenant_db(&agent, &tenant).await?;
let db = &db;
let db = &agent.db;
let skip = (params.page.saturating_sub(1)) * params.limit as u64;
let total = db
.dast_targets()
@@ -84,7 +80,6 @@ pub async fn list_targets(
#[tracing::instrument(skip_all)]
pub async fn add_target(
Extension(agent): AgentExt,
tenant: TenantCtx,
Json(req): Json<AddTargetRequest>,
) -> Result<Json<ApiResponse<DastTarget>>, StatusCode> {
let mut target = DastTarget::new(req.name, req.base_url, req.target_type);
@@ -94,8 +89,9 @@ pub async fn add_target(
target.rate_limit = req.rate_limit;
target.allow_destructive = req.allow_destructive;
let db = tenant_db(&agent, &tenant).await?;
db.dast_targets()
agent
.db
.dast_targets()
.insert_one(&target)
.await
.map_err(|_| StatusCode::INTERNAL_SERVER_ERROR)?;
@@ -111,19 +107,19 @@ pub async fn add_target(
#[tracing::instrument(skip_all, fields(target_id = %id))]
pub async fn trigger_scan(
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 target = db
let target = agent
.db
.dast_targets()
.find_one(doc! { "_id": oid })
.await
.map_err(|_| StatusCode::INTERNAL_SERVER_ERROR)?
.ok_or(StatusCode::NOT_FOUND)?;
let db = agent.db.clone();
tokio::spawn(async move {
let orchestrator = compliance_dast::DastOrchestrator::new(100);
match orchestrator.run_scan(&target, Vec::new()).await {
@@ -151,11 +147,9 @@ pub async fn trigger_scan(
#[tracing::instrument(skip_all)]
pub async fn list_scan_runs(
Extension(agent): AgentExt,
tenant: TenantCtx,
Query(params): Query<PaginationParams>,
) -> Result<Json<ApiResponse<Vec<DastScanRun>>>, StatusCode> {
let db = tenant_db(&agent, &tenant).await?;
let db = &db;
let db = &agent.db;
let skip = (params.page.saturating_sub(1)) * params.limit as u64;
let total = db
.dast_scan_runs()
@@ -189,11 +183,9 @@ pub async fn list_scan_runs(
#[tracing::instrument(skip_all)]
pub async fn list_findings(
Extension(agent): AgentExt,
tenant: TenantCtx,
Query(params): Query<PaginationParams>,
) -> Result<Json<ApiResponse<Vec<DastFinding>>>, StatusCode> {
let db = tenant_db(&agent, &tenant).await?;
let db = &db;
let db = &agent.db;
let skip = (params.page.saturating_sub(1)) * params.limit as u64;
let total = db
.dast_findings()
@@ -227,13 +219,12 @@ pub async fn list_findings(
#[tracing::instrument(skip_all, fields(finding_id = %id))]
pub async fn get_finding(
Extension(agent): AgentExt,
tenant: TenantCtx,
Path(id): Path<String>,
) -> Result<Json<ApiResponse<DastFinding>>, StatusCode> {
let oid = mongodb::bson::oid::ObjectId::parse_str(&id).map_err(|_| StatusCode::BAD_REQUEST)?;
let db = tenant_db(&agent, &tenant).await?;
let finding = db
let finding = agent
.db
.dast_findings()
.find_one(doc! { "_id": oid })
.await
-21
View File
@@ -180,27 +180,6 @@ pub struct SbomVersionDiff {
pub(crate) type AgentExt = axum::extract::Extension<std::sync::Arc<crate::agent::ComplianceAgent>>;
pub(crate) type ApiResult<T> = Result<axum::Json<ApiResponse<T>>, axum::http::StatusCode>;
/// Resolve a tenant-scoped [`Database`] from the request's
/// [`TenantContext`] (inserted by the M7.1 JWT middleware, or by the
/// dev fallback in unsecured environments). The pool ensures the
/// tenant's indexes idempotently.
///
/// Returns 500 on the rare path where Mongo refuses the database
/// handle — the M7.1 auth/status middleware already rejects every
/// other failure mode with 4xx before we get here.
pub(crate) async fn tenant_db(
agent: &crate::agent::ComplianceAgent,
tenant: &compliance_core::tenant_ctx::TenantCtx,
) -> Result<crate::database::Database, axum::http::StatusCode> {
agent.db_pool.for_tenant(&tenant.0).await.map_err(|e| {
tracing::error!(
tenant_id = %tenant.0.tenant_id,
"Failed to acquire tenant database: {e}"
);
axum::http::StatusCode::INTERNAL_SERVER_ERROR
})
}
pub(crate) async fn collect_cursor_async<T: serde::de::DeserializeOwned + Unpin + Send>(
mut cursor: mongodb::Cursor<T>,
) -> Vec<T> {
+11 -16
View File
@@ -5,16 +5,13 @@ use mongodb::bson::doc;
use super::dto::*;
use compliance_core::models::Finding;
use compliance_core::tenant_ctx::TenantCtx;
#[tracing::instrument(skip_all, fields(repo_id = ?filter.repo_id, severity = ?filter.severity, scan_type = ?filter.scan_type))]
pub async fn list_findings(
Extension(agent): AgentExt,
tenant: TenantCtx,
Query(filter): Query<FindingsFilter>,
) -> ApiResult<Vec<Finding>> {
let db = tenant_db(&agent, &tenant).await?;
let db = &db;
let db = &agent.db;
let mut query = doc! {};
if let Some(repo_id) = &filter.repo_id {
query.insert("repo_id", repo_id);
@@ -84,12 +81,11 @@ pub async fn list_findings(
#[tracing::instrument(skip_all, fields(finding_id = %id))]
pub async fn get_finding(
Extension(agent): AgentExt,
tenant: TenantCtx,
Path(id): Path<String>,
) -> Result<Json<ApiResponse<Finding>>, StatusCode> {
let oid = mongodb::bson::oid::ObjectId::parse_str(&id).map_err(|_| StatusCode::BAD_REQUEST)?;
let db = tenant_db(&agent, &tenant).await?;
let finding = db
let finding = agent
.db
.findings()
.find_one(doc! { "_id": oid })
.await
@@ -106,14 +102,14 @@ pub async fn get_finding(
#[tracing::instrument(skip_all, fields(finding_id = %id))]
pub async fn update_finding_status(
Extension(agent): AgentExt,
tenant: TenantCtx,
Path(id): Path<String>,
Json(req): Json<UpdateStatusRequest>,
) -> 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?;
db.findings()
agent
.db
.findings()
.update_one(
doc! { "_id": oid },
doc! { "$set": { "status": &req.status, "updated_at": mongodb::bson::DateTime::now() } },
@@ -127,7 +123,6 @@ pub async fn update_finding_status(
#[tracing::instrument(skip_all)]
pub async fn bulk_update_finding_status(
Extension(agent): AgentExt,
tenant: TenantCtx,
Json(req): Json<BulkUpdateStatusRequest>,
) -> Result<Json<serde_json::Value>, StatusCode> {
let oids: Vec<mongodb::bson::oid::ObjectId> = req
@@ -140,8 +135,8 @@ pub async fn bulk_update_finding_status(
return Err(StatusCode::BAD_REQUEST);
}
let db = tenant_db(&agent, &tenant).await?;
let result = db
let result = agent
.db
.findings()
.update_many(
doc! { "_id": { "$in": oids } },
@@ -158,14 +153,14 @@ pub async fn bulk_update_finding_status(
#[tracing::instrument(skip_all)]
pub async fn update_finding_feedback(
Extension(agent): AgentExt,
tenant: TenantCtx,
Path(id): Path<String>,
Json(req): Json<UpdateFeedbackRequest>,
) -> 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?;
db.findings()
agent
.db
.findings()
.update_one(
doc! { "_id": oid },
doc! { "$set": { "developer_feedback": &req.feedback, "updated_at": mongodb::bson::DateTime::now() } },
+15 -37
View File
@@ -7,11 +7,9 @@ use mongodb::bson::doc;
use serde::{Deserialize, Serialize};
use compliance_core::models::graph::{CodeEdge, CodeNode, GraphBuildRun, ImpactAnalysis};
use compliance_core::tenant_ctx::TenantCtx;
use crate::agent::ComplianceAgent;
use super::dto::tenant_db;
use super::{collect_cursor_async, ApiResponse};
type AgentExt = Extension<Arc<ComplianceAgent>>;
@@ -38,11 +36,9 @@ fn default_search_limit() -> usize {
#[tracing::instrument(skip_all, fields(repo_id = %repo_id))]
pub async fn get_graph(
Extension(agent): AgentExt,
tenant: TenantCtx,
Path(repo_id): Path<String>,
) -> Result<Json<ApiResponse<GraphData>>, StatusCode> {
let db = tenant_db(&agent, &tenant).await?;
let db = &db;
let db = &agent.db;
// Get latest build
let build: Option<GraphBuildRun> = db
@@ -102,11 +98,9 @@ pub async fn get_graph(
#[tracing::instrument(skip_all, fields(repo_id = %repo_id))]
pub async fn get_nodes(
Extension(agent): AgentExt,
tenant: TenantCtx,
Path(repo_id): Path<String>,
) -> Result<Json<ApiResponse<Vec<CodeNode>>>, StatusCode> {
let db = tenant_db(&agent, &tenant).await?;
let db = &db;
let db = &agent.db;
let filter = doc! { "repo_id": &repo_id };
let nodes: Vec<CodeNode> = match db.graph_nodes().find(filter).await {
@@ -129,11 +123,9 @@ pub async fn get_nodes(
#[tracing::instrument(skip_all, fields(repo_id = %repo_id))]
pub async fn get_communities(
Extension(agent): AgentExt,
tenant: TenantCtx,
Path(repo_id): Path<String>,
) -> Result<Json<ApiResponse<Vec<CommunityInfo>>>, StatusCode> {
let db = tenant_db(&agent, &tenant).await?;
let db = &db;
let db = &agent.db;
let filter = doc! { "repo_id": &repo_id };
let nodes: Vec<CodeNode> = match db.graph_nodes().find(filter).await {
@@ -184,11 +176,9 @@ pub struct CommunityInfo {
#[tracing::instrument(skip_all, fields(repo_id = %repo_id, finding_id = %finding_id))]
pub async fn get_impact(
Extension(agent): AgentExt,
tenant: TenantCtx,
Path((repo_id, finding_id)): Path<(String, String)>,
) -> Result<Json<ApiResponse<Option<ImpactAnalysis>>>, StatusCode> {
let db = tenant_db(&agent, &tenant).await?;
let db = &db;
let db = &agent.db;
let filter = doc! { "repo_id": &repo_id, "finding_id": &finding_id };
let impact = db
@@ -208,12 +198,10 @@ pub async fn get_impact(
#[tracing::instrument(skip_all, fields(repo_id = %repo_id, query = %params.q))]
pub async fn search_symbols(
Extension(agent): AgentExt,
tenant: TenantCtx,
Path(repo_id): Path<String>,
Query(params): Query<SearchParams>,
) -> Result<Json<ApiResponse<Vec<CodeNode>>>, StatusCode> {
let db = tenant_db(&agent, &tenant).await?;
let db = &db;
let db = &agent.db;
// Simple text search on qualified_name and name fields
let filter = doc! {
@@ -246,16 +234,14 @@ pub async fn search_symbols(
#[tracing::instrument(skip_all, fields(repo_id = %repo_id))]
pub async fn get_file_content(
Extension(agent): AgentExt,
tenant: TenantCtx,
Path(repo_id): Path<String>,
Query(params): Query<FileContentParams>,
) -> Result<Json<ApiResponse<FileContent>>, StatusCode> {
let db = tenant_db(&agent, &tenant).await?;
let db = &db;
let db = &agent.db;
// Look up the repository to get repo name
let repo = db
.onboarded_targets()
.repositories()
.find_one(doc! { "_id": mongodb::bson::oid::ObjectId::parse_str(&repo_id).ok() })
.await
.map_err(|_| StatusCode::INTERNAL_SERVER_ERROR)?
@@ -310,14 +296,13 @@ pub struct FileContent {
#[tracing::instrument(skip_all, fields(repo_id = %repo_id))]
pub async fn trigger_build(
Extension(agent): AgentExt,
tenant: TenantCtx,
Path(repo_id): Path<String>,
) -> Result<Json<serde_json::Value>, StatusCode> {
let db = tenant_db(&agent, &tenant).await?;
let agent_clone = (*agent).clone();
tokio::spawn(async move {
let repo = match db
.onboarded_targets()
let repo = match agent_clone
.db
.repositories()
.find_one(doc! { "_id": mongodb::bson::oid::ObjectId::parse_str(&repo_id).ok() })
.await
{
@@ -328,22 +313,14 @@ 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: view.auth_token.clone(),
auth_username: view.auth_username.clone(),
auth_token: repo.auth_token.clone(),
auth_username: repo.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(&view.git_url, &view.name) {
let repo_path = match git_ops.clone_or_fetch(&repo.git_url, &repo.name) {
Ok(p) => p,
Err(e) => {
tracing::error!("Failed to clone repo for graph build: {e}");
@@ -356,7 +333,8 @@ pub async fn trigger_build(
match engine.build_graph(&repo_path, &repo_id, &graph_build_id) {
Ok((code_graph, build_run)) => {
let store = compliance_graph::graph::persistence::GraphStore::new(db.inner());
let store =
compliance_graph::graph::persistence::GraphStore::new(agent_clone.db.inner());
let _ = store.delete_repo_graph(&repo_id).await;
let _ = store
.store_graph(&build_run, &code_graph.nodes, &code_graph.edges)
+3 -20
View File
@@ -3,35 +3,18 @@ use mongodb::bson::doc;
use super::dto::*;
use compliance_core::models::ScanRun;
use compliance_core::tenant_ctx::TenantCtx;
#[tracing::instrument(skip_all)]
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,
tenant: TenantCtx,
) -> ApiResult<OverviewStats> {
let db = tenant_db(&agent, &tenant).await?;
let db = &db;
pub async fn stats_overview(axum::extract::Extension(agent): AgentExt) -> ApiResult<OverviewStats> {
let db = &agent.db;
let total_repositories = db
.onboarded_targets()
.repositories()
.count_documents(doc! {})
.await
.unwrap_or(0);
+1 -4
View File
@@ -4,16 +4,13 @@ use mongodb::bson::doc;
use super::dto::*;
use compliance_core::models::TrackerIssue;
use compliance_core::tenant_ctx::TenantCtx;
#[tracing::instrument(skip_all)]
pub async fn list_issues(
Extension(agent): AgentExt,
tenant: TenantCtx,
Query(params): Query<PaginationParams>,
) -> ApiResult<Vec<TrackerIssue>> {
let db = tenant_db(&agent, &tenant).await?;
let db = &db;
let db = &agent.db;
let skip = (params.page.saturating_sub(1)) * params.limit as u64;
let total = db
.tracker_issues()
@@ -1,186 +0,0 @@
//! `/api/v1/mcp-tokens` — per-tenant API tokens for the MCP server.
//!
//! These are opaque static bearers issued via the dashboard (or a
//! direct curl with a KC JWT) and copied into LLM clients (Claude
//! Desktop / Cursor / ChatGPT). The MCP server hashes incoming bearers
//! and looks them up in the cross-tenant `<prefix>__admin.mcp_tokens`
//! collection to derive the tenant_id for routing.
//!
//! The raw token is shown to the caller exactly once at creation; the
//! database only ever stores the SHA-256 hash. Revocation is a soft
//! delete (sets `revoked: true`) so the audit log keeps the record.
use axum::extract::{Extension, Path};
use axum::http::StatusCode;
use axum::Json;
use base64::{engine::general_purpose::URL_SAFE_NO_PAD, Engine as _};
use compliance_core::models::{McpToken, McpTokenView};
use compliance_core::tenant_ctx::TenantCtx;
use mongodb::bson::doc;
use rand::RngCore;
use sha2::{Digest, Sha256};
use super::dto::{AgentExt, ApiResponse};
/// Mongo collection name inside the admin DB.
const COLLECTION: &str = "mcp_tokens";
/// Token prefix the MCP server expects on every bearer.
const TOKEN_PREFIX: &str = "mcpt_";
/// Bytes of randomness behind each token. 32 → ~256 bits.
/// Encoded as URL-safe base64 without padding → 43 chars.
/// Combined with `mcpt_` → 48-char tokens.
const TOKEN_RAND_BYTES: usize = 32;
#[derive(serde::Deserialize)]
pub struct CreateMcpTokenRequest {
pub name: String,
}
/// Returned exactly once at creation. The `token` field is gone from
/// the listing endpoint — the user must save it now.
#[derive(serde::Serialize)]
pub struct CreateMcpTokenResponse {
pub token: String,
pub view: McpTokenView,
}
/// `POST /api/v1/mcp-tokens` — mint a new token for the caller's tenant.
#[tracing::instrument(skip_all)]
pub async fn create_mcp_token(
Extension(agent): AgentExt,
tenant: TenantCtx,
Json(req): Json<CreateMcpTokenRequest>,
) -> Result<Json<CreateMcpTokenResponse>, StatusCode> {
if req.name.trim().is_empty() {
return Err(StatusCode::BAD_REQUEST);
}
let raw = generate_token();
let token_hash = sha256_hex(&raw);
let token_prefix: String = raw.chars().take(12).collect();
let mut token = McpToken {
id: None,
token_hash,
token_prefix,
tenant_id: tenant.0.tenant_id.clone(),
name: req.name.trim().to_string(),
created_by: tenant.0.user_id.clone(),
created_at: chrono::Utc::now(),
last_used_at: None,
revoked: false,
};
let col = agent.db_pool.admin_db().collection::<McpToken>(COLLECTION);
let res = col.insert_one(&token).await.map_err(|e| {
tracing::error!("Failed to insert MCP token: {e}");
StatusCode::INTERNAL_SERVER_ERROR
})?;
token.id = res.inserted_id.as_object_id();
Ok(Json(CreateMcpTokenResponse {
view: McpTokenView::from(&token),
token: raw,
}))
}
/// `GET /api/v1/mcp-tokens` — list tokens for the caller's tenant.
/// Hash is never returned; only metadata + the 12-char prefix so the
/// user can identify which row is which.
#[tracing::instrument(skip_all)]
pub async fn list_mcp_tokens(
Extension(agent): AgentExt,
tenant: TenantCtx,
) -> Result<Json<ApiResponse<Vec<McpTokenView>>>, StatusCode> {
let col = agent.db_pool.admin_db().collection::<McpToken>(COLLECTION);
let mut cursor = col
.find(doc! { "tenant_id": &tenant.0.tenant_id })
.sort(doc! { "created_at": -1 })
.await
.map_err(|e| {
tracing::error!("Failed to list MCP tokens: {e}");
StatusCode::INTERNAL_SERVER_ERROR
})?;
let mut out = Vec::new();
while cursor.advance().await.map_err(|e| {
tracing::warn!("MCP tokens cursor advance failed: {e}");
StatusCode::INTERNAL_SERVER_ERROR
})? {
match cursor.deserialize_current() {
Ok(t) => out.push(McpTokenView::from(&t)),
Err(e) => tracing::warn!("Failed to deserialize MCP token: {e}"),
}
}
Ok(Json(ApiResponse {
data: out,
total: None,
page: None,
}))
}
/// `DELETE /api/v1/mcp-tokens/{id}` — revoke (soft delete).
/// Scoped to the caller's tenant: a user can't revoke another tenant's
/// token even if they guess its id.
#[tracing::instrument(skip_all, fields(id = %id))]
pub async fn revoke_mcp_token(
Extension(agent): AgentExt,
tenant: TenantCtx,
Path(id): Path<String>,
) -> Result<Json<serde_json::Value>, StatusCode> {
let oid = mongodb::bson::oid::ObjectId::parse_str(&id).map_err(|_| StatusCode::BAD_REQUEST)?;
let col = agent.db_pool.admin_db().collection::<McpToken>(COLLECTION);
let result = col
.update_one(
doc! { "_id": oid, "tenant_id": &tenant.0.tenant_id },
doc! { "$set": { "revoked": true } },
)
.await
.map_err(|e| {
tracing::error!("Failed to revoke MCP token: {e}");
StatusCode::INTERNAL_SERVER_ERROR
})?;
if result.matched_count == 0 {
return Err(StatusCode::NOT_FOUND);
}
Ok(Json(serde_json::json!({ "status": "revoked" })))
}
/// 32 bytes random → URL-safe base64 → 43 chars, no padding.
/// Prefixed with `mcpt_` so the MCP server can sniff the format
/// before bothering with the DB lookup.
fn generate_token() -> String {
let mut bytes = [0u8; TOKEN_RAND_BYTES];
rand::rng().fill_bytes(&mut bytes);
format!("{TOKEN_PREFIX}{}", URL_SAFE_NO_PAD.encode(bytes))
}
fn sha256_hex(s: &str) -> String {
let mut h = Sha256::new();
h.update(s.as_bytes());
hex::encode(h.finalize())
}
#[cfg(test)]
mod tests {
use super::*;
#[test]
fn generated_tokens_are_unique_and_prefixed() {
let a = generate_token();
let b = generate_token();
assert_ne!(a, b);
assert!(a.starts_with(TOKEN_PREFIX));
assert!(b.starts_with(TOKEN_PREFIX));
// 5 + 43 = 48 chars
assert_eq!(a.len(), 5 + 43);
}
#[test]
fn sha256_is_stable_and_64_hex() {
let h = sha256_hex("mcpt_abc");
assert_eq!(h.len(), 64);
assert!(h.chars().all(|c| c.is_ascii_hexdigit()));
assert_eq!(sha256_hex("mcpt_abc"), h);
}
}
+2 -3
View File
@@ -1,4 +1,3 @@
pub mod admin;
pub mod chat;
pub mod dast;
pub mod dto;
@@ -7,11 +6,10 @@ pub mod graph;
pub mod health;
pub mod help_chat;
pub mod issues;
pub mod mcp_tokens;
pub mod notifications;
pub mod onboarding;
pub mod pentest_handlers;
pub use pentest_handlers as pentest;
pub mod repos;
pub mod sbom;
pub mod scans;
@@ -20,5 +18,6 @@ pub use dto::*;
pub use findings::*;
pub use health::*;
pub use issues::*;
pub use repos::*;
pub use sbom::*;
pub use scans::*;
@@ -5,18 +5,15 @@ use mongodb::bson::doc;
use serde::Deserialize;
use compliance_core::models::notification::CveNotification;
use compliance_core::tenant_ctx::TenantCtx;
use super::dto::{tenant_db, AgentExt, ApiResponse};
use super::dto::{AgentExt, ApiResponse};
/// GET /api/v1/notifications — List CVE notifications (newest first)
#[tracing::instrument(skip_all)]
pub async fn list_notifications(
Extension(agent): AgentExt,
tenant: TenantCtx,
axum::extract::Query(params): axum::extract::Query<NotificationFilter>,
) -> Result<Json<ApiResponse<Vec<CveNotification>>>, StatusCode> {
let db = tenant_db(&agent, &tenant).await?;
let mut filter = doc! {};
// Filter by status (default: show new + read, exclude dismissed)
@@ -44,13 +41,15 @@ pub async fn list_notifications(
let limit = params.limit.unwrap_or(50).min(200);
let skip = (page - 1) * limit as u64;
let total = db
let total = agent
.db
.cve_notifications()
.count_documents(filter.clone())
.await
.unwrap_or(0);
let notifications: Vec<CveNotification> = match db
let notifications: Vec<CveNotification> = match agent
.db
.cve_notifications()
.find(filter)
.sort(doc! { "created_at": -1 })
@@ -84,10 +83,9 @@ pub async fn list_notifications(
#[tracing::instrument(skip_all)]
pub async fn notification_count(
Extension(agent): AgentExt,
tenant: TenantCtx,
) -> Result<Json<serde_json::Value>, StatusCode> {
let db = tenant_db(&agent, &tenant).await?;
let count = db
let count = agent
.db
.cve_notifications()
.count_documents(doc! { "status": "new" })
.await
@@ -100,13 +98,12 @@ pub async fn notification_count(
#[tracing::instrument(skip_all, fields(id = %id))]
pub async fn mark_read(
Extension(agent): AgentExt,
tenant: TenantCtx,
axum::extract::Path(id): axum::extract::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 result = db
let result = agent
.db
.cve_notifications()
.update_one(
doc! { "_id": oid },
@@ -128,13 +125,12 @@ pub async fn mark_read(
#[tracing::instrument(skip_all, fields(id = %id))]
pub async fn dismiss_notification(
Extension(agent): AgentExt,
tenant: TenantCtx,
axum::extract::Path(id): axum::extract::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 result = db
let result = agent
.db
.cve_notifications()
.update_one(
doc! { "_id": oid },
@@ -153,10 +149,9 @@ pub async fn dismiss_notification(
#[tracing::instrument(skip_all)]
pub async fn mark_all_read(
Extension(agent): AgentExt,
tenant: TenantCtx,
) -> Result<Json<serde_json::Value>, StatusCode> {
let db = tenant_db(&agent, &tenant).await?;
let result = db
let result = agent
.db
.cve_notifications()
.update_many(
doc! { "status": "new" },
@@ -1,614 +0,0 @@
//! Onboarding API — CRUD for unified targets, artifact add, classification, and
//! the scan-applicability matrix. The wizard (and future integrations) drive
//! onboarding through these endpoints.
use std::collections::HashMap;
use std::sync::Arc;
use axum::extract::{Extension, Multipart, Path, Query};
use axum::http::StatusCode;
use axum::Json;
use mongodb::bson::{doc, oid::ObjectId, to_bson};
use serde::{Deserialize, Serialize};
use compliance_core::models::{
Artifact, ArtifactKind, ComplianceProfile, OnboardedTarget, PlcFormat, TargetScanConfig,
TargetType,
};
use compliance_core::scan_matrix::{applicable_scans, supports_pentest};
use compliance_core::tenant_ctx::TenantCtx;
use crate::agent::ComplianceAgent;
use crate::classify::{classify_target, MockFirmwareDetector};
use super::dto::tenant_db;
use super::{collect_cursor_async, ApiResponse, PaginationParams};
type AgentExt = Extension<Arc<ComplianceAgent>>;
/// A client-supplied artifact spec. The server builds the [`Artifact`] (and its
/// id) from it, so clients never set internal fields.
#[derive(Deserialize)]
pub struct ArtifactInput {
pub kind: ArtifactKind,
pub source_ref: String,
#[serde(default)]
pub branch: Option<String>,
#[serde(default)]
pub plc_format: Option<PlcFormat>,
}
impl ArtifactInput {
fn build(&self) -> Artifact {
let s = self.source_ref.clone();
match self.kind {
ArtifactKind::GitRepo => {
Artifact::git_repo(s, self.branch.clone().unwrap_or_else(|| "main".to_string()))
}
ArtifactKind::LiveUrl => Artifact::live_url(s),
ArtifactKind::FirmwareImage => Artifact::firmware_image(s),
ArtifactKind::SourceArchive => Artifact::source_archive(s),
ArtifactKind::MobilePackage => Artifact::mobile_package(s),
ArtifactKind::ContainerImage => Artifact::container_image(s),
ArtifactKind::PlcProject => {
Artifact::plc_project(s, self.plc_format.unwrap_or(PlcFormat::PlcopenXml))
}
ArtifactKind::PlaintextDescription => Artifact::plaintext(s),
}
}
}
#[derive(Deserialize)]
pub struct CreateTargetRequest {
pub name: String,
pub target_type: TargetType,
#[serde(default)]
pub description: Option<String>,
#[serde(default)]
pub artifacts: Vec<ArtifactInput>,
}
#[derive(Deserialize)]
pub struct UpdateTargetRequest {
pub name: Option<String>,
pub target_type: Option<TargetType>,
pub scan_config: Option<TargetScanConfig>,
pub compliance_profile: Option<ComplianceProfile>,
pub scan_schedule: Option<String>,
/// Replace the target's artifacts wholesale (used by the dashboard editor).
#[serde(default)]
pub artifacts: Option<Vec<ArtifactInput>>,
}
/// One applicable-scan option, serialized for the wizard.
#[derive(Serialize)]
pub struct ScanOptionDto {
pub scan: String,
pub default_on: bool,
pub rationale: String,
pub required_artifact: Option<String>,
pub blocked_reason: Option<String>,
}
#[derive(Serialize)]
pub struct ApplicableScansResponse {
pub scans: Vec<ScanOptionDto>,
pub pentest_supported: bool,
}
fn parse_oid(id: &str) -> Result<ObjectId, StatusCode> {
ObjectId::parse_str(id).map_err(|_| StatusCode::BAD_REQUEST)
}
/// GET /api/v1/targets — list onboarded targets (paginated).
#[tracing::instrument(skip_all)]
pub async fn list_targets(
Extension(agent): AgentExt,
tenant: TenantCtx,
Query(params): Query<PaginationParams>,
) -> Result<Json<ApiResponse<Vec<OnboardedTarget>>>, StatusCode> {
let db = tenant_db(&agent, &tenant).await?;
let skip = (params.page.saturating_sub(1)) * params.limit as u64;
let total = db
.onboarded_targets()
.count_documents(doc! {})
.await
.unwrap_or(0);
let targets = match db
.onboarded_targets()
.find(doc! {})
.skip(skip)
.limit(params.limit)
.await
{
Ok(cursor) => collect_cursor_async(cursor).await,
Err(e) => {
tracing::warn!("Failed to fetch onboarded targets: {e}");
Vec::new()
}
};
Ok(Json(ApiResponse {
data: targets,
total: Some(total),
page: Some(params.page),
}))
}
/// POST /api/v1/targets — create an onboarded target.
#[tracing::instrument(skip_all)]
pub async fn create_target(
Extension(agent): AgentExt,
tenant: TenantCtx,
Json(req): Json<CreateTargetRequest>,
) -> Result<Json<ApiResponse<OnboardedTarget>>, StatusCode> {
let mut target = OnboardedTarget::new(req.name, req.target_type);
target.description = req.description;
target.artifacts = req.artifacts.iter().map(ArtifactInput::build).collect();
let db = tenant_db(&agent, &tenant).await?;
let res = db
.onboarded_targets()
.insert_one(&target)
.await
.map_err(|_| StatusCode::INTERNAL_SERVER_ERROR)?;
target.id = res.inserted_id.as_object_id();
Ok(Json(ApiResponse {
data: target,
total: None,
page: None,
}))
}
/// GET /api/v1/targets/{id} — fetch one target.
#[tracing::instrument(skip_all, fields(target_id = %id))]
pub async fn get_target(
Extension(agent): AgentExt,
tenant: TenantCtx,
Path(id): Path<String>,
) -> Result<Json<ApiResponse<OnboardedTarget>>, StatusCode> {
let oid = parse_oid(&id)?;
let db = tenant_db(&agent, &tenant).await?;
let target = db
.onboarded_targets()
.find_one(doc! { "_id": oid })
.await
.map_err(|_| StatusCode::INTERNAL_SERVER_ERROR)?
.ok_or(StatusCode::NOT_FOUND)?;
Ok(Json(ApiResponse {
data: target,
total: None,
page: None,
}))
}
/// PATCH /api/v1/targets/{id} — update mutable fields.
#[tracing::instrument(skip_all, fields(target_id = %id))]
pub async fn update_target(
Extension(agent): AgentExt,
tenant: TenantCtx,
Path(id): Path<String>,
Json(req): Json<UpdateTargetRequest>,
) -> Result<Json<ApiResponse<OnboardedTarget>>, StatusCode> {
let oid = parse_oid(&id)?;
let db = tenant_db(&agent, &tenant).await?;
let mut set = doc! { "updated_at": mongodb::bson::DateTime::now() };
if let Some(name) = req.name {
set.insert("name", name);
}
if let Some(tt) = req.target_type {
set.insert(
"target_type",
to_bson(&tt).map_err(|_| StatusCode::BAD_REQUEST)?,
);
}
if let Some(sc) = req.scan_config {
set.insert(
"scan_config",
to_bson(&sc).map_err(|_| StatusCode::BAD_REQUEST)?,
);
}
if let Some(cp) = req.compliance_profile {
set.insert(
"compliance_profile",
to_bson(&cp).map_err(|_| StatusCode::BAD_REQUEST)?,
);
}
if let Some(ss) = req.scan_schedule {
set.insert("scan_schedule", ss);
}
if let Some(arts) = req.artifacts {
let built: Vec<Artifact> = arts.iter().map(ArtifactInput::build).collect();
set.insert(
"artifacts",
to_bson(&built).map_err(|_| StatusCode::BAD_REQUEST)?,
);
}
db.onboarded_targets()
.update_one(doc! { "_id": oid }, doc! { "$set": set })
.await
.map_err(|_| StatusCode::INTERNAL_SERVER_ERROR)?;
get_target(Extension(agent), tenant, Path(id)).await
}
/// DELETE /api/v1/targets/{id} — remove the target and its findings/scans.
#[tracing::instrument(skip_all, fields(target_id = %id))]
pub async fn delete_target(
Extension(agent): AgentExt,
tenant: TenantCtx,
Path(id): Path<String>,
) -> Result<Json<serde_json::Value>, StatusCode> {
let oid = parse_oid(&id)?;
let db = tenant_db(&agent, &tenant).await?;
db.onboarded_targets()
.delete_one(doc! { "_id": oid })
.await
.map_err(|_| StatusCode::INTERNAL_SERVER_ERROR)?;
// Cascade all data keyed by repo_id == target id (best-effort).
let db = &db;
let _ = db.findings().delete_many(doc! { "repo_id": &id }).await;
let _ = db.sbom_entries().delete_many(doc! { "repo_id": &id }).await;
let _ = db.scan_runs().delete_many(doc! { "repo_id": &id }).await;
let _ = db.cve_alerts().delete_many(doc! { "repo_id": &id }).await;
let _ = db
.tracker_issues()
.delete_many(doc! { "repo_id": &id })
.await;
let _ = db.graph_nodes().delete_many(doc! { "repo_id": &id }).await;
let _ = db.graph_edges().delete_many(doc! { "repo_id": &id }).await;
let _ = db.graph_builds().delete_many(doc! { "repo_id": &id }).await;
let _ = db
.impact_analyses()
.delete_many(doc! { "repo_id": &id })
.await;
let _ = db
.code_embeddings()
.delete_many(doc! { "repo_id": &id })
.await;
let _ = db
.embedding_builds()
.delete_many(doc! { "repo_id": &id })
.await;
// DAST targets linked to this target, and all their downstream data.
if let Ok(mut cursor) = db.dast_targets().find(doc! { "repo_id": &id }).await {
use futures_util::StreamExt;
while let Some(Ok(dt)) = cursor.next().await {
let dast_target_id = dt.id.map(|oid| oid.to_hex()).unwrap_or_default();
if !dast_target_id.is_empty() {
cascade_delete_dast_target(db, &dast_target_id).await;
}
}
}
// Pentest sessions linked directly to this target (not via a DAST target).
if let Ok(mut cursor) = db.pentest_sessions().find(doc! { "repo_id": &id }).await {
use futures_util::StreamExt;
while let Some(Ok(session)) = cursor.next().await {
let session_id = session.id.map(|oid| oid.to_hex()).unwrap_or_default();
if !session_id.is_empty() {
let _ = db
.attack_chain_nodes()
.delete_many(doc! { "session_id": &session_id })
.await;
let _ = db
.pentest_messages()
.delete_many(doc! { "session_id": &session_id })
.await;
let _ = db
.dast_findings()
.delete_many(doc! { "session_id": &session_id })
.await;
}
}
}
let _ = db
.pentest_sessions()
.delete_many(doc! { "repo_id": &id })
.await;
Ok(Json(serde_json::json!({ "status": "deleted" })))
}
/// Delete a DAST target and everything downstream of it (pentest sessions +
/// their attack chains / messages / findings, DAST scan runs + findings).
async fn cascade_delete_dast_target(db: &crate::database::Database, target_id: &str) {
use futures_util::StreamExt;
if let Ok(mut cursor) = db
.pentest_sessions()
.find(doc! { "target_id": target_id })
.await
{
while let Some(Ok(session)) = cursor.next().await {
let session_id = session.id.map(|oid| oid.to_hex()).unwrap_or_default();
if !session_id.is_empty() {
let _ = db
.attack_chain_nodes()
.delete_many(doc! { "session_id": &session_id })
.await;
let _ = db
.pentest_messages()
.delete_many(doc! { "session_id": &session_id })
.await;
let _ = db
.dast_findings()
.delete_many(doc! { "session_id": &session_id })
.await;
}
}
}
let _ = db
.pentest_sessions()
.delete_many(doc! { "target_id": target_id })
.await;
let _ = db
.dast_findings()
.delete_many(doc! { "target_id": target_id })
.await;
let _ = db
.dast_scan_runs()
.delete_many(doc! { "target_id": target_id })
.await;
if let Ok(oid) = mongodb::bson::oid::ObjectId::parse_str(target_id) {
let _ = db.dast_targets().delete_one(doc! { "_id": oid }).await;
}
}
/// POST /api/v1/targets/{id}/artifacts — attach an artifact (by reference).
#[tracing::instrument(skip_all, fields(target_id = %id))]
pub async fn add_artifact(
Extension(agent): AgentExt,
tenant: TenantCtx,
Path(id): Path<String>,
Json(input): Json<ArtifactInput>,
) -> Result<Json<ApiResponse<OnboardedTarget>>, StatusCode> {
let oid = parse_oid(&id)?;
let db = tenant_db(&agent, &tenant).await?;
let artifact = to_bson(&input.build()).map_err(|_| StatusCode::BAD_REQUEST)?;
db.onboarded_targets()
.update_one(
doc! { "_id": oid },
doc! { "$push": { "artifacts": artifact }, "$set": { "updated_at": mongodb::bson::DateTime::now() } },
)
.await
.map_err(|_| StatusCode::INTERNAL_SERVER_ERROR)?;
get_target(Extension(agent), tenant, Path(id)).await
}
/// POST /api/v1/targets/{id}/artifacts/upload — attach an artifact by uploading
/// its file (PLC project, firmware image, source archive, mobile package). The
/// bytes are written to the artifact blob store and referenced by `stored_path`,
/// so ingest resolves them locally (no URL fetch).
///
/// Multipart fields: `file` (required), `kind` (required, snake_case
/// `ArtifactKind`), `plc_format` (optional, for PLC projects).
#[tracing::instrument(skip_all, fields(target_id = %id))]
pub async fn upload_artifact(
Extension(agent): AgentExt,
tenant: TenantCtx,
Path(id): Path<String>,
mut multipart: Multipart,
) -> Result<Json<ApiResponse<OnboardedTarget>>, StatusCode> {
let oid = parse_oid(&id)?;
let db = tenant_db(&agent, &tenant).await?;
if db
.onboarded_targets()
.find_one(doc! { "_id": oid })
.await
.map_err(|_| StatusCode::INTERNAL_SERVER_ERROR)?
.is_none()
{
return Err(StatusCode::NOT_FOUND);
}
let mut kind: Option<ArtifactKind> = None;
let mut plc_format: Option<PlcFormat> = None;
let mut filename = String::from("upload.bin");
let mut bytes: Option<axum::body::Bytes> = None;
while let Some(field) = multipart
.next_field()
.await
.map_err(|_| StatusCode::BAD_REQUEST)?
{
match field.name().unwrap_or("") {
"kind" => {
let v = field.text().await.map_err(|_| StatusCode::BAD_REQUEST)?;
kind = parse_enum(&v);
}
"plc_format" => {
let v = field.text().await.map_err(|_| StatusCode::BAD_REQUEST)?;
plc_format = parse_enum(&v);
}
"file" => {
if let Some(fname) = field.file_name() {
filename = fname.to_string();
}
bytes = Some(field.bytes().await.map_err(|_| StatusCode::BAD_REQUEST)?);
}
_ => {}
}
}
let (Some(kind), Some(bytes)) = (kind, bytes) else {
return Err(StatusCode::BAD_REQUEST);
};
// Store the uploaded bytes under the artifact blob store.
let safe_name: String = filename
.chars()
.map(|c| {
if c.is_ascii_alphanumeric() || matches!(c, '.' | '-' | '_') {
c
} else {
'_'
}
})
.collect();
let dir = std::path::Path::new(&agent.config.artifact_store_base_path)
.join("uploads")
.join(&id);
std::fs::create_dir_all(&dir).map_err(|_| StatusCode::INTERNAL_SERVER_ERROR)?;
let dest = dir.join(format!("{}_{safe_name}", uuid::Uuid::new_v4()));
std::fs::write(&dest, bytes.as_ref()).map_err(|_| StatusCode::INTERNAL_SERVER_ERROR)?;
// Build the artifact for this kind, referencing the stored file.
let mut artifact = match kind {
ArtifactKind::PlcProject => Artifact::plc_project(
filename.clone(),
plc_format.unwrap_or(PlcFormat::PlcopenXml),
),
ArtifactKind::FirmwareImage => Artifact::firmware_image(filename.clone()),
ArtifactKind::SourceArchive => Artifact::source_archive(filename.clone()),
ArtifactKind::MobilePackage => Artifact::mobile_package(filename.clone()),
// Non-file kinds (git repo, live URL, container ref, text) use the JSON
// add-artifact endpoint, not upload.
_ => return Err(StatusCode::BAD_REQUEST),
};
artifact.stored_path = Some(dest.to_string_lossy().to_string());
artifact.size_bytes = Some(bytes.len() as u64);
let artifact_bson = to_bson(&artifact).map_err(|_| StatusCode::INTERNAL_SERVER_ERROR)?;
db.onboarded_targets()
.update_one(
doc! { "_id": oid },
doc! { "$push": { "artifacts": artifact_bson }, "$set": { "updated_at": mongodb::bson::DateTime::now() } },
)
.await
.map_err(|_| StatusCode::INTERNAL_SERVER_ERROR)?;
get_target(Extension(agent), tenant, Path(id)).await
}
/// Deserialize a snake_case enum value from a plain string.
fn parse_enum<T: for<'de> Deserialize<'de>>(s: &str) -> Option<T> {
serde_json::from_value(serde_json::Value::String(s.to_string())).ok()
}
/// GET /api/v1/targets/{id}/applicable-scans — the scan-applicability matrix.
#[tracing::instrument(skip_all, fields(target_id = %id))]
pub async fn applicable_scans_for_target(
Extension(agent): AgentExt,
tenant: TenantCtx,
Path(id): Path<String>,
) -> Result<Json<ApiResponse<ApplicableScansResponse>>, StatusCode> {
let oid = parse_oid(&id)?;
let db = tenant_db(&agent, &tenant).await?;
let target = db
.onboarded_targets()
.find_one(doc! { "_id": oid })
.await
.map_err(|_| StatusCode::INTERNAL_SERVER_ERROR)?
.ok_or(StatusCode::NOT_FOUND)?;
let scans = applicable_scans(&target)
.into_iter()
.map(|o| ScanOptionDto {
scan: o.scan.to_string(),
default_on: o.default_on,
rationale: o.rationale,
required_artifact: o.required_artifact.map(|k| k.to_string()),
blocked_reason: o.blocked_reason,
})
.collect();
Ok(Json(ApiResponse {
data: ApplicableScansResponse {
scans,
pentest_supported: supports_pentest(target.target_type),
},
total: None,
page: None,
}))
}
/// POST /api/v1/targets/{id}/detect — classify the target from its artifacts.
///
/// This is the lightweight pass: it classifies from artifact kinds without
/// ingesting (cloning) sources, so it returns immediately. Deep detection (after
/// ingest, with tramiton firmware analysis) is a follow-up background step.
#[tracing::instrument(skip_all, fields(target_id = %id))]
pub async fn detect_target(
Extension(agent): AgentExt,
tenant: TenantCtx,
Path(id): Path<String>,
) -> Result<Json<ApiResponse<OnboardedTarget>>, StatusCode> {
let oid = parse_oid(&id)?;
let db = tenant_db(&agent, &tenant).await?;
let mut target = db
.onboarded_targets()
.find_one(doc! { "_id": oid })
.await
.map_err(|_| StatusCode::INTERNAL_SERVER_ERROR)?
.ok_or(StatusCode::NOT_FOUND)?;
// No ingested working paths here → kind-based classification only; the mock
// firmware detector is never invoked (no firmware working path present).
let empty = HashMap::new();
let detector = MockFirmwareDetector { detection: None };
let classification = classify_target(&target, &empty, &detector)
.await
.map_err(|_| StatusCode::INTERNAL_SERVER_ERROR)?;
let classification_bson =
to_bson(&classification).map_err(|_| StatusCode::INTERNAL_SERVER_ERROR)?;
db.onboarded_targets()
.update_one(
doc! { "_id": oid },
doc! { "$set": { "classification": classification_bson, "updated_at": mongodb::bson::DateTime::now() } },
)
.await
.map_err(|_| StatusCode::INTERNAL_SERVER_ERROR)?;
target.classification = Some(classification);
Ok(Json(ApiResponse {
data: target,
total: None,
page: None,
}))
}
/// POST /api/v1/targets/{id}/scan — trigger a scan for the target.
///
/// Dispatches to the unified pipeline when `UNIFIED_PIPELINE` is set (else the
/// legacy path). Runs in the background and returns immediately.
#[tracing::instrument(skip_all, fields(target_id = %id))]
pub async fn trigger_target_scan(
Extension(agent): AgentExt,
tenant: TenantCtx,
Path(id): Path<String>,
) -> Result<Json<serde_json::Value>, StatusCode> {
let oid = parse_oid(&id)?;
let db = tenant_db(&agent, &tenant).await?;
// 404 if the target doesn't exist for this tenant.
if db
.onboarded_targets()
.find_one(doc! { "_id": oid })
.await
.map_err(|_| StatusCode::INTERNAL_SERVER_ERROR)?
.is_none()
{
return Err(StatusCode::NOT_FOUND);
}
let agent_clone = (*agent).clone();
let tenant_id = tenant.0.tenant_id.clone();
tokio::spawn(async move {
// Always the unified target pipeline — this endpoint is about an
// onboarded target by construction, independent of the global
// `unified_pipeline` transition flag used by the legacy paths.
if let Err(e) = agent_clone
.run_target_scan(
&tenant_id,
&id,
compliance_core::models::ScanTrigger::Manual,
)
.await
{
tracing::error!("Manual target scan failed for {id}: {e}");
}
});
Ok(Json(serde_json::json!({ "status": "scan_triggered" })))
}
@@ -13,11 +13,10 @@ use compliance_core::models::dast::DastFinding;
use compliance_core::models::finding::Finding;
use compliance_core::models::pentest::*;
use compliance_core::models::sbom::SbomEntry;
use compliance_core::tenant_ctx::TenantCtx;
use crate::agent::ComplianceAgent;
use super::super::dto::{collect_cursor_async, tenant_db};
use super::super::dto::collect_cursor_async;
type AgentExt = Extension<Arc<ComplianceAgent>>;
@@ -36,15 +35,11 @@ pub struct ExportBody {
#[tracing::instrument(skip_all, fields(session_id = %id))]
pub async fn export_session_report(
Extension(agent): AgentExt,
tenant: TenantCtx,
Path(id): Path<String>,
Json(body): Json<ExportBody>,
) -> Result<axum::response::Response, (StatusCode, String)> {
let oid = mongodb::bson::oid::ObjectId::parse_str(&id)
.map_err(|_| (StatusCode::BAD_REQUEST, "Invalid session ID".to_string()))?;
let db = tenant_db(&agent, &tenant)
.await
.map_err(|s| (s, "failed to acquire tenant database".to_string()))?;
if body.password.len() < 8 {
return Err((
@@ -54,7 +49,8 @@ pub async fn export_session_report(
}
// Fetch session
let session = db
let session = agent
.db
.pentest_sessions()
.find_one(doc! { "_id": oid })
.await
@@ -68,7 +64,9 @@ pub async fn export_session_report(
// Resolve target name
let target = if let Ok(tid) = mongodb::bson::oid::ObjectId::parse_str(&session.target_id) {
db.dast_targets()
agent
.db
.dast_targets()
.find_one(doc! { "_id": tid })
.await
.ok()
@@ -86,7 +84,8 @@ pub async fn export_session_report(
.unwrap_or_default();
// Fetch attack chain nodes
let nodes: Vec<AttackChainNode> = match db
let nodes: Vec<AttackChainNode> = match agent
.db
.attack_chain_nodes()
.find(doc! { "session_id": &id })
.sort(doc! { "started_at": 1 })
@@ -97,7 +96,8 @@ pub async fn export_session_report(
};
// Fetch DAST findings for this session, then deduplicate
let raw_findings: Vec<DastFinding> = match db
let raw_findings: Vec<DastFinding> = match agent
.db
.dast_findings()
.find(doc! { "session_id": &id })
.sort(doc! { "severity": -1, "created_at": -1 })
@@ -122,7 +122,8 @@ pub async fn export_session_report(
.or_else(|| target.as_ref().and_then(|t| t.repo_id.clone()));
let (sast_findings, sbom_entries, code_context) = if let Some(ref rid) = repo_id {
let sast: Vec<Finding> = match db
let sast: Vec<Finding> = match agent
.db
.findings()
.find(doc! {
"repo_id": rid,
@@ -142,7 +143,8 @@ pub async fn export_session_report(
Err(_) => Vec::new(),
};
let sbom: Vec<SbomEntry> = match db
let sbom: Vec<SbomEntry> = match agent
.db
.sbom_entries()
.find(doc! {
"repo_id": rid,
@@ -162,7 +164,8 @@ pub async fn export_session_report(
};
// Build code context from graph nodes
let code_ctx: Vec<CodeContextHint> = match db
let code_ctx: Vec<CodeContextHint> = match agent
.db
.graph_nodes()
.find(doc! { "repo_id": rid, "is_entry_point": true })
.limit(50)
@@ -7,12 +7,11 @@ use mongodb::bson::doc;
use serde::Deserialize;
use compliance_core::models::pentest::*;
use compliance_core::tenant_ctx::TenantCtx;
use crate::agent::ComplianceAgent;
use crate::pentest::PentestOrchestrator;
use super::super::dto::{collect_cursor_async, tenant_db, ApiResponse, PaginationParams};
use super::super::dto::{collect_cursor_async, ApiResponse, PaginationParams};
type AgentExt = Extension<Arc<ComplianceAgent>>;
@@ -44,7 +43,6 @@ pub struct LookupRepoQuery {
#[tracing::instrument(skip_all)]
pub async fn create_session(
Extension(agent): AgentExt,
tenant: TenantCtx,
Json(req): Json<CreateSessionRequest>,
) -> Result<Json<ApiResponse<PentestSession>>, (StatusCode, String)> {
// Try to acquire a concurrency permit
@@ -59,10 +57,6 @@ pub async fn create_session(
)
})?;
let db = tenant_db(&agent, &tenant)
.await
.map_err(|s| (s, "failed to acquire tenant database".to_string()))?;
if let Some(ref config) = req.config {
// ── Wizard path ──────────────────────────────────────────────
if !config.disclaimer_accepted {
@@ -73,7 +67,8 @@ pub async fn create_session(
}
// Look up or auto-create DastTarget by app_url
let target = match db
let target = match agent
.db
.dast_targets()
.find_one(doc! { "base_url": &config.app_url })
.await
@@ -92,7 +87,7 @@ pub async fn create_session(
}
t.allow_destructive = config.allow_destructive;
t.excluded_paths = config.scope_exclusions.clone();
let res = db.dast_targets().insert_one(&t).await.map_err(|e| {
let res = agent.db.dast_targets().insert_one(&t).await.map_err(|e| {
(
StatusCode::INTERNAL_SERVER_ERROR,
format!("Failed to create target: {e}"),
@@ -113,18 +108,20 @@ pub async fn create_session(
session.config = Some(config.clone());
session.repo_id = target.repo_id.clone();
// Resolve repo_id (target id) from git_repo_url if provided
// Resolve repo_id from git_repo_url if provided
if let Some(ref git_url) = config.git_repo_url {
if let Ok(Some(target)) = db
.onboarded_targets()
.find_one(doc! { "artifacts.source_ref": git_url })
if let Ok(Some(repo)) = agent
.db
.repositories()
.find_one(doc! { "git_url": git_url })
.await
{
session.repo_id = target.id.map(|oid| oid.to_hex());
session.repo_id = repo.id.map(|oid| oid.to_hex());
}
}
let insert_result = db
let insert_result = agent
.db
.pentest_sessions()
.insert_one(&session)
.await
@@ -215,7 +212,8 @@ pub async fn create_session(
// Persist encrypted credentials to DB
if session_for_task.config.is_some() {
if let Some(sid) = session.id {
let _ = db
let _ = agent
.db
.pentest_sessions()
.update_one(
doc! { "_id": sid },
@@ -247,13 +245,12 @@ pub async fn create_session(
});
let llm = agent.llm.clone();
let db_for_orchestrator = db.clone();
let db = agent.db.clone();
let session_clone = session.clone();
let target_clone = target.clone();
let agent_ref = agent.clone();
tokio::spawn(async move {
let orchestrator =
PentestOrchestrator::new(llm, db_for_orchestrator, event_tx, Some(pause_rx));
let orchestrator = PentestOrchestrator::new(llm, db, event_tx, Some(pause_rx));
orchestrator
.run_session_guarded(&session_clone, &target_clone, &initial_message)
.await;
@@ -295,7 +292,8 @@ pub async fn create_session(
)
})?;
let target = db
let target = agent
.db
.dast_targets()
.find_one(doc! { "_id": oid })
.await
@@ -312,7 +310,8 @@ pub async fn create_session(
let mut session = PentestSession::new(target_id, strategy);
session.repo_id = target.repo_id.clone();
let insert_result = db
let insert_result = agent
.db
.pentest_sessions()
.insert_one(&session)
.await
@@ -339,13 +338,12 @@ pub async fn create_session(
});
let llm = agent.llm.clone();
let db_for_orchestrator = db.clone();
let db = agent.db.clone();
let session_clone = session.clone();
let target_clone = target.clone();
let agent_ref = agent.clone();
tokio::spawn(async move {
let orchestrator =
PentestOrchestrator::new(llm, db_for_orchestrator, event_tx, Some(pause_rx));
let orchestrator = PentestOrchestrator::new(llm, db, event_tx, Some(pause_rx));
orchestrator
.run_session_guarded(&session_clone, &target_clone, &initial_message)
.await;
@@ -375,25 +373,21 @@ fn parse_strategy(s: &str) -> PentestStrategy {
#[tracing::instrument(skip_all)]
pub async fn lookup_repo(
Extension(agent): AgentExt,
tenant: TenantCtx,
Query(params): Query<LookupRepoQuery>,
) -> Result<Json<ApiResponse<serde_json::Value>>, StatusCode> {
let db = tenant_db(&agent, &tenant).await?;
let repo = db
.onboarded_targets()
.find_one(doc! { "artifacts.source_ref": &params.url })
let repo = agent
.db
.repositories()
.find_one(doc! { "git_url": &params.url })
.await
.map_err(|_| StatusCode::INTERNAL_SERVER_ERROR)?;
let data = match repo {
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()),
})
}
Some(r) => serde_json::json!({
"name": r.name,
"default_branch": r.default_branch,
"last_scanned_commit": r.last_scanned_commit,
}),
None => serde_json::Value::Null,
};
@@ -408,11 +402,9 @@ pub async fn lookup_repo(
#[tracing::instrument(skip_all)]
pub async fn list_sessions(
Extension(agent): AgentExt,
tenant: TenantCtx,
Query(params): Query<PaginationParams>,
) -> Result<Json<ApiResponse<Vec<PentestSession>>>, StatusCode> {
let db = tenant_db(&agent, &tenant).await?;
let db = &db;
let db = &agent.db;
let skip = (params.page.saturating_sub(1)) * params.limit as u64;
let total = db
.pentest_sessions()
@@ -446,13 +438,12 @@ pub async fn list_sessions(
#[tracing::instrument(skip_all, fields(session_id = %id))]
pub async fn get_session(
Extension(agent): AgentExt,
tenant: TenantCtx,
Path(id): Path<String>,
) -> Result<Json<ApiResponse<PentestSession>>, StatusCode> {
let oid = mongodb::bson::oid::ObjectId::parse_str(&id).map_err(|_| StatusCode::BAD_REQUEST)?;
let db = tenant_db(&agent, &tenant).await?;
let mut session = db
let mut session = agent
.db
.pentest_sessions()
.find_one(doc! { "_id": oid })
.await
@@ -480,18 +471,15 @@ pub async fn get_session(
#[tracing::instrument(skip_all, fields(session_id = %id))]
pub async fn send_message(
Extension(agent): AgentExt,
tenant: TenantCtx,
Path(id): Path<String>,
Json(req): Json<SendMessageRequest>,
) -> Result<Json<ApiResponse<PentestMessage>>, (StatusCode, String)> {
let oid = mongodb::bson::oid::ObjectId::parse_str(&id)
.map_err(|_| (StatusCode::BAD_REQUEST, "Invalid session ID".to_string()))?;
let db = tenant_db(&agent, &tenant)
.await
.map_err(|s| (s, "failed to acquire tenant database".to_string()))?;
// Verify session exists and is running
let session = db
let session = agent
.db
.pentest_sessions()
.find_one(doc! { "_id": oid })
.await
@@ -518,7 +506,8 @@ pub async fn send_message(
)
})?;
let target = db
let target = agent
.db
.dast_targets()
.find_one(doc! { "_id": target_oid })
.await
@@ -538,13 +527,13 @@ pub async fn send_message(
// Store user message
let session_id = id.clone();
let user_msg = PentestMessage::user(session_id.clone(), req.message.clone());
let _ = db.pentest_messages().insert_one(&user_msg).await;
let _ = agent.db.pentest_messages().insert_one(&user_msg).await;
let response_msg = user_msg.clone();
// Spawn orchestrator to continue the session
let llm = agent.llm.clone();
let db_for_orchestrator = db.clone();
let db = agent.db.clone();
let message = req.message.clone();
// Use existing broadcast sender if available, otherwise create a new one
@@ -559,7 +548,7 @@ pub async fn send_message(
.unwrap_or_else(|| agent.register_session_stream(&session_id));
tokio::spawn(async move {
let orchestrator = PentestOrchestrator::new(llm, db_for_orchestrator, event_tx, None);
let orchestrator = PentestOrchestrator::new(llm, db, event_tx, None);
orchestrator
.run_session_guarded(&session, &target, &message)
.await;
@@ -576,16 +565,13 @@ pub async fn send_message(
#[tracing::instrument(skip_all, fields(session_id = %id))]
pub async fn stop_session(
Extension(agent): AgentExt,
tenant: TenantCtx,
Path(id): Path<String>,
) -> Result<Json<ApiResponse<PentestSession>>, (StatusCode, String)> {
let oid = mongodb::bson::oid::ObjectId::parse_str(&id)
.map_err(|_| (StatusCode::BAD_REQUEST, "Invalid session ID".to_string()))?;
let db = tenant_db(&agent, &tenant)
.await
.map_err(|s| (s, "failed to acquire tenant database".to_string()))?;
let session = db
let session = agent
.db
.pentest_sessions()
.find_one(doc! { "_id": oid })
.await
@@ -604,7 +590,9 @@ pub async fn stop_session(
));
}
db.pentest_sessions()
agent
.db
.pentest_sessions()
.update_one(
doc! { "_id": oid },
doc! { "$set": {
@@ -624,7 +612,8 @@ pub async fn stop_session(
// Clean up session resources
agent.cleanup_session(&id);
let updated = db
let updated = agent
.db
.pentest_sessions()
.find_one(doc! { "_id": oid })
.await
@@ -652,16 +641,13 @@ pub async fn stop_session(
#[tracing::instrument(skip_all, fields(session_id = %id))]
pub async fn pause_session(
Extension(agent): AgentExt,
tenant: TenantCtx,
Path(id): Path<String>,
) -> Result<Json<ApiResponse<serde_json::Value>>, (StatusCode, String)> {
let oid = mongodb::bson::oid::ObjectId::parse_str(&id)
.map_err(|_| (StatusCode::BAD_REQUEST, "Invalid session ID".to_string()))?;
let db = tenant_db(&agent, &tenant)
.await
.map_err(|s| (s, "failed to acquire tenant database".to_string()))?;
let session = db
let session = agent
.db
.pentest_sessions()
.find_one(doc! { "_id": oid })
.await
@@ -698,16 +684,13 @@ pub async fn pause_session(
#[tracing::instrument(skip_all, fields(session_id = %id))]
pub async fn resume_session(
Extension(agent): AgentExt,
tenant: TenantCtx,
Path(id): Path<String>,
) -> Result<Json<ApiResponse<serde_json::Value>>, (StatusCode, String)> {
let oid = mongodb::bson::oid::ObjectId::parse_str(&id)
.map_err(|_| (StatusCode::BAD_REQUEST, "Invalid session ID".to_string()))?;
let db = tenant_db(&agent, &tenant)
.await
.map_err(|s| (s, "failed to acquire tenant database".to_string()))?;
let session = db
let session = agent
.db
.pentest_sessions()
.find_one(doc! { "_id": oid })
.await
@@ -744,13 +727,12 @@ pub async fn resume_session(
#[tracing::instrument(skip_all, fields(session_id = %id))]
pub async fn get_attack_chain(
Extension(agent): AgentExt,
tenant: TenantCtx,
Path(id): Path<String>,
) -> Result<Json<ApiResponse<Vec<AttackChainNode>>>, StatusCode> {
let _oid = mongodb::bson::oid::ObjectId::parse_str(&id).map_err(|_| StatusCode::BAD_REQUEST)?;
let db = tenant_db(&agent, &tenant).await?;
let nodes = match db
let nodes = match agent
.db
.attack_chain_nodes()
.find(doc! { "session_id": &id })
.sort(doc! { "started_at": 1 })
@@ -775,21 +757,21 @@ pub async fn get_attack_chain(
#[tracing::instrument(skip_all, fields(session_id = %id))]
pub async fn get_messages(
Extension(agent): AgentExt,
tenant: TenantCtx,
Path(id): Path<String>,
Query(params): Query<PaginationParams>,
) -> Result<Json<ApiResponse<Vec<PentestMessage>>>, StatusCode> {
let _oid = mongodb::bson::oid::ObjectId::parse_str(&id).map_err(|_| StatusCode::BAD_REQUEST)?;
let db = tenant_db(&agent, &tenant).await?;
let skip = (params.page.saturating_sub(1)) * params.limit as u64;
let total = db
let total = agent
.db
.pentest_messages()
.count_documents(doc! { "session_id": &id })
.await
.unwrap_or(0);
let messages = match db
let messages = match agent
.db
.pentest_messages()
.find(doc! { "session_id": &id })
.sort(doc! { "created_at": 1 })
@@ -815,21 +797,21 @@ pub async fn get_messages(
#[tracing::instrument(skip_all, fields(session_id = %id))]
pub async fn get_session_findings(
Extension(agent): AgentExt,
tenant: TenantCtx,
Path(id): Path<String>,
Query(params): Query<PaginationParams>,
) -> Result<Json<ApiResponse<Vec<compliance_core::models::dast::DastFinding>>>, StatusCode> {
let _oid = mongodb::bson::oid::ObjectId::parse_str(&id).map_err(|_| StatusCode::BAD_REQUEST)?;
let db = tenant_db(&agent, &tenant).await?;
let skip = (params.page.saturating_sub(1)) * params.limit as u64;
let total = db
let total = agent
.db
.dast_findings()
.count_documents(doc! { "session_id": &id })
.await
.unwrap_or(0);
let findings = match db
let findings = match agent
.db
.dast_findings()
.find(doc! { "session_id": &id })
.sort(doc! { "created_at": -1 })
@@ -6,11 +6,10 @@ use axum::Json;
use mongodb::bson::doc;
use compliance_core::models::pentest::*;
use compliance_core::tenant_ctx::TenantCtx;
use crate::agent::ComplianceAgent;
use super::super::dto::{collect_cursor_async, tenant_db, ApiResponse};
use super::super::dto::{collect_cursor_async, ApiResponse};
type AgentExt = Extension<Arc<ComplianceAgent>>;
@@ -18,10 +17,8 @@ type AgentExt = Extension<Arc<ComplianceAgent>>;
#[tracing::instrument(skip_all)]
pub async fn pentest_stats(
Extension(agent): AgentExt,
tenant: TenantCtx,
) -> Result<Json<ApiResponse<PentestStats>>, StatusCode> {
let db = tenant_db(&agent, &tenant).await?;
let db = &db;
let db = &agent.db;
let running_sessions = db
.pentest_sessions()
@@ -11,11 +11,10 @@ use tokio_stream::wrappers::BroadcastStream;
use tokio_stream::StreamExt;
use compliance_core::models::pentest::*;
use compliance_core::tenant_ctx::TenantCtx;
use crate::agent::ComplianceAgent;
use super::super::dto::{collect_cursor_async, tenant_db};
use super::super::dto::collect_cursor_async;
type AgentExt = Extension<Arc<ComplianceAgent>>;
@@ -26,14 +25,13 @@ type AgentExt = Extension<Arc<ComplianceAgent>>;
#[tracing::instrument(skip_all, fields(session_id = %id))]
pub async fn session_stream(
Extension(agent): AgentExt,
tenant: TenantCtx,
Path(id): Path<String>,
) -> Result<Sse<impl futures_util::Stream<Item = Result<Event, Infallible>>>, StatusCode> {
let oid = mongodb::bson::oid::ObjectId::parse_str(&id).map_err(|_| StatusCode::BAD_REQUEST)?;
let db = tenant_db(&agent, &tenant).await?;
// Verify session exists
let _session = db
let _session = agent
.db
.pentest_sessions()
.find_one(doc! { "_id": oid })
.await
@@ -45,7 +43,8 @@ pub async fn session_stream(
let mut initial_events: Vec<Result<Event, Infallible>> = Vec::new();
// Fetch recent messages for this session
let messages: Vec<PentestMessage> = match db
let messages: Vec<PentestMessage> = match agent
.db
.pentest_messages()
.find(doc! { "session_id": &id })
.sort(doc! { "created_at": 1 })
@@ -57,7 +56,8 @@ pub async fn session_stream(
};
// Fetch recent attack chain nodes
let nodes: Vec<AttackChainNode> = match db
let nodes: Vec<AttackChainNode> = match agent
.db
.attack_chain_nodes()
.find(doc! { "session_id": &id })
.sort(doc! { "started_at": 1 })
@@ -94,7 +94,8 @@ pub async fn session_stream(
}
// Add current session status event
let session = db
let session = agent
.db
.pentest_sessions()
.find_one(doc! { "_id": oid })
.await
+328
View File
@@ -0,0 +1,328 @@
use axum::extract::{Extension, Path, Query};
use axum::http::StatusCode;
use axum::Json;
use mongodb::bson::doc;
use super::dto::*;
use compliance_core::models::*;
#[tracing::instrument(skip_all)]
pub async fn list_repositories(
Extension(agent): AgentExt,
Query(params): Query<PaginationParams>,
) -> ApiResult<Vec<TrackedRepository>> {
let db = &agent.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,
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;
agent
.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,
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 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 = agent
.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,
Path(id): Path<String>,
) -> Result<Json<serde_json::Value>, StatusCode> {
let agent_clone = (*agent).clone();
tokio::spawn(async move {
if let Err(e) = agent_clone.run_scan(&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,
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 repo = agent
.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,
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 = &agent.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;
}
}
+6 -17
View File
@@ -6,7 +6,6 @@ use mongodb::bson::doc;
use super::dto::*;
use compliance_core::models::SbomEntry;
use compliance_core::tenant_ctx::TenantCtx;
const COPYLEFT_LICENSES: &[&str] = &[
"GPL-2.0",
@@ -30,10 +29,8 @@ const COPYLEFT_LICENSES: &[&str] = &[
#[tracing::instrument(skip_all)]
pub async fn sbom_filters(
Extension(agent): AgentExt,
tenant: TenantCtx,
) -> Result<Json<serde_json::Value>, StatusCode> {
let db = tenant_db(&agent, &tenant).await?;
let db = &db;
let db = &agent.db;
let managers: Vec<String> = db
.sbom_entries()
@@ -64,11 +61,9 @@ pub async fn sbom_filters(
#[tracing::instrument(skip_all, fields(repo_id = ?filter.repo_id, package_manager = ?filter.package_manager))]
pub async fn list_sbom(
Extension(agent): AgentExt,
tenant: TenantCtx,
Query(filter): Query<SbomFilter>,
) -> ApiResult<Vec<SbomEntry>> {
let db = tenant_db(&agent, &tenant).await?;
let db = &db;
let db = &agent.db;
let mut query = doc! {};
if let Some(repo_id) = &filter.repo_id {
@@ -125,11 +120,9 @@ pub async fn list_sbom(
#[tracing::instrument(skip_all)]
pub async fn export_sbom(
Extension(agent): AgentExt,
tenant: TenantCtx,
Query(params): Query<SbomExportParams>,
) -> Result<impl IntoResponse, StatusCode> {
let db = tenant_db(&agent, &tenant).await?;
let db = &db;
let db = &agent.db;
let entries: Vec<SbomEntry> = match db
.sbom_entries()
.find(doc! { "repo_id": &params.repo_id })
@@ -243,11 +236,9 @@ pub async fn export_sbom(
#[tracing::instrument(skip_all)]
pub async fn license_summary(
Extension(agent): AgentExt,
tenant: TenantCtx,
Query(params): Query<SbomFilter>,
) -> ApiResult<Vec<LicenseSummary>> {
let db = tenant_db(&agent, &tenant).await?;
let db = &db;
let db = &agent.db;
let mut query = doc! {};
if let Some(repo_id) = &params.repo_id {
query.insert("repo_id", repo_id);
@@ -282,7 +273,7 @@ pub async fn license_summary(
}
})
.collect();
summaries.sort_by_key(|s| std::cmp::Reverse(s.count));
summaries.sort_by(|a, b| b.count.cmp(&a.count));
Ok(Json(ApiResponse {
data: summaries,
@@ -294,11 +285,9 @@ pub async fn license_summary(
#[tracing::instrument(skip_all)]
pub async fn sbom_diff(
Extension(agent): AgentExt,
tenant: TenantCtx,
Query(params): Query<SbomDiffParams>,
) -> ApiResult<SbomDiffResult> {
let db = tenant_db(&agent, &tenant).await?;
let db = &db;
let db = &agent.db;
let entries_a: Vec<SbomEntry> = match db
.sbom_entries()
+1 -4
View File
@@ -4,16 +4,13 @@ use mongodb::bson::doc;
use super::dto::*;
use compliance_core::models::ScanRun;
use compliance_core::tenant_ctx::TenantCtx;
#[tracing::instrument(skip_all)]
pub async fn list_scan_runs(
Extension(agent): AgentExt,
tenant: TenantCtx,
Query(params): Query<PaginationParams>,
) -> ApiResult<Vec<ScanRun>> {
let db = tenant_db(&agent, &tenant).await?;
let db = &db;
let db = &agent.db;
let skip = (params.page.saturating_sub(1)) * params.limit as u64;
let total = db.scan_runs().count_documents(doc! {}).await.unwrap_or(0);
+22 -40
View File
@@ -2,6 +2,7 @@ use axum::routing::{delete, get, patch, post};
use axum::Router;
use crate::api::handlers;
use crate::webhooks;
pub fn build_router() -> Router {
Router::new()
@@ -11,36 +12,19 @@ pub fn build_router() -> Router {
"/api/v1/settings/ssh-public-key",
get(handlers::get_ssh_public_key),
)
// Unified onboarding targets (#131).
.route("/api/v1/repositories", get(handlers::list_repositories))
.route("/api/v1/repositories", post(handlers::add_repository))
.route(
"/api/v1/targets",
get(handlers::onboarding::list_targets).post(handlers::onboarding::create_target),
"/api/v1/repositories/{id}/scan",
post(handlers::trigger_scan),
)
.route(
"/api/v1/targets/{id}",
get(handlers::onboarding::get_target)
.patch(handlers::onboarding::update_target)
.delete(handlers::onboarding::delete_target),
"/api/v1/repositories/{id}",
delete(handlers::delete_repository).patch(handlers::update_repository),
)
.route(
"/api/v1/targets/{id}/artifacts",
post(handlers::onboarding::add_artifact),
)
.route(
"/api/v1/targets/{id}/artifacts/upload",
post(handlers::onboarding::upload_artifact),
)
.route(
"/api/v1/targets/{id}/applicable-scans",
get(handlers::onboarding::applicable_scans_for_target),
)
.route(
"/api/v1/targets/{id}/detect",
post(handlers::onboarding::detect_target),
)
.route(
"/api/v1/targets/{id}/scan",
post(handlers::onboarding::trigger_target_scan),
"/api/v1/repositories/{id}/webhook-config",
get(handlers::get_webhook_config),
)
.route("/api/v1/findings", get(handlers::list_findings))
.route("/api/v1/findings/{id}", get(handlers::get_finding))
@@ -63,15 +47,6 @@ pub fn build_router() -> Router {
.route("/api/v1/sbom/diff", get(handlers::sbom_diff))
.route("/api/v1/issues", get(handlers::list_issues))
.route("/api/v1/scan-runs", get(handlers::list_scan_runs))
// MCP token management (per-tenant API tokens for the MCP server)
.route(
"/api/v1/mcp-tokens",
get(handlers::mcp_tokens::list_mcp_tokens).post(handlers::mcp_tokens::create_mcp_token),
)
.route(
"/api/v1/mcp-tokens/{id}",
delete(handlers::mcp_tokens::revoke_mcp_token),
)
// Graph API endpoints
.route("/api/v1/graph/{repo_id}", get(handlers::graph::get_graph))
.route(
@@ -200,10 +175,17 @@ pub fn build_router() -> Router {
"/api/v1/pentest/stats",
get(handlers::pentest::pentest_stats),
)
// Webhook routes live on the separate webhook server (port 3002,
// see crate::webhooks::server). The M7.2-C tenant-in-URL form is
// `/webhook/{tenant_id}/{platform}/{repo_id}` and the handlers
// expect a (tenant_id, repo_id) path tuple. Anything mounting
// them here on the API server would mismatch the handler
// signature, so the routes are not exported.
// Webhook endpoints (proxied through dashboard)
.route(
"/webhook/github/{repo_id}",
post(webhooks::github::handle_github_webhook),
)
.route(
"/webhook/gitlab/{repo_id}",
post(webhooks::gitlab::handle_gitlab_webhook),
)
.route(
"/webhook/gitea/{repo_id}",
post(webhooks::gitea::handle_gitea_webhook),
)
}
+2 -71
View File
@@ -1,82 +1,20 @@
use std::sync::Arc;
use axum::extract::{DefaultBodyLimit, Request};
use axum::http::HeaderValue;
use axum::middleware::Next;
use axum::response::Response;
use axum::routing::{delete, get};
use axum::{middleware, Extension, Router};
use axum::{middleware, Extension};
use tokio::sync::RwLock;
use tower_http::cors::CorsLayer;
use tower_http::set_header::SetResponseHeaderLayer;
use tower_http::trace::TraceLayer;
use compliance_core::auth::{require_jwt_auth, require_tenant_status, JwksState};
use compliance_core::{TenantContext, TenantStatus};
use crate::agent::ComplianceAgent;
use crate::api::handlers;
use crate::api::routes;
use crate::error::AgentError;
/// Synthetic tenant id used when Keycloak isn't configured (local dev,
/// `cargo run` against a bare Mongo). Lets the handler stack stay
/// uniformly tenant-scoped without the operator having to spin up KC
/// just to poke at the API. Override via `DEV_TENANT_ID`.
const DEFAULT_DEV_TENANT_ID: &str = "dev";
/// Inject a synthetic [`TenantContext`] for any request that lacks one.
/// Only mounted when Keycloak is NOT configured; with KC, the real
/// `require_jwt_auth` middleware owns this and we never reach here
/// without a context.
///
/// Public so the integration-test harness can mount it without
/// duplicating the synthetic-context shape.
pub async fn inject_dev_tenant(mut request: Request, next: Next) -> Response {
if request.extensions().get::<TenantContext>().is_none() {
let tenant_id =
std::env::var("DEV_TENANT_ID").unwrap_or_else(|_| DEFAULT_DEV_TENANT_ID.to_string());
let ctx = TenantContext {
tenant_slug: tenant_id.clone(),
tenant_id,
org_roles: vec![],
products: vec![],
plan: "dev".to_string(),
status: TenantStatus::Active,
user_id: "dev-user".to_string(),
user_name: None,
};
request.extensions_mut().insert(ctx);
}
next.run(request).await
}
pub async fn start_api_server(agent: ComplianceAgent, port: u16) -> Result<(), AgentError> {
// Admin sub-router. Routes are only mounted when ADMIN_API_TOKEN is
// configured — without it, the paths don't exist at all (404 rather
// than 401), so an operator who hasn't opted in can't fingerprint
// the surface area.
let admin_router: Router = if agent.config.admin_api_token.is_some() {
tracing::info!("Admin API enabled — /api/v1/admin/* mounted behind ADMIN_API_TOKEN bearer");
Router::new()
.route(
"/api/v1/admin/tenants",
get(handlers::admin::list_tenant_dbs),
)
.route(
"/api/v1/admin/tenants/{tenant_id}",
delete(handlers::admin::drop_tenant_db),
)
.layer(middleware::from_fn(handlers::admin::require_admin_token))
} else {
Router::new()
};
let mut app = routes::build_router()
.merge(admin_router)
// Allow large artifact uploads (PLC .projectarchive, firmware images,
// mobile packages) — axum's default request-body limit is only 2 MiB.
.layer(DefaultBodyLimit::max(512 * 1024 * 1024))
.layer(Extension(Arc::new(agent.clone())))
.layer(CorsLayer::permissive())
.layer(TraceLayer::new_for_http())
@@ -115,14 +53,7 @@ pub async fn start_api_server(agent: ComplianceAgent, port: u16) -> Result<(), A
.layer(middleware::from_fn(require_jwt_auth))
.layer(Extension(jwks_state));
} else {
let tenant_id =
std::env::var("DEV_TENANT_ID").unwrap_or_else(|_| DEFAULT_DEV_TENANT_ID.to_string());
tracing::warn!(
tenant_id = %tenant_id,
"Keycloak not configured — running unauthenticated against the dev tenant. \
DO NOT use in any environment with real customer data."
);
app = app.layer(middleware::from_fn(inject_dev_tenant));
tracing::warn!("Keycloak not configured - API endpoints are unprotected");
}
let addr = format!("0.0.0.0:{port}");
-217
View File
@@ -1,217 +0,0 @@
//! Firmware classification via tramiton.
//!
//! tramiton is the company's firmware build/repro engine; we do not re-implement
//! its detection. We depend on `tramiton-core` directly (same-company IP) and run
//! its provider analysis in-process behind a [`FirmwareDetector`] port, mapping
//! tramiton's `BuildPlan` onto a [`TargetType`]. A deterministic
//! [`MockFirmwareDetector`] backs the tests so CI unit tests need neither the
//! tramiton sources nor a real firmware tree.
use std::path::Path;
use compliance_core::error::CoreError;
use compliance_core::models::{DetectedFact, TargetType};
use compliance_core::traits::ClassifierVerdict;
/// A minimal firmware-detection summary, mapped from tramiton's `BuildPlan`.
/// Kept small and tramiton-independent so the classifier and the test mock don't
/// need to construct a full tramiton plan.
#[derive(Debug, Clone, Default)]
pub struct FirmwareDetection {
/// The detecting provider (e.g. `zephyr`, `cmake`, `source-archaeology`).
pub provider: String,
/// Detection confidence: `low` | `medium` | `high`.
pub confidence: String,
/// Build-system label (e.g. `Zephyr`, `ESP-IDF`, `CMake`).
pub build_system: String,
/// Framework, when known (`zephyr`, `esp-idf`, `bare-metal`, ...).
pub framework: Option<String>,
/// Target board / MCU / arch.
pub target: FirmwareTarget,
/// Unresolved gaps in the plan.
pub gaps: Vec<String>,
}
/// The detected firmware target (board / MCU / arch).
#[derive(Debug, Clone, Default)]
pub struct FirmwareTarget {
/// Board name.
pub board: Option<String>,
/// MCU part.
pub mcu: Option<String>,
/// Architecture.
pub arch: Option<String>,
}
/// A source of tramiton firmware detection.
#[allow(async_fn_in_trait)]
pub trait FirmwareDetector: Send + Sync {
/// Run detection over a path, returning a firmware detection if tramiton
/// could form a build plan.
async fn detect(&self, path: &Path) -> Result<Option<FirmwareDetection>, CoreError>;
}
/// Uses `tramiton-core` in-process. The analysis is blocking (filesystem walk),
/// so it runs on a blocking thread to avoid stalling the async runtime. A path
/// with no recognizable build system yields `Ok(None)`.
pub struct TramitonNative;
impl FirmwareDetector for TramitonNative {
async fn detect(&self, path: &Path) -> Result<Option<FirmwareDetection>, CoreError> {
let path = path.to_path_buf();
let plan = tokio::task::spawn_blocking(move || {
let repo = tramiton_core::Repo::new(&path);
tramiton_core::provider::analyze(&repo)
})
.await
.map_err(|e| CoreError::Other(format!("tramiton detect task join error: {e}")))?
.map_err(|e| CoreError::Other(format!("tramiton analyze error: {e}")))?;
Ok(plan.map(|bp| detection_from_build_plan(&bp)))
}
}
/// Map tramiton's `BuildPlan` onto our minimal detection summary.
fn detection_from_build_plan(bp: &tramiton_core::BuildPlan) -> FirmwareDetection {
FirmwareDetection {
provider: bp.provider.clone(),
confidence: bp.confidence.to_string(),
build_system: bp.build_system.label().to_string(),
framework: bp.framework.clone(),
target: FirmwareTarget {
board: bp.target.board.clone(),
mcu: bp.target.mcu.clone(),
arch: bp.target.arch.clone(),
},
gaps: bp.gaps.clone(),
}
}
/// Map a firmware detection to a target type. Framework/build-system signals
/// distinguish RTOS from bare-metal from Yocto.
pub fn detection_to_target_type(det: &FirmwareDetection) -> TargetType {
let framework = det.framework.as_deref().unwrap_or("").to_lowercase();
let build_system = det.build_system.to_lowercase();
let signal = format!("{framework} {build_system} {}", det.provider.to_lowercase());
const RTOS: [&str; 6] = ["zephyr", "esp-idf", "freertos", "nuttx", "riot", "chibios"];
if signal.contains("bitbake") || signal.contains("yocto") || signal.contains("openembedded") {
TargetType::EmbeddedLinuxYocto
} else if RTOS.iter().any(|k| signal.contains(k)) {
TargetType::FirmwareRtos
} else {
TargetType::FirmwareBareMetal
}
}
/// Map tramiton's confidence label to a `[0,1]` score.
fn confidence_score(label: &str) -> f32 {
match label.to_lowercase().as_str() {
"high" => 0.9,
"medium" => 0.6,
"low" => 0.3,
_ => 0.4,
}
}
/// Turn a firmware detection into a classifier verdict, carrying the MCU / board
/// / build-system as facts.
pub fn detection_to_verdict(det: &FirmwareDetection) -> ClassifierVerdict {
let target_type = detection_to_target_type(det);
let mut facts = vec![DetectedFact::new(
"build_system",
det.build_system.clone(),
"tramiton",
)];
if let Some(fw) = &det.framework {
facts.push(DetectedFact::new("framework", fw.clone(), "tramiton"));
}
if let Some(mcu) = &det.target.mcu {
facts.push(DetectedFact::new("mcu", mcu.clone(), "tramiton"));
}
if let Some(board) = &det.target.board {
facts.push(DetectedFact::new("board", board.clone(), "tramiton"));
}
if let Some(arch) = &det.target.arch {
facts.push(DetectedFact::new("arch", arch.clone(), "tramiton"));
}
ClassifierVerdict {
target_type,
confidence: confidence_score(&det.confidence),
facts,
rationale: format!(
"tramiton detected build system '{}'{}",
det.build_system,
det.framework
.as_ref()
.map(|f| format!(" (framework {f})"))
.unwrap_or_default()
),
}
}
/// A deterministic [`FirmwareDetector`] for tests — returns a preset detection.
pub struct MockFirmwareDetector {
/// The detection to return (or `None` for "no detection").
pub detection: Option<FirmwareDetection>,
}
impl FirmwareDetector for MockFirmwareDetector {
async fn detect(&self, _path: &Path) -> Result<Option<FirmwareDetection>, CoreError> {
Ok(self.detection.clone())
}
}
#[cfg(test)]
#[allow(clippy::expect_used, clippy::unwrap_used)]
mod tests {
use super::*;
fn detection(build_system: &str, framework: Option<&str>) -> FirmwareDetection {
FirmwareDetection {
provider: build_system.to_string(),
confidence: "high".to_string(),
build_system: build_system.to_string(),
framework: framework.map(|s| s.to_string()),
target: FirmwareTarget {
mcu: Some("stm32f429".to_string()),
..Default::default()
},
gaps: Vec::new(),
}
}
#[test]
fn zephyr_maps_to_rtos() {
assert_eq!(
detection_to_target_type(&detection("zephyr", Some("zephyr"))),
TargetType::FirmwareRtos
);
}
#[test]
fn bare_cmake_maps_to_bare_metal() {
assert_eq!(
detection_to_target_type(&detection("cmake", Some("bare-metal"))),
TargetType::FirmwareBareMetal
);
}
#[test]
fn bitbake_maps_to_yocto() {
assert_eq!(
detection_to_target_type(&detection("bitbake", None)),
TargetType::EmbeddedLinuxYocto
);
}
#[test]
fn verdict_carries_mcu_fact_and_confidence() {
let v = detection_to_verdict(&detection("esp-idf", Some("esp-idf")));
assert_eq!(v.target_type, TargetType::FirmwareRtos);
assert!((v.confidence - 0.9).abs() < f32::EPSILON);
assert!(v
.facts
.iter()
.any(|f| f.key == "mcu" && f.value == "stm32f429"));
}
}
-357
View File
@@ -1,357 +0,0 @@
//! Heuristic target-type classification from artifact kinds and source markers.
//!
//! Complements the tramiton firmware detector: this handles web / backend /
//! mobile / desktop / PLC by sniffing manifest files and file extensions in the
//! ingested code trees, plus strong priors from the artifact kinds themselves
//! (a PLC-project artifact is a PLC target; an `.ipa` is an iOS app).
use std::collections::HashSet;
use std::fs;
use std::path::Path;
use compliance_core::error::CoreError;
use compliance_core::models::{ArtifactKind, DetectedFact, TargetType};
use compliance_core::traits::{ClassificationInput, ClassifierVerdict, TargetClassifier};
/// Max directory depth scanned for marker files.
const SCAN_DEPTH: usize = 2;
/// Markers collected from a code tree.
#[derive(Default)]
struct Markers {
files: HashSet<String>,
dirs: HashSet<String>,
exts: HashSet<String>,
}
impl Markers {
fn has_file(&self, name: &str) -> bool {
self.files.contains(name)
}
fn has_ext(&self, ext: &str) -> bool {
self.exts.contains(ext)
}
fn any_dir_ends_with(&self, suffix: &str) -> bool {
self.dirs.iter().any(|d| d.ends_with(suffix))
}
}
/// Recursively collect marker file/dir/extension names up to [`SCAN_DEPTH`].
fn collect_markers(root: &Path) -> Markers {
let mut m = Markers::default();
scan_dir(root, 0, &mut m);
m
}
fn scan_dir(dir: &Path, depth: usize, m: &mut Markers) {
let Ok(entries) = fs::read_dir(dir) else {
return;
};
for entry in entries.flatten() {
let path = entry.path();
let name = entry.file_name().to_string_lossy().to_lowercase();
if path.is_dir() {
m.dirs.insert(name);
if depth < SCAN_DEPTH {
scan_dir(&path, depth + 1, m);
}
} else {
if let Some(ext) = path.extension() {
m.exts.insert(ext.to_string_lossy().to_lowercase());
}
m.files.insert(name);
}
}
}
/// Whether a `package.json` at `root` looks like a front-end app.
fn package_json_is_frontend(root: &Path) -> bool {
let Ok(content) = fs::read_to_string(root.join("package.json")) else {
return false;
};
let c = content.to_lowercase();
["react", "next", "vue", "@angular", "svelte", "vite"]
.iter()
.any(|f| c.contains(f))
}
/// The heuristic classifier: artifact-kind priors + source-tree markers.
pub struct HeuristicClassifier;
impl HeuristicClassifier {
/// Verdicts from the artifact kinds alone (no filesystem needed).
fn kind_priors(&self, input: &ClassificationInput<'_>) -> Vec<ClassifierVerdict> {
let mut out = Vec::new();
for a in input.artifacts {
let lower = a.source_ref.to_lowercase();
match a.kind {
ArtifactKind::PlcProject => out.push(verdict(
TargetType::PlcSps,
0.85,
"PLC project artifact",
vec![],
)),
ArtifactKind::MobilePackage => {
let (tt, why) = if lower.ends_with(".ipa") {
(TargetType::IosApp, "iOS package (.ipa)")
} else {
(TargetType::AndroidApp, "Android package (.apk/.aab)")
};
out.push(verdict(tt, 0.85, why, vec![]));
}
ArtifactKind::ContainerImage => out.push(verdict(
TargetType::BackendService,
0.4,
"container image",
vec![],
)),
ArtifactKind::FirmwareImage => out.push(verdict(
TargetType::FirmwareBareMetal,
0.35,
"firmware image (pending tramiton detection)",
vec![],
)),
ArtifactKind::LiveUrl if input.artifacts.len() == 1 => {
out.push(verdict(TargetType::WebApp, 0.3, "live URL only", vec![]))
}
_ => {}
}
}
out
}
/// Verdicts from scanning the ingested code trees for manifest markers.
fn source_verdicts(&self, input: &ClassificationInput<'_>) -> Vec<ClassifierVerdict> {
let mut out = Vec::new();
for a in input.artifacts {
if !matches!(a.kind, ArtifactKind::GitRepo | ArtifactKind::SourceArchive) {
continue;
}
let Some(path) = input.working_paths.get(&a.id) else {
continue;
};
let m = collect_markers(path);
// Mobile (checked first — strongest signal).
if m.has_file("androidmanifest.xml") || m.has_ext("apk") || m.has_ext("aab") {
out.push(verdict(
TargetType::AndroidApp,
0.8,
"Android manifest / gradle",
facts_lang("kotlin/java"),
));
}
if m.any_dir_ends_with(".xcodeproj")
|| m.has_file("info.plist")
|| m.has_file("podfile")
|| m.has_ext("ipa")
{
out.push(verdict(
TargetType::IosApp,
0.8,
"Xcode project / Info.plist",
facts_lang("swift/objc"),
));
}
// Desktop.
if m.has_ext("sln")
|| m.has_ext("csproj")
|| m.has_ext("vcxproj")
|| m.has_ext("desktop")
{
out.push(verdict(
TargetType::DesktopApp,
0.7,
"desktop project files",
facts_lang("dotnet/native"),
));
}
// PLC.
if m.has_ext("st") {
out.push(verdict(
TargetType::PlcSps,
0.8,
"Structured Text sources",
facts_lang("iec-61131-3"),
));
}
// Web vs backend from package.json.
if m.has_file("package.json") {
if package_json_is_frontend(path) {
out.push(verdict(
TargetType::WebApp,
0.65,
"package.json with a front-end framework",
facts_lang("javascript"),
));
} else {
out.push(verdict(
TargetType::BackendService,
0.55,
"package.json (no front-end framework)",
facts_lang("javascript"),
));
}
}
// Backend languages.
for (file, lang) in [
("cargo.toml", "rust"),
("go.mod", "go"),
("pom.xml", "java"),
("requirements.txt", "python"),
("pyproject.toml", "python"),
] {
if m.has_file(file) {
out.push(verdict(
TargetType::BackendService,
0.6,
"backend build manifest",
facts_lang(lang),
));
}
}
// Container-only.
if m.has_file("dockerfile") && out.is_empty() {
out.push(verdict(
TargetType::BackendService,
0.4,
"Dockerfile",
facts_lang("container"),
));
}
}
out
}
}
impl TargetClassifier for HeuristicClassifier {
fn name(&self) -> &str {
"heuristic"
}
async fn classify(
&self,
input: &ClassificationInput<'_>,
) -> Result<Vec<ClassifierVerdict>, CoreError> {
let mut out = self.kind_priors(input);
out.extend(self.source_verdicts(input));
Ok(out)
}
}
fn verdict(
target_type: TargetType,
confidence: f32,
rationale: &str,
facts: Vec<DetectedFact>,
) -> ClassifierVerdict {
ClassifierVerdict {
target_type,
confidence,
facts,
rationale: rationale.to_string(),
}
}
fn facts_lang(lang: &str) -> Vec<DetectedFact> {
vec![DetectedFact::new("language", lang, "heuristic")]
}
#[cfg(test)]
#[allow(clippy::expect_used, clippy::unwrap_used)]
mod tests {
use super::*;
use compliance_core::models::Artifact;
use std::collections::HashMap;
use std::path::PathBuf;
struct Scratch(PathBuf);
impl Scratch {
fn new() -> Self {
let p = std::env::temp_dir().join(format!("cs-classify-{}", uuid::Uuid::new_v4()));
fs::create_dir_all(&p).expect("mkdir");
Self(p)
}
}
impl Drop for Scratch {
fn drop(&mut self) {
let _ = fs::remove_dir_all(&self.0);
}
}
async fn classify_tree(setup: impl FnOnce(&Path)) -> Vec<ClassifierVerdict> {
let scratch = Scratch::new();
setup(&scratch.0);
let artifact = Artifact::git_repo("https://git/x", "main");
let mut wp = HashMap::new();
wp.insert(artifact.id.clone(), scratch.0.clone());
let artifacts = vec![artifact];
let input = ClassificationInput {
artifacts: &artifacts,
working_paths: &wp,
description: None,
};
HeuristicClassifier
.classify(&input)
.await
.expect("classify")
}
#[tokio::test]
async fn frontend_package_json_is_webapp() {
let v = classify_tree(|root| {
fs::write(
root.join("package.json"),
r#"{"dependencies":{"react":"18"}}"#,
)
.unwrap();
})
.await;
assert!(v.iter().any(|x| x.target_type == TargetType::WebApp));
}
#[tokio::test]
async fn cargo_toml_is_backend() {
let v = classify_tree(|root| {
fs::write(root.join("Cargo.toml"), "[package]\nname='x'").unwrap();
})
.await;
assert!(v
.iter()
.any(|x| x.target_type == TargetType::BackendService));
}
#[tokio::test]
async fn android_manifest_is_android() {
let v = classify_tree(|root| {
fs::write(root.join("AndroidManifest.xml"), "<manifest/>").unwrap();
})
.await;
assert!(v.iter().any(|x| x.target_type == TargetType::AndroidApp));
}
#[tokio::test]
async fn structured_text_is_plc() {
let v = classify_tree(|root| {
fs::write(root.join("main.st"), "PROGRAM main END_PROGRAM").unwrap();
})
.await;
assert!(v.iter().any(|x| x.target_type == TargetType::PlcSps));
}
#[tokio::test]
async fn ipa_artifact_prior_is_ios() {
let artifacts = vec![Artifact::mobile_package("app.ipa")];
let wp = HashMap::new();
let input = ClassificationInput {
artifacts: &artifacts,
working_paths: &wp,
description: None,
};
let v = HeuristicClassifier
.classify(&input)
.await
.expect("classify");
assert!(v.iter().any(|x| x.target_type == TargetType::IosApp));
}
}
-226
View File
@@ -1,226 +0,0 @@
//! Target classification.
//!
//! Runs the classifier registry over a target's artifacts and their ingested
//! working paths, then merges and ranks the verdicts into a [`Classification`].
//! The registry is the heuristic classifier (artifact kinds + source markers)
//! plus the tramiton firmware detector (behind a [`FirmwareDetector`] port).
mod firmware;
mod language;
pub use firmware::{
FirmwareDetection, FirmwareDetector, FirmwareTarget, MockFirmwareDetector, TramitonNative,
};
pub use language::HeuristicClassifier;
use std::collections::HashMap;
use std::path::PathBuf;
use compliance_core::error::CoreError;
use compliance_core::models::{
ArtifactKind, Classification, DetectedFact, OnboardedTarget, TargetType, TargetTypeCandidate,
};
use compliance_core::traits::{ClassificationInput, ClassifierVerdict, TargetClassifier};
use firmware::detection_to_verdict;
/// Classify a target from its artifacts and their ingested working paths, using
/// the heuristic classifier plus the tramiton firmware detector. Verdicts are
/// merged (max confidence per target type) and ranked into a [`Classification`].
pub async fn classify_target<D: FirmwareDetector>(
target: &OnboardedTarget,
working_paths: &HashMap<String, PathBuf>,
firmware_detector: &D,
) -> Result<Classification, CoreError> {
let input = ClassificationInput {
artifacts: &target.artifacts,
working_paths,
description: target.description.as_deref(),
};
let mut verdicts = Vec::new();
let mut detected_by = Vec::new();
let heuristic = HeuristicClassifier.classify(&input).await?;
if !heuristic.is_empty() {
detected_by.push("heuristic".to_string());
}
verdicts.extend(heuristic);
// Tramiton firmware detection over firmware / code working paths.
let mut tramiton_used = false;
for artifact in &target.artifacts {
if !matches!(
artifact.kind,
ArtifactKind::FirmwareImage | ArtifactKind::GitRepo | ArtifactKind::SourceArchive
) {
continue;
}
let Some(path) = working_paths.get(&artifact.id) else {
continue;
};
if let Some(detection) = firmware_detector.detect(path).await? {
verdicts.push(detection_to_verdict(&detection));
tramiton_used = true;
}
}
if tramiton_used {
detected_by.push("tramiton".to_string());
}
Ok(rank(verdicts, detected_by, target.target_type))
}
/// Merge verdicts by target type (keeping the max confidence and its rationale),
/// dedupe facts, rank by descending confidence, and assemble a [`Classification`].
/// Falls back to the declared type when no verdict is produced.
fn rank(
verdicts: Vec<ClassifierVerdict>,
detected_by: Vec<String>,
fallback: TargetType,
) -> Classification {
let mut best: HashMap<TargetType, (f32, String)> = HashMap::new();
let mut facts: Vec<DetectedFact> = Vec::new();
for verdict in verdicts {
for fact in verdict.facts {
if !facts
.iter()
.any(|e| e.key == fact.key && e.value == fact.value)
{
facts.push(fact);
}
}
let entry = best
.entry(verdict.target_type)
.or_insert((0.0, String::new()));
if verdict.confidence > entry.0 {
*entry = (verdict.confidence, verdict.rationale);
}
}
let mut candidates: Vec<TargetTypeCandidate> = best
.into_iter()
.map(
|(target_type, (confidence, rationale))| TargetTypeCandidate {
target_type,
confidence,
rationale,
},
)
.collect();
// Descending confidence; ties broken by type name for deterministic ordering.
candidates.sort_by(|a, b| {
b.confidence
.partial_cmp(&a.confidence)
.unwrap_or(std::cmp::Ordering::Equal)
.then_with(|| a.target_type.to_string().cmp(&b.target_type.to_string()))
});
let suggested = candidates
.first()
.map(|c| c.target_type)
.unwrap_or(fallback);
Classification {
suggested,
candidates,
facts,
detected_by,
detected_at: chrono::Utc::now(),
confirmed: false,
}
}
#[cfg(test)]
#[allow(clippy::expect_used, clippy::unwrap_used)]
mod tests {
use super::*;
use compliance_core::models::Artifact;
use std::fs;
use std::path::Path;
struct Scratch(PathBuf);
impl Scratch {
fn new() -> Self {
let p = std::env::temp_dir().join(format!("cs-classify-mod-{}", uuid::Uuid::new_v4()));
fs::create_dir_all(&p).expect("mkdir");
Self(p)
}
}
impl Drop for Scratch {
fn drop(&mut self) {
let _ = fs::remove_dir_all(&self.0);
}
}
fn no_firmware() -> MockFirmwareDetector {
MockFirmwareDetector { detection: None }
}
#[tokio::test]
async fn backend_repo_classifies_as_backend() {
let scratch = Scratch::new();
fs::write(scratch.0.join("go.mod"), "module x").unwrap();
let artifact = Artifact::git_repo("https://git/x", "main");
let mut wp = HashMap::new();
wp.insert(artifact.id.clone(), scratch.0.clone());
let mut target = OnboardedTarget::new("x".to_string(), TargetType::WebApp);
target.artifacts.push(artifact);
let c = classify_target(&target, &wp, &no_firmware())
.await
.expect("classify");
assert_eq!(c.suggested, TargetType::BackendService);
assert!(c.detected_by.contains(&"heuristic".to_string()));
assert!(!c.confirmed);
}
#[tokio::test]
async fn firmware_detector_verdict_ranks_top() {
let scratch = Scratch::new();
fs::write(scratch.0.join("fw.bin"), b"x").unwrap();
let artifact =
Artifact::firmware_image(scratch.0.join("fw.bin").to_string_lossy().to_string());
let mut wp = HashMap::new();
wp.insert(artifact.id.clone(), scratch.0.clone());
let mut target = OnboardedTarget::new("fw".to_string(), TargetType::FirmwareBareMetal);
target.artifacts.push(artifact);
let detector = MockFirmwareDetector {
detection: Some(FirmwareDetection {
provider: "zephyr".to_string(),
confidence: "high".to_string(),
build_system: "zephyr".to_string(),
framework: Some("zephyr".to_string()),
target: FirmwareTarget {
mcu: Some("nrf52840".to_string()),
..Default::default()
},
gaps: vec![],
}),
};
let c = classify_target(&target, &wp, &detector)
.await
.expect("classify");
// tramiton's high-confidence RTOS verdict beats the weak firmware prior.
assert_eq!(c.suggested, TargetType::FirmwareRtos);
assert!(c.detected_by.contains(&"tramiton".to_string()));
assert!(c.facts.iter().any(|f| f.key == "mcu"));
}
#[tokio::test]
async fn no_signal_falls_back_to_declared_type() {
let scratch = Scratch::new();
let _ = Path::new(&scratch.0);
let target = OnboardedTarget::new("empty".to_string(), TargetType::DesktopApp);
let wp = HashMap::new();
let c = classify_target(&target, &wp, &no_firmware())
.await
.expect("classify");
assert_eq!(c.suggested, TargetType::DesktopApp);
assert!(c.candidates.is_empty());
}
}
-4
View File
@@ -45,8 +45,6 @@ pub fn load_config() -> Result<AgentConfig, AgentError> {
.unwrap_or_else(|| "0 0 * * * *".to_string()),
git_clone_base_path: env_var_opt("GIT_CLONE_BASE_PATH")
.unwrap_or_else(|| "/tmp/compliance-scanner/repos".to_string()),
artifact_store_base_path: env_var_opt("ARTIFACT_STORE_BASE_PATH")
.unwrap_or_else(|| "/data/compliance-scanner/artifacts".to_string()),
ssh_key_path: env_var_opt("SSH_KEY_PATH")
.unwrap_or_else(|| "/data/compliance-scanner/ssh/id_ed25519".to_string()),
keycloak_url: env_var_opt("KEYCLOAK_URL"),
@@ -61,7 +59,5 @@ pub fn load_config() -> Result<AgentConfig, AgentError> {
.unwrap_or(true),
pentest_imap_username: env_var_opt("PENTEST_IMAP_USERNAME"),
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"),
})
}
+14 -272
View File
@@ -1,233 +1,11 @@
use std::sync::Arc;
use dashmap::DashMap;
use mongodb::bson::doc;
use mongodb::options::IndexOptions;
use mongodb::{Client, Collection, IndexModel};
use sha2::{Digest, Sha256};
use compliance_core::models::*;
use compliance_core::TenantContext;
use crate::error::AgentError;
/// Mongo enforces a 63-byte cap on database names (older clusters: 64
/// on Linux, 63 on Windows; we target the conservative limit).
const MAX_DB_NAME_LEN: usize = 63;
/// Hex length of the SHA-256 truncation used for the hash fallback
/// tenant DB name (16 bytes → 32 hex chars). 16 bytes gives ~2^64
/// birthday-collision resistance — at our 10s-100s tenant scale this
/// is effectively impossible to hit.
const HASH_HEX_LEN: usize = 32;
/// Largest `db_prefix` that still guarantees the hash-fallback name
/// fits in the 63-byte cap: `prefix + "_" + 32 hex chars`.
const MAX_PREFIX_LEN: usize = MAX_DB_NAME_LEN - 1 - HASH_HEX_LEN;
/// Per-tenant Mongo connection broker (M7.2 isolation model).
///
/// Holds one [`Client`] and hands out [`Database`] handles physically
/// scoped to `<db_prefix>_<tenant_id>`. The driver is the isolation
/// boundary — a handle for tenant A cannot see tenant B's documents
/// because it is connected to a different database, not because of an
/// application-level filter.
///
/// Index creation runs idempotently the first time each tenant is seen
/// in the process's lifetime. Mongo's `createIndex` is itself idempotent
/// by index name; the in-memory `ensured` set just skips the round-trip.
#[derive(Clone, Debug)]
pub struct DatabasePool {
client: Client,
db_prefix: String,
ensured: Arc<DashMap<String, ()>>,
}
impl DatabasePool {
/// Connect to the cluster and prepare to hand out tenant databases
/// named `<db_prefix>_<tenant_id>`.
///
/// Validates `db_prefix.len() <= MAX_PREFIX_LEN` so the
/// hash-fallback path is provably within Mongo's 63-byte db-name
/// cap. Refuses to construct a pool that could ever produce an
/// over-long name.
pub async fn connect(uri: &str, db_prefix: &str) -> Result<Self, AgentError> {
if db_prefix.len() > MAX_PREFIX_LEN {
return Err(AgentError::Other(format!(
"db_prefix '{db_prefix}' is {} chars; max is {MAX_PREFIX_LEN} so the \
hash-fallback tenant DB name fits Mongo's {MAX_DB_NAME_LEN}-byte cap",
db_prefix.len()
)));
}
let client = Client::with_uri_str(uri).await?;
client
.database("admin")
.run_command(doc! { "ping": 1 })
.await?;
tracing::info!(
"MongoDB cluster reachable; per-tenant pool ready (db prefix '{db_prefix}')"
);
Ok(Self {
client,
db_prefix: db_prefix.to_string(),
ensured: Arc::new(DashMap::new()),
})
}
/// Return a [`Database`] scoped to this tenant. Ensures indexes on
/// first call per tenant (per process). Cheap on the hot path —
/// subsequent calls skip the round-trip.
pub async fn for_tenant(&self, ctx: &TenantContext) -> Result<Database, AgentError> {
self.for_tenant_id(&ctx.tenant_id).await
}
/// Like [`Self::for_tenant`] but accepts a bare tenant_id.
/// For background paths (scheduler, webhooks, pipeline orchestrators)
/// that don't have a full [`TenantContext`] but know which tenant
/// they're operating on (typically resolved from a URL path, a job
/// argument, or the registry).
pub async fn for_tenant_id(&self, tenant_id: &str) -> Result<Database, AgentError> {
let db_name = self.tenant_db_name(tenant_id);
let db = Database::from_database(self.client.database(&db_name));
// `DashMap::insert` returns the previous value; `None` means we
// were the first writer for this tenant_id and own the
// index-ensure work.
if self.ensured.insert(tenant_id.to_string(), ()).is_none() {
if let Err(e) = db.ensure_indexes().await {
// Roll the marker back so the next request retries.
self.ensured.remove(tenant_id);
return Err(e);
}
tracing::debug!(
tenant_id = %tenant_id,
db_name = %db_name,
"Indexes ensured for tenant database"
);
}
Ok(db)
}
/// Compute the Mongo database name for a tenant. Public for tests
/// and tenant offboarding (`pool.client().database(name).drop()`).
///
/// Format: `<prefix>_<sanitized_tenant_id>` if it fits the 63-byte
/// cap, else `<prefix>_<sha256-16-byte-hex-of-tenant_id>`. The
/// `db_prefix` length invariant established at [`Self::connect`]
/// guarantees the hash-fallback name always fits — no runtime
/// assertion needed.
///
/// Collision resistance: the hash fallback is a 16-byte SHA-256
/// truncation, which gives ~2^64 birthday-collision resistance. At
/// our 10s100s tenant scale the probability of two tenant_ids
/// colliding is effectively zero. (8-byte truncation would have
/// been ~2^32 — too close for comfort on a regulated product.)
pub fn tenant_db_name(&self, tenant_id: &str) -> String {
let sanitized = sanitize_tenant_id(tenant_id);
let natural = format!("{}_{}", self.db_prefix, sanitized);
if natural.len() <= MAX_DB_NAME_LEN {
natural
} else {
let mut hasher = Sha256::new();
hasher.update(tenant_id.as_bytes());
let digest = hasher.finalize();
let suffix = hex::encode(&digest[..HASH_HEX_LEN / 2]);
format!("{}_{}", self.db_prefix, suffix)
}
}
/// Raw client handle. Reserved for cross-tenant admin flows that
/// must opt in explicitly (tenant listing, drop-on-offboard).
pub fn client(&self) -> &Client {
&self.client
}
/// Cross-tenant admin database used by features that intentionally
/// span tenants (today: MCP bearer tokens — each token row carries
/// a `tenant_id` and the MCP server reads them to route requests).
///
/// The name `<db_prefix>__admin` (double underscore) is reserved —
/// the sanitizer never produces it for a normal tenant DB because
/// the natural format is `<db_prefix>_<sanitized_tenant_id>` (one
/// underscore) and tenant_ids would have to start with `_admin` to
/// collide. New tenant provisioning should reject such ids.
pub fn admin_db(&self) -> mongodb::Database {
self.client.database(&self.admin_db_name())
}
/// Name of the admin database — public so tests / operators can
/// drop it via the raw client.
pub fn admin_db_name(&self) -> String {
format!("{}__admin", self.db_prefix)
}
/// List every Mongo database currently belonging to this pool,
/// identified by the `<db_prefix>_` prefix. The result is the raw
/// database names — opening one for offboarding/cleanup goes
/// through [`Self::client`].
///
/// Note: hashed-fallback names (very long tenant_ids) lose the
/// original tenant_id at the cluster level — we know a database
/// exists for *some* tenant but not which one. In practice
/// tenant_ids are UUIDs (36 chars) and never hit the fallback,
/// so this is a theoretical concern, not an operational one.
pub async fn list_tenant_db_names(&self) -> Result<Vec<String>, AgentError> {
let prefix = format!("{}_", self.db_prefix);
let names = self.client.list_database_names().await?;
Ok(names
.into_iter()
.filter(|n| n.starts_with(&prefix))
.collect())
}
/// Tenant ids for every provisioned tenant database, derived by stripping
/// the `<prefix>_` from the database names. Skips the admin database
/// (`<prefix>__admin`). Hash-fallback names (very long tenant_ids) are lost
/// at the cluster level and cannot be recovered here — in practice tenant
/// ids are UUIDs and never hit that path. Used by the migration CLI's
/// `--all` mode.
pub async fn list_tenant_ids(&self) -> Result<Vec<String>, AgentError> {
let prefix = format!("{}_", self.db_prefix);
Ok(self
.list_tenant_db_names()
.await?
.into_iter()
.filter_map(|n| n.strip_prefix(&prefix).map(str::to_string))
.filter(|id| !id.starts_with('_'))
.collect())
}
/// Drop the database for a specific tenant. Used by GDPR delete
/// and tenant offboarding. Idempotent — dropping a non-existent
/// database is a no-op at the driver level.
///
/// Also evicts the tenant from the in-memory `ensured` set so a
/// later re-provision triggers fresh `ensure_indexes`.
pub async fn drop_tenant(&self, tenant_id: &str) -> Result<(), AgentError> {
let db_name = self.tenant_db_name(tenant_id);
self.client.database(&db_name).drop().await?;
self.ensured.remove(tenant_id);
tracing::info!(
tenant_id = %tenant_id,
db_name = %db_name,
"Dropped tenant database"
);
Ok(())
}
}
/// Mongo database names disallow `/`, `\`, `.`, `"`, `$`, ` `, and NUL.
/// breakpilot-dev tenant_ids are UUIDs so this is belt-and-braces, but
/// it lets the pool tolerate any future tenant_id shape without surprise.
fn sanitize_tenant_id(tenant_id: &str) -> String {
tenant_id
.chars()
.map(|c| match c {
'/' | '\\' | '.' | '"' | '$' | ' ' | '\0' => '_',
c => c,
})
.collect()
}
#[derive(Clone, Debug)]
pub struct Database {
inner: mongodb::Database,
@@ -242,13 +20,17 @@ impl Database {
Ok(Self { inner: db })
}
/// Wrap an already-resolved Mongo database. Used by [`DatabasePool`]
/// to hand out tenant-scoped handles without a fresh client per tenant.
pub(crate) fn from_database(inner: mongodb::Database) -> Self {
Self { inner }
}
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(
@@ -435,40 +217,14 @@ impl Database {
)
.await?;
// onboarded_targets: multikey on artifact source ref (webhook + dedupe
// lookup). Non-unique — "one git URL per tenant" is enforced in the
// create handler, since a unique multikey index on an array field has
// null-collision caveats.
self.onboarded_targets()
.create_index(
IndexModel::builder()
.keys(doc! { "artifacts.source_ref": 1 })
.build(),
)
.await?;
// onboarded_targets: multikey on artifact kind
self.onboarded_targets()
.create_index(
IndexModel::builder()
.keys(doc! { "artifacts.kind": 1 })
.build(),
)
.await?;
// onboarded_targets: target_type filter
self.onboarded_targets()
.create_index(
IndexModel::builder()
.keys(doc! { "target_type": 1 })
.build(),
)
.await?;
tracing::info!("Database indexes ensured");
Ok(())
}
pub fn repositories(&self) -> Collection<TrackedRepository> {
self.inner.collection("repositories")
}
pub fn findings(&self) -> Collection<Finding> {
self.inner.collection("findings")
}
@@ -517,20 +273,6 @@ impl Database {
self.inner.collection("dast_targets")
}
/// The unified onboarding targets that replace `repositories` and
/// `dast_targets`. Ids are preserved from the legacy collections during
/// migration so downstream `repo_id` / `target_id` references keep resolving.
pub fn onboarded_targets(&self) -> Collection<OnboardedTarget> {
self.inner.collection("onboarded_targets")
}
/// A typed handle to an arbitrary collection by name. For bookkeeping
/// collections without a dedicated model (e.g. `schema_migrations`,
/// `onboarding_migration_log`).
pub fn collection_named<T: Send + Sync>(&self, name: &str) -> Collection<T> {
self.inner.collection(name)
}
pub fn dast_scan_runs(&self) -> Collection<DastScanRun> {
self.inner.collection("dast_scan_runs")
}
-154
View File
@@ -1,154 +0,0 @@
//! Content-addressed blob storage and archive extraction for ingest.
//!
//! Blobs are stored at `<base>/blobs/<sha[0:2]>/<sha>` and deduplicated by
//! digest; per-run working directories live under `<base>/work/`.
use std::fs::{self, File};
use std::io::{self, Read};
use std::path::{Path, PathBuf};
use sha2::{Digest, Sha256};
use crate::error::AgentError;
/// Read buffer size for streaming hashes/copies (64 KiB).
const BUF_LEN: usize = 64 * 1024;
/// Stream-hash a file with SHA-256, returning the lowercase-hex digest and the
/// byte length. Streams so large firmware images never load fully into memory.
pub fn hash_file(path: &Path) -> Result<(String, u64), AgentError> {
let mut file = File::open(path)?;
let mut hasher = Sha256::new();
let mut buf = [0u8; BUF_LEN];
let mut total: u64 = 0;
loop {
let n = file.read(&mut buf)?;
if n == 0 {
break;
}
hasher.update(&buf[..n]);
total += n as u64;
}
Ok((hex::encode(hasher.finalize()), total))
}
/// Copy `src` into the content-addressed blob store under `base`, returning the
/// stored path. Idempotent: an already-present blob is not rewritten.
pub fn store_file(base: &Path, src: &Path, sha: &str) -> Result<PathBuf, AgentError> {
if sha.len() < 2 {
return Err(AgentError::Other(format!("invalid content hash '{sha}'")));
}
let dir = base.join("blobs").join(&sha[0..2]);
fs::create_dir_all(&dir)?;
let dest = dir.join(sha);
if !dest.exists() {
fs::copy(src, &dest)?;
}
Ok(dest)
}
/// Extract a zip archive into `dest` (created if needed). `enclosed_name`
/// sanitizes each entry path, so this is safe against zip-slip traversal.
pub fn extract_zip(archive: &Path, dest: &Path) -> Result<(), AgentError> {
let file = File::open(archive)?;
let mut zip =
zip::ZipArchive::new(file).map_err(|e| AgentError::Other(format!("open zip: {e}")))?;
fs::create_dir_all(dest)?;
for i in 0..zip.len() {
let mut entry = zip
.by_index(i)
.map_err(|e| AgentError::Other(format!("read zip entry: {e}")))?;
// `enclosed_name` returns `None` for traversal-unsafe paths — skip them.
let Some(rel) = entry.enclosed_name() else {
continue;
};
let out = dest.join(rel);
if entry.is_dir() {
fs::create_dir_all(&out)?;
} else {
if let Some(parent) = out.parent() {
fs::create_dir_all(parent)?;
}
let mut outfile = File::create(&out)?;
io::copy(&mut entry, &mut outfile)?;
}
}
Ok(())
}
/// The working directory for one artifact of a target: `<base>/work/<target>/<artifact>`.
pub fn work_dir(base: &Path, target_id: &str, artifact_id: &str) -> PathBuf {
base.join("work").join(target_id).join(artifact_id)
}
#[cfg(test)]
#[allow(clippy::expect_used, clippy::unwrap_used)]
mod tests {
use super::*;
/// A unique scratch directory, removed on drop.
struct Scratch(PathBuf);
impl Scratch {
fn new() -> Self {
let p = std::env::temp_dir().join(format!("cs-ingest-{}", uuid::Uuid::new_v4()));
fs::create_dir_all(&p).expect("mkdir scratch");
Self(p)
}
fn path(&self) -> &Path {
&self.0
}
}
impl Drop for Scratch {
fn drop(&mut self) {
let _ = fs::remove_dir_all(&self.0);
}
}
#[test]
fn hash_is_stable_and_reports_size() {
let dir = Scratch::new();
let f = dir.path().join("a.bin");
fs::write(&f, b"hello world").expect("write");
let (sha, size) = hash_file(&f).expect("hash");
assert_eq!(size, 11);
// Known SHA-256 of "hello world".
assert_eq!(
sha,
"b94d27b9934d3e08a52e52d7da7dabfac484efe37a5380ee9088f7ace2efcde9"
);
}
#[test]
fn store_is_content_addressed_and_idempotent() {
let base = Scratch::new();
let src = base.path().join("src.bin");
fs::write(&src, b"payload").expect("write");
let (sha, _) = hash_file(&src).expect("hash");
let p1 = store_file(base.path(), &src, &sha).expect("store");
let p2 = store_file(base.path(), &src, &sha).expect("store again");
assert_eq!(p1, p2);
assert!(p1.ends_with(&sha));
assert!(p1.starts_with(base.path().join("blobs").join(&sha[0..2])));
assert_eq!(fs::read(&p1).expect("read"), b"payload");
}
#[test]
fn extract_zip_writes_entries() {
let base = Scratch::new();
let archive = base.path().join("a.zip");
{
let file = File::create(&archive).expect("create");
let mut w = zip::ZipWriter::new(file);
let opts: zip::write::SimpleFileOptions = Default::default();
w.start_file("dir/hello.txt", opts).expect("start");
io::Write::write_all(&mut w, b"hi").expect("write");
w.finish().expect("finish");
}
let dest = base.path().join("out");
extract_zip(&archive, &dest).expect("extract");
assert_eq!(
fs::read_to_string(dest.join("dir/hello.txt")).expect("read"),
"hi"
);
}
}
-416
View File
@@ -1,416 +0,0 @@
//! Artifact ingest.
//!
//! Normalizes each [`Artifact`] on an [`OnboardedTarget`] into a local working
//! path plus recorded metadata (content hash, size, discovered facts) that the
//! classifier and scanners consume. Every blob is SHA-256 hashed — that digest
//! is also the reconciliation key against sibling products (a firmware sha256
//! matches tramiton's `Artifact.sha256`).
mod blob;
use std::collections::HashMap;
use std::path::{Path, PathBuf};
use compliance_core::models::{Artifact, ArtifactKind, DetectedFact, OnboardedTarget};
use compliance_core::AgentConfig;
use crate::error::AgentError;
use crate::pipeline::git::{GitOps, RepoCredentials};
/// The paths and identifiers an ingest needs. Decoupled from the full
/// [`AgentConfig`] so ingest is testable without a complete config.
pub struct IngestContext<'a> {
/// Base directory for content-addressed blobs and working dirs.
pub artifact_store_base: &'a Path,
/// Base directory for git clones.
pub git_clone_base: &'a str,
/// Default SSH key path (used when an artifact provides none).
pub ssh_key_path: &'a str,
/// The id of the target these artifacts belong to (namespaces working dirs).
pub target_id: &'a str,
}
impl<'a> IngestContext<'a> {
/// Build an ingest context from the agent config for a given target.
pub fn from_config(config: &'a AgentConfig, target_id: &'a str) -> Self {
Self {
artifact_store_base: Path::new(&config.artifact_store_base_path),
git_clone_base: &config.git_clone_base_path,
ssh_key_path: &config.ssh_key_path,
target_id,
}
}
}
/// The result of ingesting one artifact.
pub struct IngestedArtifact {
/// The artifact this corresponds to ([`Artifact::id`]).
pub artifact_id: String,
/// The artifact kind.
pub kind: ArtifactKind,
/// Local working path (clone dir, extracted dir, or blob file). `None` for
/// artifacts with no on-disk form (live URL, plaintext, container ref).
pub working_path: Option<PathBuf>,
/// SHA-256 of the content (blobs) or git head SHA (git repos).
pub content_hash: Option<String>,
/// Stored blob size in bytes, when applicable.
pub size_bytes: Option<u64>,
/// Facts discovered during ingest.
pub facts: Vec<DetectedFact>,
}
/// All ingested artifacts for a target, keyed by artifact id.
pub struct IngestSet {
/// The ingested artifacts, keyed by [`Artifact::id`].
pub by_artifact: HashMap<String, IngestedArtifact>,
}
impl IngestSet {
/// The working paths of every ingested artifact that has one — the input the
/// classifier expects.
pub fn working_paths(&self) -> HashMap<String, PathBuf> {
self.by_artifact
.iter()
.filter_map(|(id, a)| a.working_path.clone().map(|p| (id.clone(), p)))
.collect()
}
/// The ingest result for a specific artifact.
pub fn get(&self, artifact_id: &str) -> Option<&IngestedArtifact> {
self.by_artifact.get(artifact_id)
}
}
/// Ingest every artifact on a target.
pub fn ingest_all(
target: &OnboardedTarget,
ctx: &IngestContext<'_>,
) -> Result<IngestSet, AgentError> {
let mut by_artifact = HashMap::new();
for artifact in &target.artifacts {
let ingested = ingest_artifact(artifact, ctx)?;
by_artifact.insert(artifact.id.clone(), ingested);
}
Ok(IngestSet { by_artifact })
}
/// Ingest a single artifact, dispatching on its kind.
pub fn ingest_artifact(
artifact: &Artifact,
ctx: &IngestContext<'_>,
) -> Result<IngestedArtifact, AgentError> {
match artifact.kind {
ArtifactKind::GitRepo => ingest_git(artifact, ctx),
ArtifactKind::SourceArchive | ArtifactKind::MobilePackage | ArtifactKind::PlcProject => {
ingest_blob(artifact, ctx, true)
}
ArtifactKind::FirmwareImage => ingest_blob(artifact, ctx, false),
ArtifactKind::ContainerImage => Ok(metadata_only(
artifact,
DetectedFact::new("container_ref", artifact.source_ref.as_str(), "ingest"),
)),
ArtifactKind::LiveUrl => Ok(metadata_only(
artifact,
DetectedFact::new("live_url", artifact.source_ref.as_str(), "ingest"),
)),
ArtifactKind::PlaintextDescription => Ok(metadata_only(
artifact,
DetectedFact::new(
"description_len",
artifact.source_ref.len().to_string(),
"ingest",
),
)),
}
}
/// Clone (or fetch) a git artifact, recording the head SHA as the content hash.
fn ingest_git(
artifact: &Artifact,
ctx: &IngestContext<'_>,
) -> Result<IngestedArtifact, AgentError> {
let creds = credentials_for(artifact, ctx.ssh_key_path);
let git_ops = GitOps::new(ctx.git_clone_base, creds);
let repo_path = git_ops.clone_or_fetch(&artifact.source_ref, &artifact.id)?;
let head = GitOps::get_head_sha(&repo_path).ok();
Ok(IngestedArtifact {
artifact_id: artifact.id.clone(),
kind: artifact.kind,
working_path: Some(repo_path),
content_hash: head,
size_bytes: None,
facts: Vec::new(),
})
}
/// Store a blob artifact content-addressed. When `extract` is set and the blob
/// is a zip container (source archive, APK/AAB/IPA), also unpack it into a
/// working directory; otherwise the working path is the stored blob.
fn ingest_blob(
artifact: &Artifact,
ctx: &IngestContext<'_>,
extract: bool,
) -> Result<IngestedArtifact, AgentError> {
let base = ctx.artifact_store_base;
let src = local_source(artifact)?;
let (sha, size) = blob::hash_file(&src)?;
let stored = blob::store_file(base, &src, &sha)?;
let mut facts = Vec::new();
let working_path = if extract {
let dest = blob::work_dir(base, ctx.target_id, &artifact.id);
match blob::extract_zip(&stored, &dest) {
Ok(()) => dest,
Err(e) => {
// Not a zip container — this is a single uploaded file (e.g. a
// `.st`/`.xml` PLC project or a `.tar.gz`). The content-addressed
// blob has no extension, so materialize it into a working dir
// under its original name; extension-based scanners (PLC) can then
// discover it and report a readable path.
facts.push(DetectedFact::new(
"archive_unextracted",
e.to_string(),
"ingest",
));
match materialize_single(&stored, &dest, &blob_file_name(artifact)) {
Ok(dir) => dir,
Err(copy_err) => {
facts.push(DetectedFact::new(
"materialize_failed",
copy_err.to_string(),
"ingest",
));
stored.clone()
}
}
}
}
} else {
stored.clone()
};
Ok(IngestedArtifact {
artifact_id: artifact.id.clone(),
kind: artifact.kind,
working_path: Some(working_path),
content_hash: Some(sha),
size_bytes: Some(size),
facts,
})
}
/// Copy a stored blob into `dest`/`name`, returning `dest`. Used when an
/// "extractable" artifact turns out to be a single file rather than an archive.
fn materialize_single(stored: &Path, dest: &Path, name: &str) -> Result<PathBuf, AgentError> {
std::fs::create_dir_all(dest)?;
std::fs::copy(stored, dest.join(name))?;
Ok(dest.to_path_buf())
}
/// A safe, single-segment file name for an artifact, preserving the original
/// extension so scanners can identify it. Derives from `source_ref` (the
/// uploaded/original file name); `file_name` strips any directory components,
/// so this is traversal-safe. Falls back to the artifact id.
fn blob_file_name(artifact: &Artifact) -> String {
Path::new(&artifact.source_ref)
.file_name()
.and_then(|n| n.to_str())
.map(str::to_string)
.filter(|s| !s.is_empty())
.unwrap_or_else(|| format!("artifact-{}", artifact.id))
}
/// An artifact with no on-disk form: record a single fact, no hash/path.
fn metadata_only(artifact: &Artifact, fact: DetectedFact) -> IngestedArtifact {
IngestedArtifact {
artifact_id: artifact.id.clone(),
kind: artifact.kind,
working_path: None,
content_hash: None,
size_bytes: None,
facts: vec![fact],
}
}
/// The local file backing a blob artifact: its `stored_path` if already
/// uploaded, else its `source_ref` interpreted as a filesystem path.
fn local_source(artifact: &Artifact) -> Result<PathBuf, AgentError> {
let path = artifact
.stored_path
.as_deref()
.unwrap_or(artifact.source_ref.as_str());
let path = PathBuf::from(path);
if !path.exists() {
return Err(AgentError::Other(format!(
"artifact {} source not found at {}",
artifact.id,
path.display()
)));
}
Ok(path)
}
/// Build git credentials from an artifact's auth plus a default SSH key path.
fn credentials_for(artifact: &Artifact, default_ssh_key_path: &str) -> RepoCredentials {
let auth = artifact.auth.as_ref();
RepoCredentials {
ssh_key_path: auth
.and_then(|a| a.ssh_key_path.clone())
.or_else(|| Some(default_ssh_key_path.to_string())),
auth_token: auth.and_then(|a| a.secret.clone()),
auth_username: auth.and_then(|a| a.username.clone()),
}
}
#[cfg(test)]
#[allow(clippy::expect_used, clippy::unwrap_used)]
mod tests {
use super::*;
use compliance_core::models::{ArtifactAuth, TargetType};
/// A unique scratch directory, removed on drop.
struct Scratch(PathBuf);
impl Scratch {
fn new() -> Self {
let p = std::env::temp_dir().join(format!("cs-ingest-mod-{}", uuid::Uuid::new_v4()));
std::fs::create_dir_all(&p).expect("mkdir scratch");
Self(p)
}
}
impl Drop for Scratch {
fn drop(&mut self) {
let _ = std::fs::remove_dir_all(&self.0);
}
}
fn ctx_for<'a>(store: &'a Path, target_id: &'a str) -> IngestContext<'a> {
IngestContext {
artifact_store_base: store,
git_clone_base: "/tmp/cs-ingest-test-repos",
ssh_key_path: "/tmp/cs-ingest-test-ssh",
target_id,
}
}
#[test]
fn firmware_blob_is_hashed_and_stored() {
let scratch = Scratch::new();
let store = scratch.0.join("store");
let fw = scratch.0.join("fw.bin");
std::fs::write(&fw, b"firmware-bytes").expect("write");
let ctx = ctx_for(&store, "t1");
let artifact = Artifact::firmware_image(fw.to_string_lossy().to_string());
let out = ingest_artifact(&artifact, &ctx).expect("ingest");
assert_eq!(out.kind, ArtifactKind::FirmwareImage);
assert_eq!(out.size_bytes, Some(14));
let sha = out.content_hash.expect("hash");
assert_eq!(sha.len(), 64);
// working path is the content-addressed blob
let wp = out.working_path.expect("working path");
assert!(wp.starts_with(store.join("blobs")));
}
#[test]
fn live_url_has_no_blob() {
let scratch = Scratch::new();
let store = scratch.0.join("store");
let ctx = ctx_for(&store, "t1");
let artifact = Artifact::live_url("https://example.com");
let out = ingest_artifact(&artifact, &ctx).expect("ingest");
assert!(out.working_path.is_none());
assert!(out.content_hash.is_none());
assert!(out.facts.iter().any(|f| f.key == "live_url"));
}
#[test]
fn ingest_all_collects_working_paths() {
let scratch = Scratch::new();
let store = scratch.0.join("store");
let fw = scratch.0.join("fw.bin");
std::fs::write(&fw, b"abc").expect("write");
let ctx = ctx_for(&store, "t1");
let mut target = OnboardedTarget::new("t".to_string(), TargetType::FirmwareBareMetal);
target
.artifacts
.push(Artifact::firmware_image(fw.to_string_lossy().to_string()));
target.artifacts.push(Artifact::live_url("https://x"));
let set = ingest_all(&target, &ctx).expect("ingest all");
assert_eq!(set.by_artifact.len(), 2);
// Only the firmware artifact yields a working path.
assert_eq!(set.working_paths().len(), 1);
}
#[test]
fn credentials_prefer_artifact_auth() {
let mut artifact = Artifact::git_repo("https://git/x", "main");
artifact.auth = Some(ArtifactAuth {
method: "token".to_string(),
username: Some("bob".to_string()),
secret: Some("pat".to_string()),
..Default::default()
});
let creds = credentials_for(&artifact, "/default/ssh/key");
assert_eq!(creds.auth_token.as_deref(), Some("pat"));
assert_eq!(creds.auth_username.as_deref(), Some("bob"));
}
#[test]
fn credentials_fall_back_to_default_ssh_key() {
let artifact = Artifact::git_repo("git@host:x.git", "main");
let creds = credentials_for(&artifact, "/default/ssh/key");
assert_eq!(creds.ssh_key_path.as_deref(), Some("/default/ssh/key"));
assert!(creds.auth_token.is_none());
}
/// A single uploaded PLC file (not an archive) must land in a working dir
/// under its original name so the PLC scanner can discover it by extension
/// and report a readable path — the demo's upload → scan path.
#[test]
fn single_uploaded_plc_file_is_materialized_and_scannable() {
use compliance_core::models::PlcFormat;
let scratch = Scratch::new();
let store = scratch.0.join("store");
// Simulate the upload handler: bytes written to an `uploads/` path,
// `source_ref` carrying the original (clean) file name.
let uploads = scratch.0.join("uploads");
std::fs::create_dir_all(&uploads).expect("mkdir uploads");
let uploaded = uploads.join("a1b2c3_pump_station.st");
std::fs::write(
&uploaded,
"PROGRAM P\nVAR\n ApiKey : STRING := 'sk-live-1234';\nEND_VAR\nEND_PROGRAM\n",
)
.expect("write st");
let mut artifact = Artifact::plc_project("pump_station.st", PlcFormat::StructuredText);
artifact.stored_path = Some(uploaded.to_string_lossy().to_string());
let ctx = ctx_for(&store, "t-plc");
let out = ingest_artifact(&artifact, &ctx).expect("ingest");
// Working path is a directory (not the extensionless blob) holding the
// file under its original name.
let wp = out.working_path.expect("working path");
assert!(wp.is_dir(), "expected a working dir, got {wp:?}");
assert!(wp.join("pump_station.st").is_file());
// The PLC scanner finds the hardcoded credential and reports a clean path.
let findings = crate::pipeline::plc::analyze_tree(&wp, "t-plc");
assert!(
!findings.is_empty(),
"scanner should flag the uploaded file"
);
assert!(findings
.iter()
.any(|f| f.rule_id.as_deref() == Some("plc-hardcoded-credential")));
assert_eq!(
findings[0].file_path.as_deref(),
Some("pump_station.st"),
"finding should reference the original file name"
);
}
}
-2
View File
@@ -2,11 +2,9 @@
pub mod agent;
pub mod api;
pub mod classify;
pub mod config;
pub mod database;
pub mod error;
pub mod ingest;
pub mod llm;
pub mod pentest;
pub mod pipeline;
+3 -6
View File
@@ -25,13 +25,10 @@ async fn main() -> Result<(), Box<dyn std::error::Error>> {
}
tracing::info!("Connecting to MongoDB...");
// Per-tenant pool only — the agent has no shared "default" database
// after M7.2-D. `mongodb_database` is now the db-name prefix used
// for tenant databases (`<prefix>_<tenant_id>`).
let db_pool =
database::DatabasePool::connect(&config.mongodb_uri, &config.mongodb_database).await?;
let db = database::Database::connect(&config.mongodb_uri, &config.mongodb_database).await?;
db.ensure_indexes().await?;
let agent = agent::ComplianceAgent::new(config.clone(), db_pool);
let agent = agent::ComplianceAgent::new(config.clone(), db.clone());
tracing::info!("Starting scheduler...");
let scheduler_agent = agent.clone();
-3
View File
@@ -328,7 +328,6 @@ mod tests {
scan_schedule: String::new(),
cve_monitor_schedule: String::new(),
git_clone_base_path: String::new(),
artifact_store_base_path: String::new(),
ssh_key_path: String::new(),
keycloak_url: None,
keycloak_realm: None,
@@ -340,8 +339,6 @@ mod tests {
pentest_imap_tls: true,
pentest_imap_username: None,
pentest_imap_password: None,
admin_api_token: None,
tenant_registry_url: None,
}
}
-283
View File
@@ -204,202 +204,6 @@ 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)]
@@ -424,90 +228,3 @@ 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));
}
}
@@ -1,152 +0,0 @@
//! Firmware SBOM via tramiton.
//!
//! Phase 2 (full, the default): drive a **reproducible build** with tramiton's
//! `NixBackend` — `analyze` → `seal_and_build` → a sealed lock whose libraries
//! are pinned and whose firmware artifact carries a content hash — then render
//! the SBOM from the lock plus deep binary SCA of pre-compiled inputs. This is
//! the complete bill of materials (toolchain + every fetched library + the
//! firmware image), the same one `tramiton sbom` produces.
//!
//! Phase 1 fallback (analysis-only): when no nix backend is available or the
//! build fails, fall back to the resolvable libraries + toolchain from the build
//! plan alone (no build). A scan therefore always yields *something*, and a nix
//! that can't run in the deployment never breaks a scan.
use std::path::Path;
use compliance_core::models::{SbomEntry, TargetType};
use tramiton_repro::ReproBackend;
use tramiton_sbom::ComponentKind;
/// Whether firmware SBOM applies to this target family.
pub fn is_firmware_target(target_type: TargetType) -> bool {
matches!(
target_type,
TargetType::FirmwareBareMetal | TargetType::FirmwareRtos | TargetType::EmbeddedLinuxYocto
)
}
/// Build SBOM entries for a firmware target from its source tree. Prefers a full
/// reproducible build (sealed lock); falls back to analysis-only. Returns an
/// empty vector when tramiton cannot even form a build plan.
pub async fn firmware_sbom_entries(path: &Path, repo_id: &str) -> Vec<SbomEntry> {
let p = path.to_path_buf();
let repo = repo_id.to_string();
// The whole analyze → seal → build → render sequence is blocking (it shells
// out to nix), so keep it off the async runtime. Bound it: a firmware build
// that hangs must not wedge the scan (the orphaned task is abandoned).
let handle = tokio::task::spawn_blocking(move || build_sbom_blocking(&p, &repo));
match tokio::time::timeout(std::time::Duration::from_secs(900), handle).await {
Ok(Ok(entries)) => entries,
Ok(Err(e)) => {
tracing::warn!(repo_id, error = %e, "Firmware SBOM: task join error");
Vec::new()
}
Err(_) => {
tracing::warn!(repo_id, "Firmware SBOM: build exceeded 15m; skipping");
Vec::new()
}
}
}
fn build_sbom_blocking(path: &Path, repo_id: &str) -> Vec<SbomEntry> {
let repo = tramiton_core::Repo::new(path);
let plan = match tramiton_core::provider::analyze(&repo) {
Ok(Some(bp)) => bp,
Ok(None) => return Vec::new(),
Err(e) => {
tracing::warn!(repo_id, error = %e, "Firmware SBOM: tramiton analyze failed");
return Vec::new();
}
};
// Phase 2: reproducible build → sealed lock → complete SBOM.
if let Some(backend) = tramiton_repro::NixBackend::detect() {
match tramiton_repro::seal_and_build(&backend, &plan, path) {
Ok(lock) => {
let mut sbom = tramiton_sbom::Sbom::from_lock(&lock, repo_id);
// Deep binary SCA of any pre-compiled inputs in the tree.
sbom.components.extend(tramiton_sbom::binary::scan(path));
let entries = sbom_to_entries(&sbom, repo_id);
tracing::info!(
repo_id,
backend = backend.name(),
count = entries.len(),
"Firmware SBOM: sealed reproducible build"
);
return entries;
}
Err(e) => {
tracing::warn!(repo_id, error = %e, "Firmware SBOM: reproducible build failed; falling back to analysis-only")
}
}
} else {
tracing::info!(
repo_id,
"Firmware SBOM: no nix backend available; analysis-only SBOM"
);
}
// Phase 1 fallback: analysis-only (toolchain + resolvable libraries).
analysis_entries(&plan, repo_id)
}
/// Map a rendered [`tramiton_sbom::Sbom`] (primary firmware + components) into
/// our [`SbomEntry`] rows. Source-file (`File`) components are dropped — they are
/// build inputs, not a dependency inventory.
fn sbom_to_entries(sbom: &tramiton_sbom::Sbom, repo_id: &str) -> Vec<SbomEntry> {
let mut entries = Vec::new();
if let Some(primary) = &sbom.primary {
entries.push(component_to_entry(primary, repo_id));
}
for c in &sbom.components {
if matches!(c.kind, ComponentKind::File) {
continue;
}
entries.push(component_to_entry(c, repo_id));
}
entries
}
fn component_to_entry(c: &tramiton_sbom::Component, repo_id: &str) -> SbomEntry {
let manager = match c.kind {
ComponentKind::Firmware => "firmware",
ComponentKind::Library => "library",
ComponentKind::Toolchain => "toolchain",
ComponentKind::File => "file",
};
let mut entry = SbomEntry::new(
repo_id.to_string(),
c.name.clone(),
c.version.clone().unwrap_or_default(),
manager.to_string(),
);
entry.purl = c.source.clone();
entry
}
/// Analysis-only components from the build plan: the cross-toolchain plus the
/// resolvable fetched libraries, without a build.
fn analysis_entries(bp: &tramiton_core::BuildPlan, repo_id: &str) -> Vec<SbomEntry> {
let mut entries = Vec::new();
if let Some(id) = bp.toolchain.id.clone() {
let version = bp.toolchain.version.clone().unwrap_or_default();
entries.push(SbomEntry::new(
repo_id.to_string(),
id,
version,
"toolchain".to_string(),
));
}
for lib in tramiton_repro::lock::libraries_from_inputs(&bp.inputs) {
let mut entry = SbomEntry::new(
repo_id.to_string(),
lib.name,
lib.revision,
"library".to_string(),
);
entry.purl = lib.source;
entries.push(entry);
}
entries
}
+2 -48
View File
@@ -80,10 +80,7 @@ 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> {
// 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));
let repo_path = self.base_path.join(repo_name);
if repo_path.exists() {
tracing::info!("fetching updates for existing repo");
@@ -138,7 +135,7 @@ impl GitOps {
/// Build credentials from agent config + per-repo overrides
pub fn make_repo_credentials(
config: &compliance_core::AgentConfig,
repo: &crate::pipeline::repo_view::RepoView,
repo: &compliance_core::models::TrackedRepository,
) -> RepoCredentials {
RepoCredentials {
ssh_key_path: Some(config.ssh_key_path.clone()),
@@ -256,46 +253,3 @@ 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");
}
}
@@ -1,95 +0,0 @@
//! Minimal EtherNet/IP (CIP) reachability probe.
//!
//! Sends an EtherNet/IP encapsulation **ListIdentity** command (0x0063) over TCP
//! 44818 and checks for a valid encapsulation reply — confirming a CIP device
//! without opening a session or writing anything.
use std::time::Duration;
use tokio::io::{AsyncReadExt, AsyncWriteExt};
use tokio::net::TcpStream;
use tokio::time::timeout;
/// Outcome of an EtherNet/IP handshake probe.
#[derive(Debug, Default, PartialEq, Eq)]
pub struct EnipProbe {
/// A TCP connection to the port was established.
pub reachable: bool,
/// The endpoint returned a valid EtherNet/IP encapsulation reply.
pub is_enip: bool,
}
/// Probe an EtherNet/IP endpoint with a ListIdentity request. Read-only.
pub async fn probe(host: &str, port: u16, budget: Duration) -> EnipProbe {
let mut out = EnipProbe::default();
let Ok(Ok(mut stream)) = timeout(budget, TcpStream::connect((host, port))).await else {
return out;
};
out.reachable = true;
// Encapsulation header (24 bytes): command(2) length(2) session(4) status(4)
// context(8) options(4). ListIdentity = command 0x0063, everything else zero.
let mut req = vec![0u8; 24];
req[0..2].copy_from_slice(&0x0063u16.to_le_bytes());
if timeout(budget, stream.write_all(&req))
.await
.ok()
.and_then(Result::ok)
.is_none()
{
return out;
}
let mut hdr = [0u8; 24];
if timeout(budget, stream.read_exact(&mut hdr))
.await
.ok()
.and_then(Result::ok)
.is_none()
{
return out;
}
let command = u16::from_le_bytes([hdr[0], hdr[1]]);
let status = u32::from_le_bytes([hdr[8], hdr[9], hdr[10], hdr[11]]);
// Echoed command + success status = a valid EtherNet/IP encapsulation reply.
if command == 0x0063 && status == 0 {
out.is_enip = true;
}
out
}
#[cfg(test)]
mod tests {
use super::*;
use tokio::net::TcpListener;
async fn mock_server() -> std::net::SocketAddr {
let listener = TcpListener::bind("127.0.0.1:0").await.expect("bind");
let addr = listener.local_addr().expect("addr");
tokio::spawn(async move {
let (mut sock, _) = listener.accept().await.expect("accept");
let mut req = [0u8; 24];
if sock.read_exact(&mut req).await.is_err() {
return;
}
// Reply: echo command 0x0063, status 0, no data.
let mut hdr = vec![0u8; 24];
hdr[0..2].copy_from_slice(&0x0063u16.to_le_bytes());
let _ = sock.write_all(&hdr).await;
});
addr
}
#[tokio::test]
async fn probe_detects_an_ethernetip_device() {
let addr = mock_server().await;
let p = probe(&addr.ip().to_string(), addr.port(), Duration::from_secs(2)).await;
assert!(p.reachable && p.is_enip);
}
#[tokio::test]
async fn probe_reports_unreachable_for_a_closed_port() {
let p = probe("127.0.0.1", 1, Duration::from_millis(500)).await;
assert!(!p.reachable && !p.is_enip);
}
}
-273
View File
@@ -1,273 +0,0 @@
//! Dynamic ICS (industrial control system) probing for PLC/SPS targets.
//!
//! Where the control-logic scanner is static (over ST / PLCopen XML), this probes
//! the *running* device over industrial protocols and reports exposed /
//! unauthenticated control interfaces. It is read-only: it never writes to a live
//! process. Modbus/TCP and OPC UA are implemented; EtherNet-IP is a follow-on.
pub mod ethernetip;
pub mod modbus;
pub mod opcua;
pub mod portscan;
use std::time::Duration;
use compliance_core::models::{Finding, ScanType, Severity};
use crate::pipeline::dedup;
/// Well-known deep-probe ports (each independent of any WebVisu HTTP port).
const MODBUS_PORT: u16 = 502;
const OPCUA_PORT: u16 = 4840;
const ENIP_PORT: u16 = 44818;
/// Probe a PLC/SPS device's industrial-protocol surface and return findings.
/// Read-only. Deep-probes Modbus/TCP, OPC UA and EtherNet/IP, plus a service
/// discovery scan of the remaining OT / insecure-management ports. `endpoint` is
/// the target's live-URL / host reference.
pub async fn probe_target(endpoint: &str, repo_id: &str, budget: Duration) -> Vec<Finding> {
let (host, modbus_port) = parse_endpoint(endpoint);
let mut findings = modbus_findings(&host, modbus_port, repo_id, budget).await;
findings.extend(opcua_findings(&host, OPCUA_PORT, repo_id, budget).await);
findings.extend(enip_findings(&host, ENIP_PORT, repo_id, budget).await);
findings.extend(portscan_findings(&host, repo_id, budget).await);
findings
}
/// Findings from probing the Modbus/TCP surface.
async fn modbus_findings(host: &str, port: u16, repo_id: &str, budget: Duration) -> Vec<Finding> {
let probe = modbus::probe(host, port, budget).await;
let mut findings = Vec::new();
if !probe.speaks_modbus {
// Not reachable, or the port does not speak Modbus — nothing to report.
return findings;
}
let target = format!("{host}:{port}");
// Reachable Modbus/TCP = unauthenticated, cleartext control access by design.
let fp = dedup::compute_fingerprint(&[repo_id, "ics-modbus-exposed", &target]);
let mut f = Finding::new(
repo_id.to_string(),
fp,
"ics-probe".to_string(),
ScanType::IcsProbe,
"Modbus/TCP control interface exposed without authentication".to_string(),
format!(
"The device at {target} answers Modbus/TCP requests. Modbus/TCP has no \
authentication or encryption in the protocol, so any host that can reach this \
port can read and write process variables (coils/registers) and disrupt the \
controlled process."
),
Severity::Critical,
);
f.rule_id = Some("ics-modbus-exposed".to_string());
f.cwe = Some("CWE-306".to_string());
f.remediation = Some(
"Restrict the Modbus/TCP port to a trusted control network (segmentation / \
firewall / VPN), never expose it to IT or the internet, and prefer an authenticated \
transport (e.g. Modbus/TLS) or a secure protocol gateway where available."
.to_string(),
);
findings.push(f);
if let Some(dev) = &probe.device {
let details = [
dev.vendor.as_deref(),
dev.product.as_deref(),
dev.revision.as_deref(),
]
.into_iter()
.flatten()
.collect::<Vec<_>>()
.join(" / ");
let fp = dedup::compute_fingerprint(&[repo_id, "ics-device-disclosure", &target]);
let mut f = Finding::new(
repo_id.to_string(),
fp,
"ics-probe".to_string(),
ScanType::IcsProbe,
"PLC device identity disclosed over Modbus".to_string(),
format!(
"The device at {target} discloses its identity via Modbus Read Device \
Identification: {details}. This aids fingerprinting and targeting of \
known-vulnerable firmware/runtime versions."
),
Severity::Low,
);
f.rule_id = Some("ics-device-disclosure".to_string());
f.cwe = Some("CWE-200".to_string());
f.remediation = Some(
"Limit network reach to the device; Modbus device identification cannot be \
disabled, so exposure is bounded by network segmentation."
.to_string(),
);
findings.push(f);
}
findings
}
/// Findings from probing the OPC UA surface (default port 4840). A reachability
/// probe only: it flags an exposed OPC UA server for review of its security
/// policy / authentication (deep SecurityPolicy analysis is a follow-on).
async fn opcua_findings(host: &str, port: u16, repo_id: &str, budget: Duration) -> Vec<Finding> {
let probe = opcua::probe(host, port, budget).await;
let mut findings = Vec::new();
if !probe.is_opcua {
return findings;
}
let target = format!("{host}:{port}");
let fp = dedup::compute_fingerprint(&[repo_id, "ics-opcua-exposed", &target]);
let mut f = Finding::new(
repo_id.to_string(),
fp,
"ics-probe".to_string(),
ScanType::IcsProbe,
"OPC UA server exposed on the network".to_string(),
format!(
"An OPC UA server answers at {target}. Verify it enforces message security \
(a SecurityPolicy other than None) and rejects anonymous sessions the common \
default of SecurityPolicy None + an Anonymous user token allows unauthenticated, \
unencrypted read/write of the server's address space."
),
Severity::Medium,
);
f.rule_id = Some("ics-opcua-exposed".to_string());
f.cwe = Some("CWE-319".to_string());
f.remediation = Some(
"Restrict OPC UA (4840) to a trusted network; require a signed & encrypted \
SecurityPolicy (Basic256Sha256 or better) with certificate / username \
authentication, and disable the Anonymous user token."
.to_string(),
);
findings.push(f);
findings
}
/// Findings from probing the EtherNet/IP (CIP) surface (default port 44818).
async fn enip_findings(host: &str, port: u16, repo_id: &str, budget: Duration) -> Vec<Finding> {
let probe = ethernetip::probe(host, port, budget).await;
if !probe.is_enip {
return Vec::new();
}
let target = format!("{host}:{port}");
let fp = dedup::compute_fingerprint(&[repo_id, "ics-ethernetip-exposed", &target]);
let mut f = Finding::new(
repo_id.to_string(),
fp,
"ics-probe".to_string(),
ScanType::IcsProbe,
"EtherNet/IP (CIP) interface exposed on the network".to_string(),
format!(
"The device at {target} answers EtherNet/IP (CIP) requests. EtherNet/IP has no \
authentication in the base protocol, so a host that can reach it can enumerate \
and interact with the device's control objects."
),
Severity::High,
);
f.rule_id = Some("ics-ethernetip-exposed".to_string());
f.cwe = Some("CWE-306".to_string());
f.remediation = Some(
"Restrict EtherNet/IP (44818/2222) to a trusted control network; use CIP Security \
(encryption + authentication) on devices that support it."
.to_string(),
);
vec![f]
}
/// Findings from the service-discovery port scan of the remaining OT /
/// insecure-management surface.
async fn portscan_findings(host: &str, repo_id: &str, budget: Duration) -> Vec<Finding> {
let open = portscan::scan(host, portscan::KNOWN_PORTS, budget).await;
open.into_iter()
.map(|kp| {
let target = format!("{host}:{}", kp.port);
let (title, severity, cwe, description) = match kp.kind {
portscan::PortKind::Ics => (
format!("ICS service exposed: {}", kp.service),
Severity::High,
"CWE-306",
format!(
"{target} exposes {} ({}). Industrial protocols are typically \
unauthenticated, so network reach implies control access.",
kp.service, kp.note
),
),
portscan::PortKind::InsecureMgmt => (
format!("Cleartext service exposed: {}", kp.service),
Severity::Medium,
"CWE-319",
format!(
"{target} exposes {} ({}), which transmits credentials and data in \
cleartext.",
kp.service, kp.note
),
),
};
let fp = dedup::compute_fingerprint(&[repo_id, "ics-service-exposed", &target]);
let mut f = Finding::new(
repo_id.to_string(),
fp,
"ics-probe".to_string(),
ScanType::IcsProbe,
title,
description,
severity,
);
f.rule_id = Some("ics-service-exposed".to_string());
f.cwe = Some(cwe.to_string());
f.remediation = Some(
"Restrict the service to a trusted network segment; disable it if unused; \
replace cleartext protocols (Telnet/FTP) with SSH/SFTP."
.to_string(),
);
f
})
.collect()
}
/// Extract `(host, port)` from a target reference. Modbus lives on its own port
/// (502 by default), independent of any HTTP/WebVisu URL, so unless the reference
/// explicitly carries `modbus://host:port` or a bare `host:port`, we probe 502.
fn parse_endpoint(endpoint: &str) -> (String, u16) {
let s = endpoint.trim();
let (scheme, rest) = match s.split_once("://") {
Some((sch, r)) => (Some(sch.to_ascii_lowercase()), r),
None => (None, s),
};
let hostport = rest.split(['/', '?']).next().unwrap_or(rest);
let (host, port) = match hostport.rsplit_once(':') {
Some((h, p)) => (h.to_string(), p.parse::<u16>().ok()),
None => (hostport.to_string(), None),
};
let port = match (scheme.as_deref(), port) {
// Explicit Modbus port, or a bare host:port the user chose.
(Some("modbus"), Some(p)) | (None, Some(p)) => p,
// An http(s)/WebVisu URL (or no port): Modbus is on its own port.
_ => MODBUS_PORT,
};
(host, port)
}
#[cfg(test)]
mod tests {
use super::parse_endpoint;
#[test]
fn endpoint_parsing_picks_the_modbus_port() {
assert_eq!(parse_endpoint("10.0.0.5"), ("10.0.0.5".into(), 502));
assert_eq!(parse_endpoint("10.0.0.5:1502"), ("10.0.0.5".into(), 1502));
assert_eq!(
parse_endpoint("modbus://plc.local:5020"),
("plc.local".into(), 5020)
);
// A WebVisu URL: the http port is ignored; Modbus is on 502.
assert_eq!(
parse_endpoint("http://plc.local:8080/webvisu"),
("plc.local".into(), 502)
);
assert_eq!(
parse_endpoint("https://plc.local/"),
("plc.local".into(), 502)
);
}
}
-205
View File
@@ -1,205 +0,0 @@
//! Minimal Modbus/TCP client for dynamic ICS probing.
//!
//! Modbus/TCP (port 502) has no authentication or encryption in the protocol, so
//! an endpoint that answers requests is, by design, open to any host that can
//! reach it. The probe only *reads* — a Read Holding Registers request and a Read
//! Device Identification request — and never writes to the live process.
use std::time::Duration;
use tokio::io::{AsyncReadExt, AsyncWriteExt};
use tokio::net::TcpStream;
use tokio::time::timeout;
/// Outcome of probing a Modbus/TCP endpoint.
#[derive(Debug, Default, PartialEq, Eq)]
pub struct ModbusProbe {
/// A TCP connection to the port was established.
pub reachable: bool,
/// The endpoint answered a Modbus request (a normal reply or a Modbus
/// exception) — i.e. it speaks Modbus, unauthenticated.
pub speaks_modbus: bool,
/// Device identity, if disclosed via Read Device Identification (FC 43 / 14).
pub device: Option<DeviceId>,
}
/// Vendor / product / revision from Read Device Identification.
#[derive(Debug, Default, PartialEq, Eq)]
pub struct DeviceId {
pub vendor: Option<String>,
pub product: Option<String>,
pub revision: Option<String>,
}
/// Probe a Modbus/TCP endpoint. Read-only: issues a Read Holding Registers and a
/// Read Device Identification request; never writes to the device.
pub async fn probe(host: &str, port: u16, budget: Duration) -> ModbusProbe {
let mut out = ModbusProbe::default();
let Ok(Ok(mut stream)) = timeout(budget, TcpStream::connect((host, port))).await else {
return out; // unreachable
};
out.reachable = true;
// Read Holding Registers (FC 0x03), unit 1, addr 0, qty 1 — a benign read.
let rhr = [0x03u8, 0x00, 0x00, 0x00, 0x01];
if let Some(resp) = txn(&mut stream, 1, &rhr, budget).await {
// A normal reply (0x03) or an exception (0x83) both prove it speaks Modbus.
if matches!(resp.first(), Some(0x03) | Some(0x83)) {
out.speaks_modbus = true;
}
}
// Read Device Identification (FC 0x2B / MEI 0x0E), basic (0x01), object 0.
let rdi = [0x2Bu8, 0x0E, 0x01, 0x00];
if let Some(resp) = txn(&mut stream, 1, &rdi, budget).await {
if resp.first() == Some(&0x2B) {
out.speaks_modbus = true;
out.device = parse_device_id(&resp);
}
}
out
}
/// Send one Modbus PDU and return the response PDU (function code + data), or
/// `None` on timeout / malformed reply.
async fn txn(stream: &mut TcpStream, unit: u8, pdu: &[u8], budget: Duration) -> Option<Vec<u8>> {
// MBAP header: transaction id (2) + protocol id (2) = 0 + length (2) + unit (1),
// then the PDU. `length` counts the unit byte plus the PDU.
let len = (pdu.len() + 1) as u16;
let mut frame = Vec::with_capacity(7 + pdu.len());
frame.extend_from_slice(&[0x00, 0x01]); // transaction id
frame.extend_from_slice(&[0x00, 0x00]); // protocol id
frame.extend_from_slice(&len.to_be_bytes());
frame.push(unit);
frame.extend_from_slice(pdu);
timeout(budget, stream.write_all(&frame)).await.ok()?.ok()?;
let mut hdr = [0u8; 7];
timeout(budget, stream.read_exact(&mut hdr))
.await
.ok()?
.ok()?;
// Reject non-Modbus replies (protocol id must be 0).
if hdr[2] != 0 || hdr[3] != 0 {
return None;
}
let plen = u16::from_be_bytes([hdr[4], hdr[5]]) as usize;
if !(2..=260).contains(&plen) {
return None;
}
let mut body = vec![0u8; plen - 1]; // minus the unit id already in hdr[6]
timeout(budget, stream.read_exact(&mut body))
.await
.ok()?
.ok()?;
Some(body)
}
/// Parse vendor / product / revision from a Read Device Identification PDU:
/// `[0x2B, 0x0E, readDevIdCode, conformity, moreFollows, nextObjId, numObjects,
/// (objId, len, bytes…)…]`.
fn parse_device_id(pdu: &[u8]) -> Option<DeviceId> {
if pdu.len() < 7 {
return None;
}
let num = pdu[6] as usize;
let mut i = 7;
let mut dev = DeviceId::default();
for _ in 0..num {
if i + 2 > pdu.len() {
break;
}
let id = pdu[i];
let l = pdu[i + 1] as usize;
i += 2;
if i + l > pdu.len() {
break;
}
let val = String::from_utf8_lossy(&pdu[i..i + l]).trim().to_string();
i += l;
match id {
0x00 => dev.vendor = Some(val),
0x01 => dev.product = Some(val),
0x02 => dev.revision = Some(val),
_ => {}
}
}
if dev == DeviceId::default() {
None
} else {
Some(dev)
}
}
#[cfg(test)]
mod tests {
use super::*;
use tokio::net::TcpListener;
/// A one-shot mock Modbus/TCP server that answers a Read Holding Registers
/// request and a Read Device Identification request on one connection.
async fn mock_server(with_device: bool) -> std::net::SocketAddr {
let listener = TcpListener::bind("127.0.0.1:0").await.expect("bind");
let addr = listener.local_addr().expect("addr");
tokio::spawn(async move {
let (mut sock, _) = listener.accept().await.expect("accept");
loop {
let mut hdr = [0u8; 7];
if sock.read_exact(&mut hdr).await.is_err() {
break;
}
let plen = u16::from_be_bytes([hdr[4], hdr[5]]) as usize;
let mut pdu = vec![0u8; plen - 1];
if sock.read_exact(&mut pdu).await.is_err() {
break;
}
let reply_pdu: Vec<u8> = match pdu.first() {
Some(0x03) => vec![0x03, 0x02, 0x00, 0x00], // 1 register = 0
Some(0x2B) if with_device => vec![
0x2B, 0x0E, 0x01, 0x81, 0x00, 0x00, 0x02, // 2 objects
0x00, 0x04, b'A', b'C', b'M', b'E', // vendor
0x01, 0x03, b'P', b'L', b'C', // product
],
_ => vec![pdu[0] | 0x80, 0x01], // exception
};
let len = (reply_pdu.len() + 1) as u16;
let mut frame = vec![hdr[0], hdr[1], 0x00, 0x00];
frame.extend_from_slice(&len.to_be_bytes());
frame.push(hdr[6]);
frame.extend_from_slice(&reply_pdu);
if sock.write_all(&frame).await.is_err() {
break;
}
}
});
addr
}
#[tokio::test]
async fn probe_detects_a_modbus_endpoint_and_reads_device_id() {
let addr = mock_server(true).await;
let p = probe(&addr.ip().to_string(), addr.port(), Duration::from_secs(2)).await;
assert!(p.reachable && p.speaks_modbus);
let dev = p.device.expect("device id");
assert_eq!(dev.vendor.as_deref(), Some("ACME"));
assert_eq!(dev.product.as_deref(), Some("PLC"));
}
#[tokio::test]
async fn probe_reports_unreachable_for_a_closed_port() {
// 127.0.0.1:1 is (almost certainly) closed.
let p = probe("127.0.0.1", 1, Duration::from_millis(500)).await;
assert!(!p.reachable && !p.speaks_modbus);
}
#[test]
fn parses_device_identification_objects() {
let pdu = [
0x2B, 0x0E, 0x01, 0x81, 0x00, 0x00, 0x01, // 1 object
0x02, 0x05, b'v', b'1', b'.', b'2', b'3', // revision
];
let dev = parse_device_id(&pdu).expect("device");
assert_eq!(dev.revision.as_deref(), Some("v1.23"));
assert!(dev.vendor.is_none());
}
}
-131
View File
@@ -1,131 +0,0 @@
//! Minimal OPC UA reachability probe.
//!
//! Speaks just the OPC UA Connection Protocol (UACP) handshake — a `HEL` (Hello)
//! message, expecting an `ACK` (or `ERR`) reply — to confirm an OPC UA server is
//! listening (default port 4840). It does **not** open a secure channel or make
//! service calls; deep analysis of the server's SecurityPolicy / user-token
//! policies (the common `None` + `Anonymous` misconfiguration) is a follow-on best
//! done with a full OPC UA stack.
use std::time::Duration;
use tokio::io::{AsyncReadExt, AsyncWriteExt};
use tokio::net::TcpStream;
use tokio::time::timeout;
/// Outcome of an OPC UA handshake probe.
#[derive(Debug, Default, PartialEq, Eq)]
pub struct OpcUaProbe {
/// A TCP connection to the port was established.
pub reachable: bool,
/// The endpoint replied to the UACP Hello (`ACK`) or rejected it (`ERR`) —
/// either way it speaks OPC UA.
pub is_opcua: bool,
}
/// Probe an OPC UA endpoint with a UACP Hello. Read-only handshake only.
pub async fn probe(host: &str, port: u16, budget: Duration) -> OpcUaProbe {
let mut out = OpcUaProbe::default();
let Ok(Ok(mut stream)) = timeout(budget, TcpStream::connect((host, port))).await else {
return out;
};
out.reachable = true;
let hello = hello_message(&format!("opc.tcp://{host}:{port}"));
if timeout(budget, stream.write_all(&hello))
.await
.ok()
.and_then(Result::ok)
.is_none()
{
return out;
}
// Read the 3-byte message type of the reply: ACK (accepted) or ERR (rejected
// our hello) both prove the peer speaks the OPC UA connection protocol.
let mut mt = [0u8; 3];
if timeout(budget, stream.read_exact(&mut mt))
.await
.ok()
.and_then(Result::ok)
.is_none()
{
return out;
}
if &mt == b"ACK" || &mt == b"ERR" {
out.is_opcua = true;
}
out
}
/// Build a UACP `HEL` (Hello) message advertising our buffer sizes + endpoint URL.
fn hello_message(endpoint_url: &str) -> Vec<u8> {
let url = endpoint_url.as_bytes();
let mut m = Vec::with_capacity(32 + url.len());
m.extend_from_slice(b"HELF");
m.extend_from_slice(&0u32.to_le_bytes()); // message size — patched below
m.extend_from_slice(&0u32.to_le_bytes()); // ProtocolVersion
m.extend_from_slice(&65536u32.to_le_bytes()); // ReceiveBufferSize
m.extend_from_slice(&65536u32.to_le_bytes()); // SendBufferSize
m.extend_from_slice(&0u32.to_le_bytes()); // MaxMessageSize (0 = no limit)
m.extend_from_slice(&0u32.to_le_bytes()); // MaxChunkCount
m.extend_from_slice(&(url.len() as i32).to_le_bytes()); // EndpointUrl length
m.extend_from_slice(url);
let size = m.len() as u32;
m[4..8].copy_from_slice(&size.to_le_bytes());
m
}
#[cfg(test)]
mod tests {
use super::*;
use tokio::net::TcpListener;
/// A mock OPC UA server that reads the Hello and replies with an `ACK` frame.
async fn mock_server() -> std::net::SocketAddr {
let listener = TcpListener::bind("127.0.0.1:0").await.expect("bind");
let addr = listener.local_addr().expect("addr");
tokio::spawn(async move {
let (mut sock, _) = listener.accept().await.expect("accept");
// Read the Hello header (8 bytes) to learn the size, then drain it.
let mut hdr = [0u8; 8];
if sock.read_exact(&mut hdr).await.is_err() {
return;
}
let size = u32::from_le_bytes([hdr[4], hdr[5], hdr[6], hdr[7]]) as usize;
let mut rest = vec![0u8; size.saturating_sub(8)];
let _ = sock.read_exact(&mut rest).await;
// Reply: ACK + size + 5 u32 fields.
let mut ack = Vec::new();
ack.extend_from_slice(b"ACKF");
ack.extend_from_slice(&28u32.to_le_bytes());
for _ in 0..5 {
ack.extend_from_slice(&0u32.to_le_bytes());
}
let _ = sock.write_all(&ack).await;
});
addr
}
#[tokio::test]
async fn probe_detects_an_opcua_server() {
let addr = mock_server().await;
let p = probe(&addr.ip().to_string(), addr.port(), Duration::from_secs(2)).await;
assert!(p.reachable && p.is_opcua);
}
#[tokio::test]
async fn probe_reports_unreachable_for_a_closed_port() {
let p = probe("127.0.0.1", 1, Duration::from_millis(500)).await;
assert!(!p.reachable && !p.is_opcua);
}
#[test]
fn hello_message_is_well_formed() {
let m = hello_message("opc.tcp://h:4840");
assert_eq!(&m[0..4], b"HELF");
// The embedded size equals the actual length.
let size = u32::from_le_bytes([m[4], m[5], m[6], m[7]]) as usize;
assert_eq!(size, m.len());
}
}
@@ -1,137 +0,0 @@
//! TCP service discovery for a device.
//!
//! Connect-scans a curated set of OT/ICS and insecure-management ports and reports
//! the ones that are open. The deep protocol probes own Modbus (502), OPC UA
//! (4840) and EtherNet/IP (44818); this surfaces the *rest* of the industrial and
//! cleartext-management surface (Siemens S7, DNP3, CODESYS programming, Telnet, …).
use std::time::Duration;
use futures_util::future::join_all;
use tokio::net::TcpStream;
use tokio::time::timeout;
/// Whether an open port is an industrial protocol or an insecure management service.
#[derive(Debug, Clone, Copy, PartialEq, Eq)]
pub enum PortKind {
/// An industrial control protocol (typically unauthenticated).
Ics,
/// A cleartext management service (credentials/data in the clear).
InsecureMgmt,
}
/// A well-known port worth flagging when open.
#[derive(Debug, Clone, Copy)]
pub struct KnownPort {
pub port: u16,
pub service: &'static str,
pub kind: PortKind,
pub note: &'static str,
}
/// The curated scan list. Excludes 502 / 4840 / 44818 — those have dedicated deep
/// probes (Modbus, OPC UA, EtherNet/IP) that report richer findings.
pub const KNOWN_PORTS: &[KnownPort] = &[
KnownPort {
port: 102,
service: "S7comm / ISO-TSAP",
kind: PortKind::Ics,
note: "Siemens S7 PLC communication",
},
KnownPort {
port: 20000,
service: "DNP3",
kind: PortKind::Ics,
note: "SCADA / DNP3",
},
KnownPort {
port: 1911,
service: "Niagara Fox",
kind: PortKind::Ics,
note: "Tridium Niagara building automation",
},
KnownPort {
port: 11740,
service: "CODESYS",
kind: PortKind::Ics,
note: "CODESYS programming protocol",
},
KnownPort {
port: 1962,
service: "PCWorx",
kind: PortKind::Ics,
note: "Phoenix Contact PCWorx",
},
KnownPort {
port: 9600,
service: "OMRON FINS",
kind: PortKind::Ics,
note: "Omron FINS",
},
KnownPort {
port: 789,
service: "Red Lion Crimson",
kind: PortKind::Ics,
note: "Red Lion controllers",
},
KnownPort {
port: 23,
service: "Telnet",
kind: PortKind::InsecureMgmt,
note: "cleartext remote shell",
},
KnownPort {
port: 21,
service: "FTP",
kind: PortKind::InsecureMgmt,
note: "cleartext file transfer",
},
];
/// Connect-scan `ports` on `host` (concurrently) and return those that accept a
/// TCP connection.
pub async fn scan<'a>(host: &str, ports: &'a [KnownPort], budget: Duration) -> Vec<&'a KnownPort> {
let checks = ports.iter().map(|kp| async move {
let open = timeout(budget, TcpStream::connect((host, kp.port)))
.await
.map(|r| r.is_ok())
.unwrap_or(false);
(kp, open)
});
join_all(checks)
.await
.into_iter()
.filter_map(|(kp, open)| open.then_some(kp))
.collect()
}
#[cfg(test)]
mod tests {
use super::*;
use tokio::net::TcpListener;
#[tokio::test]
async fn scan_reports_only_open_ports() {
// Bind one port (open) and pick another that is closed.
let listener = TcpListener::bind("127.0.0.1:0").await.expect("bind");
let open_port = listener.local_addr().expect("addr").port();
let ports = [
KnownPort {
port: open_port,
service: "test-open",
kind: PortKind::Ics,
note: "",
},
KnownPort {
port: 1,
service: "test-closed",
kind: PortKind::InsecureMgmt,
note: "",
},
];
let found = scan("127.0.0.1", &ports, Duration::from_millis(500)).await;
let services: Vec<&str> = found.iter().map(|p| p.service).collect();
assert_eq!(services, vec!["test-open"]);
}
}
@@ -1,6 +1,5 @@
use mongodb::bson::doc;
use crate::pipeline::repo_view::RepoView;
use compliance_core::models::*;
use super::orchestrator::{extract_base_url, PipelineOrchestrator};
@@ -11,7 +10,7 @@ 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: &RepoView) -> Option<TrackerDispatch> {
pub(super) fn build_tracker(&self, repo: &TrackedRepository) -> Option<TrackerDispatch> {
let tracker_type = repo.tracker_type.as_ref()?;
// Per-repo token takes precedence, fall back to global config
match tracker_type {
@@ -82,7 +81,7 @@ impl PipelineOrchestrator {
#[tracing::instrument(skip_all, fields(repo_id = %repo_id))]
pub(super) async fn create_tracker_issues(
&self,
repo: &RepoView,
repo: &TrackedRepository,
repo_id: &str,
new_findings: &[Finding],
) -> Result<(), AgentError> {
-5
View File
@@ -1,19 +1,14 @@
pub mod code_review;
pub mod cve;
pub mod dedup;
pub mod firmware_sbom;
pub mod git;
pub mod gitleaks;
mod graph_build;
pub mod ics;
mod issue_creation;
pub mod lint;
pub mod orchestrator;
pub mod patterns;
pub mod plan;
pub mod plc;
mod pr_review;
pub mod repo_view;
pub mod sbom;
pub mod semgrep;
mod tracker_dispatch;
+141 -674
View File
@@ -15,8 +15,6 @@ use crate::pipeline::git::GitOps;
use crate::pipeline::gitleaks::GitleaksScanner;
use crate::pipeline::lint::LintScanner;
use crate::pipeline::patterns::{GdprPatternScanner, OAuthPatternScanner};
use crate::pipeline::plan::build_scan_plan;
use crate::pipeline::repo_view::RepoView;
use crate::pipeline::sbom::SbomScanner;
use crate::pipeline::semgrep::SemgrepScanner;
@@ -52,8 +50,72 @@ 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: &RepoView, scan_run_id: &str) -> Result<u32, AgentError> {
async fn run_pipeline(
&self,
repo: &TrackedRepository,
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
@@ -67,6 +129,7 @@ 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
@@ -259,12 +322,67 @@ impl PipelineOrchestrator {
.await?;
}
// 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)");
// 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)");
}
}
// Stage 6: Issue Creation
@@ -277,9 +395,20 @@ impl PipelineOrchestrator {
tracing::warn!("[{repo_id}] Issue creation failed: {e}");
}
// 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 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?;
// Stage 8: DAST (async, optional — only if a DastTarget is configured)
tracing::info!("[{repo_id}] Stage 8: Checking for DAST targets");
@@ -290,621 +419,6 @@ impl PipelineOrchestrator {
Ok(new_count)
}
/// Unified entry point (behind `UNIFIED_PIPELINE`): run a scan for an
/// `OnboardedTarget`. Mirrors [`Self::run`] but sources the target from
/// `onboarded_targets` and dispatches by the scan plan.
#[tracing::instrument(skip_all, fields(target_id = %target_id, trigger = ?trigger))]
pub async fn run_target(
&self,
target_id: &str,
trigger: ScanTrigger,
) -> Result<(), AgentError> {
let oid = mongodb::bson::oid::ObjectId::parse_str(target_id)
.map_err(|e| AgentError::Other(e.to_string()))?;
let target = self
.db
.onboarded_targets()
.find_one(doc! { "_id": oid })
.await?
.ok_or_else(|| AgentError::Other(format!("Onboarded target {target_id} not found")))?;
let scan_run = ScanRun::new(target_id.to_string(), trigger);
let insert = self.db.scan_runs().insert_one(&scan_run).await?;
let scan_run_id = insert
.inserted_id
.as_object_id()
.map(|id| id.to_hex())
.unwrap_or_default();
let result = self.run_target_pipeline(&target, &scan_run_id).await;
match &result {
Ok(count) => {
self.db
.scan_runs()
.update_one(
doc! { "_id": &insert.inserted_id },
doc! { "$set": {
"status": "completed",
"current_phase": "completed",
"new_findings_count": *count as i64,
"completed_at": mongodb::bson::DateTime::now(),
} },
)
.await?;
// Refresh the target's cached findings count. The shared pipeline
// (Stage 7) increments `repositories`, which the unified path does
// not use, so set the accurate total on the target itself.
let total = self
.db
.findings()
.count_documents(doc! { "repo_id": target_id })
.await
.unwrap_or(*count as u64);
self.db
.onboarded_targets()
.update_one(
doc! { "_id": oid },
doc! { "$set": {
"findings_count": total as i64,
"updated_at": mongodb::bson::DateTime::now(),
} },
)
.await?;
}
Err(e) => {
tracing::error!(target_id, error = %e, "Unified scan pipeline failed");
self.db
.scan_runs()
.update_one(
doc! { "_id": &insert.inserted_id },
doc! { "$set": {
"status": "failed",
"error_message": e.to_string(),
"completed_at": mongodb::bson::DateTime::now(),
} },
)
.await?;
}
}
result.map(|_| ())
}
/// Run the applicable scans for a target. For a code target this reuses the
/// full legacy pipeline over the code artifact (clone → SAST umbrella →
/// triage → persist → issues → DAST); firmware/PLC/mobile scanners are
/// follow-ups (#128/#129/#130). Returns the number of new findings.
async fn run_target_pipeline(
&self,
target: &OnboardedTarget,
scan_run_id: &str,
) -> Result<u32, AgentError> {
let target_id = target.id.map(|id| id.to_hex()).unwrap_or_default();
let plan = build_scan_plan(target);
tracing::info!(
target_id = %target_id,
target_type = %target.target_type,
planned_steps = plan.steps.len(),
"Unified pipeline: scan plan built"
);
// Ingest + classify (tramiton for firmware) and store the detected type.
self.classify_and_store(target, &target_id, scan_run_id)
.await;
// Provision a DAST target from a LiveUrl artifact so DAST fires for
// wizard-created targets, not just migrated ones.
self.ensure_dast_target(target, &plan).await;
// PLC/SPS targets: the control-logic scan consumes the PLC source (an
// uploaded PlcProject *or* a git repo / source archive of PLCopen XML / ST
// exports), so it takes over the code artifact — we don't also run the
// SAST pipeline over it. A PLC device is reachable, so DAST still runs
// against a WebVisu / exposed endpoint when one is provisioned.
let mut new_count = 0u32;
let plc = plan.has(ScanType::PlcControlLogic);
let ics = plan.has(ScanType::IcsProbe);
if plc {
new_count += self.run_plc_scan(target, &target_id, scan_run_id).await?;
}
if ics {
new_count += self.run_ics_probe(target, &target_id, scan_run_id).await?;
}
if plc || ics {
// PLC/SPS device: also DAST against a WebVisu / exposed endpoint, but
// only when DAST is actually planned — a device reachable only over an
// industrial protocol (e.g. modbus://) has no web surface to crawl, and
// running DAST there just fails at reconnaissance. Gating here (not only
// at provisioning) also stops a DAST target left over from an earlier
// run from re-triggering. The control-logic scan already consumed the
// code artifact, so the SAST pipeline is not re-run.
if plan.has(ScanType::Dast) {
self.update_phase(scan_run_id, "dast_scanning").await;
self.maybe_trigger_dast(&target_id, scan_run_id).await;
}
return Ok(new_count);
}
match target.code_artifact() {
Some(code) if code.kind == ArtifactKind::GitRepo => {
let repo = RepoView::from_target(target, code);
let n = self.run_pipeline(&repo, scan_run_id).await?;
self.finalize_target(target, &repo, n).await?;
new_count += n;
}
Some(_) => {
tracing::warn!(
target_id = %target_id,
"Unified pipeline: source-archive scanning not yet wired; skipping"
);
}
None => {
// No code to scan (a migrated DAST target). Firmware/mobile static
// scanners land in #128/#129; DAST for a running URL works when a
// DastTarget row exists (provisioned above from a LiveUrl, or from
// a migrated target).
tracing::info!(
target_id = %target_id,
"Unified pipeline: no code artifact; attempting DAST"
);
self.update_phase(scan_run_id, "dast_scanning").await;
self.maybe_trigger_dast(&target_id, scan_run_id).await;
}
}
Ok(new_count)
}
/// Analyze a PLC/SPS project (Structured Text / PLCopen XML) for
/// control-logic security issues and persist the new findings.
async fn run_plc_scan(
&self,
target: &OnboardedTarget,
target_id: &str,
scan_run_id: &str,
) -> Result<u32, AgentError> {
tracing::info!(target_id, "[{target_id}] PLC control-logic analysis");
self.update_phase(scan_run_id, "plc_analysis").await;
let ctx = crate::ingest::IngestContext::from_config(&self.config, target_id);
let ingest_set = crate::ingest::ingest_all(target, &ctx)?;
// Every PLC-source artifact on the target: dedicated PLC projects plus any
// code artifacts (git repo / source archive) holding PLCopen XML / ST
// exports. A target can carry several (e.g. one POU export per file).
let sources: Vec<&Artifact> = target
.artifacts
.iter()
.filter(|a| {
matches!(
a.kind,
ArtifactKind::PlcProject | ArtifactKind::GitRepo | ArtifactKind::SourceArchive
)
})
.collect();
if sources.is_empty() {
tracing::warn!(target_id, "PLC scan: no PLC source artifact");
return Ok(0);
}
let mut all_findings = Vec::new();
let mut all_sbom: Vec<SbomEntry> = Vec::new();
let mut sbom_seen = std::collections::BTreeSet::new();
for a in &sources {
let Some(path) = ingest_set.get(&a.id).and_then(|ia| ia.working_path.clone()) else {
continue;
};
all_findings.extend(crate::pipeline::plc::analyze_tree(&path, target_id));
// Control-application SBOM: CODESYS libraries + runtime from a
// `.projectarchive` (uploaded, or committed in the working tree).
let archive = a
.stored_path
.clone()
.unwrap_or_else(|| a.source_ref.clone());
for e in crate::pipeline::plc::sbom::collect_sbom(
std::path::Path::new(&archive),
&path,
target_id,
) {
if sbom_seen.insert((e.name.clone(), e.version.clone())) {
all_sbom.push(e);
}
}
}
tracing::info!(
target_id,
artifacts = sources.len(),
found = all_findings.len(),
"PLC control-logic analysis complete"
);
let mut new_count = 0u32;
for mut finding in all_findings {
finding.scan_run_id = Some(scan_run_id.to_string());
if self
.db
.findings()
.find_one(doc! { "fingerprint": &finding.fingerprint })
.await?
.is_none()
{
self.db.findings().insert_one(&finding).await?;
new_count += 1;
}
}
if !all_sbom.is_empty() {
if let Err(e) = self
.persist_control_app_sbom(target_id, &target.name, all_sbom)
.await
{
tracing::warn!(target_id, error = %e, "control-app SBOM persist failed");
}
}
Ok(new_count)
}
/// Probe a running PLC/SPS device over industrial protocols (Modbus/TCP, …)
/// and persist findings for exposed / unauthenticated control access. The
/// probe is read-only; it targets the Modbus port of the target's live URL.
async fn run_ics_probe(
&self,
target: &OnboardedTarget,
target_id: &str,
scan_run_id: &str,
) -> Result<u32, AgentError> {
self.update_phase(scan_run_id, "ics_probe").await;
let Some(endpoint) = target.live_url().map(|a| a.source_ref.clone()) else {
tracing::warn!(target_id, "ICS probe: no live URL");
return Ok(0);
};
// Short per-request budget so an unreachable device doesn't stall the scan.
let budget = std::time::Duration::from_secs(5);
let findings = crate::pipeline::ics::probe_target(&endpoint, target_id, budget).await;
tracing::info!(
target_id,
endpoint = %endpoint,
found = findings.len(),
"ICS probe complete"
);
let mut new_count = 0u32;
for mut finding in findings {
finding.scan_run_id = Some(scan_run_id.to_string());
if self
.db
.findings()
.find_one(doc! { "fingerprint": &finding.fingerprint })
.await?
.is_none()
{
self.db.findings().insert_one(&finding).await?;
new_count += 1;
}
}
Ok(new_count)
}
/// Store a control-application SBOM (CODESYS libraries + runtime) for a target
/// and match it against known CVEs. Scoped to `package_manager = "codesys"` so
/// it refreshes on re-scan and coexists with any firmware/source SBOM. The
/// runtime `Cmp*` / `3SLicense` components carry real CODESYS advisories, so
/// this is where PLC-device CVE coverage comes from.
async fn persist_control_app_sbom(
&self,
target_id: &str,
target_name: &str,
mut entries: Vec<SbomEntry>,
) -> Result<(), AgentError> {
if entries.is_empty() {
return Ok(());
}
self.db
.sbom_entries()
.delete_many(doc! { "repo_id": target_id, "package_manager": "codesys" })
.await?;
let cve_scanner = CveScanner::new(
self.http.clone(),
self.config.searxng_url.clone(),
self.config.nvd_api_key.as_ref().map(|k| {
use secrecy::ExposeSecret;
k.expose_secret().to_string()
}),
);
let mut alerts = match tokio::time::timeout(
std::time::Duration::from_secs(600),
cve_scanner.scan_dependencies(target_id, &mut entries),
)
.await
{
Ok(Ok(a)) => a,
Ok(Err(e)) => {
tracing::warn!(target_id, error = %e, "control-app CVE scan failed");
Vec::new()
}
Err(_) => {
tracing::warn!(target_id, "control-app CVE scan timed out");
Vec::new()
}
};
// OSV can't match `pkg:codesys/*` (no such ecosystem); CODESYS advisories
// live in NVD keyed by CPE + runtime version. Add those (best-effort).
if let Ok(codesys) = tokio::time::timeout(
std::time::Duration::from_secs(120),
cve_scanner.scan_codesys(target_id, &mut entries),
)
.await
{
alerts.extend(codesys);
} else {
tracing::warn!(target_id, "CODESYS CVE match timed out");
}
for entry in &entries {
let filter = doc! {
"repo_id": &entry.repo_id,
"name": &entry.name,
"version": &entry.version,
};
if let Ok(d) = mongodb::bson::to_document(entry) {
self.db
.sbom_entries()
.update_one(filter, doc! { "$set": d })
.upsert(true)
.await?;
}
}
let new_notifs = self
.persist_cve_alerts(target_id, target_name, &alerts)
.await?;
tracing::info!(
target_id,
components = entries.len(),
alerts = alerts.len(),
notifications = new_notifs,
"control-app SBOM stored"
);
Ok(())
}
/// Upsert CVE alerts for a target and create dedup'd CVE notifications;
/// returns the number of newly-created notifications. Shared by the SAST
/// pipeline and the PLC control-app SBOM path, so every SBOM source (source,
/// firmware, CODESYS libraries/runtime) raises the same notifications.
async fn persist_cve_alerts(
&self,
repo_id: &str,
repo_name: &str,
alerts: &[CveAlert],
) -> Result<u32, AgentError> {
use compliance_core::models::notification::{parse_severity, CveNotification};
let mut new_notif = 0u32;
for alert in alerts {
let filter = doc! { "cve_id": &alert.cve_id, "repo_id": &alert.repo_id };
let update = mongodb::bson::to_document(alert)
.map(|d| doc! { "$set": d })
.unwrap_or_else(|_| doc! {});
self.db
.cve_alerts()
.update_one(filter, update)
.upsert(true)
.await?;
// Dedup notifications by cve + repo + package + version.
let notif_filter = doc! {
"cve_id": &alert.cve_id,
"repo_id": &alert.repo_id,
"package_name": &alert.affected_package,
"package_version": &alert.affected_version,
};
let severity = parse_severity(alert.severity.as_deref(), alert.cvss_score);
let mut notification = CveNotification::new(
alert.cve_id.clone(),
repo_id.to_string(),
repo_name.to_string(),
alert.affected_package.clone(),
alert.affected_version.clone(),
severity,
);
notification.cvss_score = alert.cvss_score;
notification.summary = alert.summary.clone();
notification.url = Some(format!("https://osv.dev/vulnerability/{}", alert.cve_id));
let notif_update = doc! {
"$setOnInsert": mongodb::bson::to_bson(&notification).unwrap_or_default()
};
if let Ok(result) = self
.db
.cve_notifications()
.update_one(notif_filter, notif_update)
.upsert(true)
.await
{
if result.upserted_id.is_some() {
new_notif += 1;
}
}
}
Ok(new_notif)
}
/// Ingest the target's artifacts, classify (tramiton for firmware/RTOS/Yocto,
/// heuristics otherwise), and store the detected classification on the target.
/// Best-effort — never fails the scan.
async fn classify_and_store(
&self,
target: &OnboardedTarget,
target_id: &str,
scan_run_id: &str,
) {
self.update_phase(scan_run_id, "classification").await;
let ctx = crate::ingest::IngestContext::from_config(&self.config, target_id);
let ingest_set = match crate::ingest::ingest_all(target, &ctx) {
Ok(set) => set,
Err(e) => {
tracing::warn!(target_id, error = %e, "Unified pipeline: ingest for classification failed");
return;
}
};
let working_paths = ingest_set.working_paths();
match crate::classify::classify_target(
target,
&working_paths,
&crate::classify::TramitonNative,
)
.await
{
Ok(classification) => {
tracing::info!(
target_id,
suggested = %classification.suggested,
"Unified pipeline: classified target"
);
if let (Some(oid), Ok(bson)) = (target.id, mongodb::bson::to_bson(&classification))
{
let _ = self
.db
.onboarded_targets()
.update_one(
doc! { "_id": oid },
doc! { "$set": { "classification": bson } },
)
.await;
}
}
Err(e) => {
tracing::warn!(target_id, error = %e, "Unified pipeline: classification failed")
}
}
// Analysis-based firmware SBOM: for embedded targets, derive components
// (resolved libraries + cross-toolchain) from tramiton's build-plan
// analysis over the already-ingested source — no build, no binary
// upload. Best-effort; empty when no build plan forms.
if crate::pipeline::firmware_sbom::is_firmware_target(target.target_type) {
if let Some(code) = target.code_artifact() {
if let Some(path) = working_paths.get(&code.id) {
let entries =
crate::pipeline::firmware_sbom::firmware_sbom_entries(path, target_id)
.await;
if !entries.is_empty() {
let _ = self
.db
.sbom_entries()
.delete_many(doc! { "repo_id": target_id })
.await;
for entry in &entries {
let filter = doc! {
"repo_id": &entry.repo_id,
"name": &entry.name,
"version": &entry.version,
};
if let Ok(d) = mongodb::bson::to_document(entry) {
let _ = self
.db
.sbom_entries()
.update_one(filter, doc! { "$set": d })
.upsert(true)
.await;
}
}
tracing::info!(
target_id,
count = entries.len(),
"Firmware SBOM: stored components from tramiton analysis"
);
}
}
}
}
}
/// If the target has a `LiveUrl` artifact and DAST is planned, provision a
/// `DastTarget` (keyed by `repo_id` = target id) so the existing DAST trigger
/// fires for wizard-created targets. Idempotent.
async fn ensure_dast_target(
&self,
target: &OnboardedTarget,
plan: &crate::pipeline::plan::ScanPlan,
) {
if !plan.has(ScanType::Dast) {
return;
}
let (Some(url), Some(oid)) = (target.live_url(), target.id) else {
return;
};
let target_id = oid.to_hex();
if self
.db
.dast_targets()
.find_one(doc! { "repo_id": &target_id })
.await
.ok()
.flatten()
.is_some()
{
return; // already provisioned
}
let kind = url
.web
.as_ref()
.map(|w| w.target_kind.clone())
.unwrap_or(DastTargetType::WebApp);
let mut dast = DastTarget::new(target.name.clone(), url.source_ref.clone(), kind);
dast.repo_id = Some(target_id);
if let Some(web) = &url.web {
dast.excluded_paths = web.excluded_paths.clone();
dast.max_crawl_depth = web.max_crawl_depth;
dast.rate_limit = web.rate_limit;
dast.allow_destructive = web.allow_destructive;
}
if let Some(auth) = &url.auth {
dast.auth_config = Some(DastAuthConfig {
method: auth.method.clone(),
login_url: auth.login_url.clone(),
username: auth.username.clone(),
password: None,
token: auth.secret.clone(),
headers: auth.headers.clone(),
});
}
if let Err(e) = self.db.dast_targets().insert_one(&dast).await {
tracing::warn!(error = %e, "Unified pipeline: failed to provision DAST target");
}
}
/// Sync the onboarded-target document after a scan: bump `findings_count`
/// and advance the git artifact's `last_scanned_commit` watermark.
async fn finalize_target(
&self,
target: &OnboardedTarget,
repo: &RepoView,
new_count: u32,
) -> Result<(), AgentError> {
let oid = match target.id {
Some(id) => id,
None => return Ok(()),
};
self.db
.onboarded_targets()
.update_one(
doc! { "_id": oid },
doc! {
"$inc": { "findings_count": new_count as i64 },
"$set": { "updated_at": mongodb::bson::DateTime::now() },
},
)
.await?;
let repo_path = std::path::Path::new(&self.config.git_clone_base_path).join(&repo.name);
if let (Ok(sha), Some(code)) = (GitOps::get_head_sha(&repo_path), target.code_artifact()) {
self.db
.onboarded_targets()
.update_one(
doc! { "_id": oid, "artifacts.id": &code.id },
doc! { "$set": { "artifacts.$.git.last_scanned_commit": sha } },
)
.await?;
}
Ok(())
}
pub(super) async fn update_phase(&self, scan_run_id: &str, phase: &str) {
if let Ok(oid) = mongodb::bson::oid::ObjectId::parse_str(scan_run_id) {
let _ = self
@@ -946,50 +460,3 @@ pub(super) fn extract_base_url(git_url: &str) -> Option<String> {
None
}
}
#[cfg(test)]
#[allow(clippy::expect_used, clippy::unwrap_used)]
mod tests {
use super::*;
use compliance_core::models::{
Artifact, ArtifactAuth, IssueTrackerConfig, TargetType, TrackerType,
};
#[test]
fn repo_view_preserves_id_git_auth_and_tracker() {
let mut target = OnboardedTarget::new("acme".to_string(), TargetType::WebApp);
target.id = Some(mongodb::bson::oid::ObjectId::new());
target.findings_count = 3;
target.scan_config.issue_tracker = Some(IssueTrackerConfig {
tracker_type: Some(TrackerType::Gitea),
owner: Some("acme".to_string()),
repo: Some("web".to_string()),
token: Some("tt".to_string()),
});
let mut artifact = Artifact::git_repo("https://git/acme.git", "develop");
if let Some(git) = artifact.git.as_mut() {
git.last_scanned_commit = Some("abc123".to_string());
}
artifact.auth = Some(ArtifactAuth {
method: "token".to_string(),
username: Some("bob".to_string()),
secret: Some("pat".to_string()),
..Default::default()
});
target.artifacts.push(artifact);
let code = target.code_artifact().expect("code artifact");
let repo = RepoView::from_target(&target, code);
assert_eq!(repo.id, target.id); // preserved
assert_eq!(repo.git_url, "https://git/acme.git");
assert_eq!(repo.default_branch, "develop");
assert_eq!(repo.last_scanned_commit.as_deref(), Some("abc123"));
assert_eq!(repo.auth_token.as_deref(), Some("pat"));
assert_eq!(repo.auth_username.as_deref(), Some("bob"));
assert_eq!(repo.tracker_type, Some(TrackerType::Gitea));
assert_eq!(repo.tracker_owner.as_deref(), Some("acme"));
assert_eq!(repo.findings_count, 3);
}
}
+1 -1
View File
@@ -215,7 +215,7 @@ fn scan_with_patterns(
repo_id.to_string(),
fingerprint,
scanner_name.to_string(),
scan_type,
scan_type.clone(),
pattern.title.clone(),
pattern.description.clone(),
pattern.severity.clone(),
-214
View File
@@ -1,214 +0,0 @@
//! The scan plan.
//!
//! [`build_scan_plan`] turns an [`OnboardedTarget`] into the concrete ordered
//! list of scans to run, each bound to the artifact it consumes. It intersects
//! the scan-applicability matrix ([`applicable_scans`]) with the target's
//! `scan_config` overrides: a scan runs when its required artifact is present and
//! it is either on by default or explicitly enabled, and is not explicitly
//! disabled. This is the decision engine the unified pipeline (`run_target`)
//! executes.
use compliance_core::models::{Artifact, ArtifactKind, OnboardedTarget, ScanPhase, ScanType};
use compliance_core::scan_matrix::applicable_scans;
/// One scan to run, bound to the artifact it operates on.
#[derive(Debug, Clone, PartialEq)]
pub struct ScanStep {
/// The scan to run.
pub scan_type: ScanType,
/// The pipeline phase to report while it runs.
pub phase: ScanPhase,
/// The id of the artifact this scan consumes ([`Artifact::id`]).
pub artifact_id: String,
}
/// The ordered set of scans to run for a target.
#[derive(Debug, Clone, Default, PartialEq)]
pub struct ScanPlan {
/// The scans, in matrix order.
pub steps: Vec<ScanStep>,
}
impl ScanPlan {
/// Whether the plan contains a step for the given scan type.
pub fn has(&self, scan: ScanType) -> bool {
self.steps.iter().any(|s| s.scan_type == scan)
}
/// Whether the plan is empty (nothing to run).
pub fn is_empty(&self) -> bool {
self.steps.is_empty()
}
}
/// Build the scan plan for a target: matrix defaults ∩ `scan_config`, each scan
/// bound to the artifact it consumes. Scans whose required artifact is absent, or
/// that are disabled, or off-by-default and not explicitly enabled, are dropped.
pub fn build_scan_plan(target: &OnboardedTarget) -> ScanPlan {
let enabled = &target.scan_config.enabled_scans;
let disabled = &target.scan_config.disabled_scans;
let mut steps = Vec::new();
for option in applicable_scans(target) {
// Required artifact missing → not runnable.
if option.blocked_reason.is_some() {
continue;
}
// Explicit opt-out wins.
if disabled.contains(&option.scan) {
continue;
}
// Run if on by default, or explicitly enabled.
if !option.default_on && !enabled.contains(&option.scan) {
continue;
}
let Some(artifact) = resolve_artifact(target, option.required_artifact) else {
continue;
};
steps.push(ScanStep {
scan_type: option.scan,
phase: phase_for(option.scan),
artifact_id: artifact.id.clone(),
});
}
ScanPlan { steps }
}
/// Resolve the artifact a scan consumes. A "code" requirement (represented by
/// `GitRepo`) is satisfied by a git repo *or* a source archive. The PLC
/// control-logic requirement (represented by `PlcProject`) prefers an uploaded
/// PLC project but also accepts a code artifact — a git repo / source archive
/// holding PLCopen XML / ST exports.
fn resolve_artifact(target: &OnboardedTarget, required: Option<ArtifactKind>) -> Option<&Artifact> {
match required {
Some(ArtifactKind::GitRepo) => target.code_artifact(),
Some(ArtifactKind::PlcProject) => target
.first_of(ArtifactKind::PlcProject)
.or_else(|| target.code_artifact()),
Some(kind) => target.first_of(kind),
None => target.code_artifact().or_else(|| target.artifacts.first()),
}
}
/// The pipeline phase reported while a given scan runs.
fn phase_for(scan: ScanType) -> ScanPhase {
match scan {
ScanType::Sast => ScanPhase::Sast,
ScanType::Sbom => ScanPhase::SbomGeneration,
ScanType::Cve => ScanPhase::CveScanning,
ScanType::Gdpr | ScanType::OAuth => ScanPhase::PatternScanning,
ScanType::SecretDetection => ScanPhase::SecretDetection,
ScanType::Lint => ScanPhase::LintScanning,
ScanType::CodeReview => ScanPhase::CodeReview,
ScanType::Graph => ScanPhase::GraphBuilding,
ScanType::Dast => ScanPhase::DastScanning,
ScanType::FirmwareStatic => ScanPhase::FirmwareStatic,
ScanType::PlcControlLogic => ScanPhase::PlcAnalysis,
ScanType::MobileStatic => ScanPhase::MobileStatic,
ScanType::ContainerScan => ScanPhase::ContainerScan,
ScanType::IcsProbe => ScanPhase::IcsProbe,
}
}
#[cfg(test)]
#[allow(clippy::expect_used, clippy::unwrap_used)]
mod tests {
use super::*;
use compliance_core::models::{PlcFormat, TargetType};
fn target(target_type: TargetType, artifacts: Vec<Artifact>) -> OnboardedTarget {
let mut t = OnboardedTarget::new("t".to_string(), target_type);
t.artifacts = artifacts;
t
}
fn step_for<'a>(plan: &'a ScanPlan, scan: ScanType) -> Option<&'a ScanStep> {
plan.steps.iter().find(|s| s.scan_type == scan)
}
#[test]
fn webapp_with_code_and_url_runs_sast_and_dast_bound_to_the_right_artifacts() {
let code = Artifact::git_repo("https://git/x", "main");
let url = Artifact::live_url("https://x");
let (code_id, url_id) = (code.id.clone(), url.id.clone());
let t = target(TargetType::WebApp, vec![code, url]);
let plan = build_scan_plan(&t);
let sast = step_for(&plan, ScanType::Sast).expect("sast planned");
assert_eq!(sast.artifact_id, code_id);
assert_eq!(sast.phase, ScanPhase::Sast);
let dast = step_for(&plan, ScanType::Dast).expect("dast planned");
assert_eq!(dast.artifact_id, url_id);
}
#[test]
fn webapp_without_url_omits_dast() {
let t = target(TargetType::WebApp, vec![Artifact::git_repo("u", "main")]);
let plan = build_scan_plan(&t);
assert!(plan.has(ScanType::Sast));
assert!(!plan.has(ScanType::Dast));
}
#[test]
fn code_scan_binds_to_source_archive_when_no_git_repo() {
let arc = Artifact::source_archive("src.zip");
let arc_id = arc.id.clone();
let t = target(TargetType::BackendService, vec![arc]);
let plan = build_scan_plan(&t);
let sast = step_for(&plan, ScanType::Sast).expect("sast planned");
assert_eq!(sast.artifact_id, arc_id);
}
#[test]
fn firmware_sbom_and_cve_bind_to_the_firmware_image() {
let fw = Artifact::firmware_image("fw.bin");
let fw_id = fw.id.clone();
let t = target(TargetType::FirmwareBareMetal, vec![fw]);
let plan = build_scan_plan(&t);
let sbom = step_for(&plan, ScanType::Sbom).expect("sbom planned");
assert_eq!(sbom.artifact_id, fw_id);
assert!(step_for(&plan, ScanType::FirmwareStatic).is_some());
assert!(!plan.has(ScanType::Dast));
}
#[test]
fn plc_plans_only_control_logic() {
let plc = Artifact::plc_project("p.xml", PlcFormat::PlcopenXml);
let t = target(TargetType::PlcSps, vec![plc]);
let plan = build_scan_plan(&t);
assert_eq!(plan.steps.len(), 1);
assert_eq!(plan.steps[0].scan_type, ScanType::PlcControlLogic);
assert_eq!(plan.steps[0].phase, ScanPhase::PlcAnalysis);
}
#[test]
fn plc_control_logic_binds_to_a_git_repo() {
// A CODESYS project in git (PLCopen XML / ST exports) with no uploaded
// PlcProject: control-logic still plans, bound to the git artifact.
let git = Artifact::git_repo("https://git/plc", "main");
let git_id = git.id.clone();
let t = target(TargetType::PlcSps, vec![git]);
let plan = build_scan_plan(&t);
let step = step_for(&plan, ScanType::PlcControlLogic).expect("control-logic planned");
assert_eq!(step.artifact_id, git_id, "PLC scan binds to the git repo");
}
#[test]
fn disabled_scan_is_dropped_and_off_by_default_can_be_enabled() {
let mut t = target(TargetType::WebApp, vec![Artifact::git_repo("u", "main")]);
t.scan_config.disabled_scans = vec![ScanType::Lint];
// CodeReview is off by default for web; enable it explicitly.
t.scan_config.enabled_scans = vec![ScanType::CodeReview];
let plan = build_scan_plan(&t);
assert!(!plan.has(ScanType::Lint));
assert!(plan.has(ScanType::CodeReview));
assert!(plan.has(ScanType::Sast));
}
#[test]
fn no_code_artifact_yields_empty_plan_for_web() {
let t = target(TargetType::WebApp, vec![]);
let plan = build_scan_plan(&t);
assert!(plan.is_empty());
}
}
-226
View File
@@ -1,226 +0,0 @@
//! 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
@@ -1,372 +0,0 @@
//! 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
@@ -1,234 +0,0 @@
//! 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
@@ -1,766 +0,0 @@
//! 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");
}
}
@@ -1,418 +0,0 @@
//! 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
@@ -1,632 +0,0 @@
//! 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
@@ -1,253 +0,0 @@
//! 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);
}
}
+1 -2
View File
@@ -1,4 +1,3 @@
use crate::pipeline::repo_view::RepoView;
use compliance_core::models::*;
use super::dedup::compute_fingerprint;
@@ -15,7 +14,7 @@ impl PipelineOrchestrator {
#[tracing::instrument(skip_all, fields(repo_id = %repo_id, pr_number))]
pub async fn run_pr_review(
&self,
repo: &RepoView,
repo: &TrackedRepository,
repo_id: &str,
pr_number: u64,
base_sha: &str,
@@ -1,74 +0,0 @@
//! `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
}
}
+25 -260
View File
@@ -4,21 +4,8 @@ use tokio_cron_scheduler::{Job, JobScheduler};
use compliance_core::models::ScanTrigger;
use crate::agent::ComplianceAgent;
use crate::database::Database;
use crate::error::AgentError;
/// Default tenant the scheduler runs against when neither the tenant
/// registry nor `SCHEDULER_TENANT_IDS` are configured. Matches the
/// dev-injector default so a bare `cargo run` has the scheduler
/// scanning whatever lives in `<prefix>_dev`.
const DEFAULT_SCHEDULER_TENANT_ID: &str = "dev";
/// Request timeout when fetching the live tenant list from the
/// registry. Kept short — if the registry is slow we'd rather fall
/// back to env-configured ids and finish the tick than block the
/// scheduler loop.
const REGISTRY_FETCH_TIMEOUT_SECS: u64 = 5;
pub async fn start_scheduler(agent: &ComplianceAgent) -> Result<(), AgentError> {
let sched = JobScheduler::new()
.await
@@ -31,14 +18,7 @@ pub async fn start_scheduler(agent: &ComplianceAgent) -> Result<(), AgentError>
let agent = scan_agent.clone();
Box::pin(async move {
tracing::info!("Scheduled scan triggered");
let tenants = scheduler_tenants(&agent).await;
tracing::debug!(
tenant_count = tenants.len(),
"Scheduled scan: tenants resolved"
);
for tenant_id in tenants {
scan_all_repos(&agent, &tenant_id).await;
}
scan_all_repos(&agent).await;
})
})
.map_err(|e| AgentError::Scheduler(format!("Failed to create scan job: {e}")))?;
@@ -54,14 +34,7 @@ pub async fn start_scheduler(agent: &ComplianceAgent) -> Result<(), AgentError>
let agent = cve_agent.clone();
Box::pin(async move {
tracing::info!("CVE monitor triggered");
let tenants = scheduler_tenants(&agent).await;
tracing::debug!(
tenant_count = tenants.len(),
"CVE monitor: tenants resolved"
);
for tenant_id in tenants {
monitor_cves(&agent, &tenant_id).await;
}
monitor_cves(&agent).await;
})
})
.map_err(|e| AgentError::Scheduler(format!("Failed to create CVE monitor job: {e}")))?;
@@ -75,14 +48,8 @@ pub async fn start_scheduler(agent: &ComplianceAgent) -> Result<(), AgentError>
.await
.map_err(|e| AgentError::Scheduler(format!("Failed to start scheduler: {e}")))?;
let tenants = scheduler_tenants(agent).await;
let source = if agent.config.tenant_registry_url.is_some() {
"tenant-registry (env fallback)"
} else {
"env (SCHEDULER_TENANT_IDS)"
};
tracing::info!(
"Scheduler started: scans='{}', CVE monitor='{}', tenant source={source}, tenants={tenants:?}",
"Scheduler started: scans='{}', CVE monitor='{}'",
agent.config.scan_schedule,
agent.config.cve_monitor_schedule,
);
@@ -93,251 +60,48 @@ pub async fn start_scheduler(agent: &ComplianceAgent) -> Result<(), AgentError>
}
}
/// Tenants the scheduler iterates each tick.
///
/// Resolution order:
/// 1. **Tenant registry** at `agent.config.tenant_registry_url`
/// (`GET /v1/tenants`). Fresh on every tick — picks up newly
/// provisioned tenants without an agent restart.
/// 2. **`SCHEDULER_TENANT_IDS`** env (comma-separated) — fallback when
/// the registry is unreachable, the response is malformed, or no
/// registry URL is configured.
/// 3. **`DEFAULT_SCHEDULER_TENANT_ID`** (`"dev"`) — last-ditch fallback
/// so the scheduler keeps doing something useful in dev.
///
/// We never panic out of this function — the scheduler must keep
/// firing even if the registry is offline.
async fn scheduler_tenants(agent: &ComplianceAgent) -> Vec<String> {
if let Some(url) = agent.config.tenant_registry_url.as_deref() {
match fetch_tenants_from_registry(&agent.http, url).await {
Ok(v) if !v.is_empty() => return v,
Ok(_) => {
tracing::warn!("tenant-registry returned empty list; falling back to env");
}
Err(e) => {
tracing::warn!(
url = %url,
error = %e,
"tenant-registry fetch failed; falling back to env"
);
}
}
}
tenants_from_env()
}
fn tenants_from_env() -> Vec<String> {
std::env::var("SCHEDULER_TENANT_IDS")
.ok()
.map(|s| {
s.split(',')
.map(str::trim)
.filter(|s| !s.is_empty())
.map(String::from)
.collect::<Vec<_>>()
})
.filter(|v| !v.is_empty())
.unwrap_or_else(|| vec![DEFAULT_SCHEDULER_TENANT_ID.to_string()])
}
/// Shape we accept from the registry. Liberal in what we accept:
/// the registry can return any field shape as long as either `id` or
/// `tenant_id` is present. Other fields are ignored.
#[derive(serde::Deserialize)]
struct RegistryTenant {
#[serde(alias = "tenant_id")]
id: String,
/// Filter out non-running tenants if status is present. Missing
/// status defaults to "active" so older registry deployments keep
/// working.
#[serde(default = "default_status")]
status: String,
}
fn default_status() -> String {
"active".to_string()
}
#[derive(serde::Deserialize)]
struct RegistryListResponse {
data: Vec<RegistryTenant>,
}
async fn fetch_tenants_from_registry(
http: &reqwest::Client,
base_url: &str,
) -> Result<Vec<String>, String> {
let url = format!("{}/v1/tenants", base_url.trim_end_matches('/'));
let resp = http
.get(&url)
.timeout(std::time::Duration::from_secs(REGISTRY_FETCH_TIMEOUT_SECS))
.send()
.await
.map_err(|e| format!("request failed: {e}"))?;
if !resp.status().is_success() {
return Err(format!("registry returned {}", resp.status()));
}
let body: RegistryListResponse = resp
.json()
.await
.map_err(|e| format!("invalid JSON: {e}"))?;
Ok(filter_active(body.data))
}
/// Frozen/Archived tenants don't need scheduled scans; the M7.1
/// status gate would 402/410 anyway. Skip them so we don't waste
/// cycles. Active / trial / demo / anything-else-unknown all run.
fn filter_active(rows: Vec<RegistryTenant>) -> Vec<String> {
rows.into_iter()
.filter(|t| !matches!(t.status.as_str(), "frozen" | "archived"))
.map(|t| t.id)
.collect()
}
#[cfg(test)]
mod tests {
use super::*;
fn tenant(id: &str, status: &str) -> RegistryTenant {
RegistryTenant {
id: id.to_string(),
status: status.to_string(),
}
}
#[test]
fn filter_active_keeps_running_skips_frozen_archived() {
let rows = vec![
tenant("a", "active"),
tenant("b", "trial"),
tenant("c", "demo"),
tenant("d", "frozen"),
tenant("e", "archived"),
tenant("f", "weird-but-not-known-dead"),
];
let out = filter_active(rows);
assert_eq!(out, vec!["a", "b", "c", "f"]);
}
#[test]
fn deserialize_registry_response_accepts_id_or_tenant_id() {
let body = r#"{"data":[
{"id":"a","status":"active"},
{"tenant_id":"b","status":"trial"},
{"id":"c"}
]}"#;
let parsed: RegistryListResponse = serde_json::from_str(body).unwrap();
assert_eq!(parsed.data.len(), 3);
assert_eq!(parsed.data[0].id, "a");
assert_eq!(parsed.data[1].id, "b");
assert_eq!(parsed.data[2].id, "c");
// Default status for the third entry should be "active"
assert_eq!(parsed.data[2].status, "active");
}
/// Combined into a single test: cargo runs tests in parallel and
/// env vars are process-global, so two separate tests touching
/// `SCHEDULER_TENANT_IDS` race each other. Doing both checks in
/// one test keeps them in a deterministic order.
#[test]
fn tenants_from_env_resolution() {
std::env::remove_var("SCHEDULER_TENANT_IDS");
assert_eq!(
tenants_from_env(),
vec![DEFAULT_SCHEDULER_TENANT_ID.to_string()],
"unset → default"
);
std::env::set_var("SCHEDULER_TENANT_IDS", "acme, globex ,,hello");
let out = tenants_from_env();
std::env::remove_var("SCHEDULER_TENANT_IDS");
assert_eq!(
out,
vec!["acme", "globex", "hello"],
"splits + trims + drops empty"
);
std::env::set_var("SCHEDULER_TENANT_IDS", "");
let out = tenants_from_env();
std::env::remove_var("SCHEDULER_TENANT_IDS");
assert_eq!(
out,
vec![DEFAULT_SCHEDULER_TENANT_ID.to_string()],
"empty → default"
);
}
}
/// Resolve the per-tenant database. Logs and returns `None` on failure
/// so the loop in the caller can continue with other tenants.
async fn tenant_db(agent: &ComplianceAgent, tenant_id: &str) -> Option<Database> {
match agent.db_pool.for_tenant_id(tenant_id).await {
Ok(db) => Some(db),
Err(e) => {
tracing::error!("Scheduler: cannot open tenant database '{tenant_id}': {e}");
None
}
}
}
async fn scan_all_repos(agent: &ComplianceAgent, tenant_id: &str) {
async fn scan_all_repos(agent: &ComplianceAgent) {
use futures_util::StreamExt;
let db = match tenant_db(agent, tenant_id).await {
Some(db) => db,
None => return,
};
let cursor = match db.onboarded_targets().find(doc! {}).await {
let cursor = match agent.db.repositories().find(doc! {}).await {
Ok(c) => c,
Err(e) => {
tracing::error!("Failed to list targets for tenant '{tenant_id}': {e}");
tracing::error!("Failed to list repos for scheduled scan: {e}");
return;
}
};
let targets: Vec<_> = cursor.filter_map(|r| async { r.ok() }).collect().await;
let repos: Vec<_> = cursor.filter_map(|r| async { r.ok() }).collect().await;
for target in targets {
let target_id = target.id.map(|id| id.to_hex()).unwrap_or_default();
if let Err(e) = agent
.run_target_scan(tenant_id, &target_id, ScanTrigger::Scheduled)
.await
{
tracing::error!(
"Scheduled scan failed for {} (tenant '{tenant_id}'): {e}",
target.name
);
for repo in repos {
let repo_id = repo.id.map(|id| id.to_hex()).unwrap_or_default();
if let Err(e) = agent.run_scan(&repo_id, ScanTrigger::Scheduled).await {
tracing::error!("Scheduled scan failed for {}: {e}", repo.name);
}
}
}
async fn monitor_cves(agent: &ComplianceAgent, tenant_id: &str) {
async fn monitor_cves(agent: &ComplianceAgent) {
use compliance_core::models::notification::{parse_severity, CveNotification};
use compliance_core::models::SbomEntry;
use futures_util::StreamExt;
let db = match tenant_db(agent, tenant_id).await {
Some(db) => db,
None => return,
};
// Fetch all SBOM entries grouped by repo
let cursor = match db.sbom_entries().find(doc! {}).await {
let cursor = match agent.db.sbom_entries().find(doc! {}).await {
Ok(c) => c,
Err(e) => {
tracing::error!("CVE monitor: failed to list SBOM entries for '{tenant_id}': {e}");
tracing::error!("CVE monitor: failed to list SBOM entries: {e}");
return;
}
};
let entries: Vec<SbomEntry> = cursor.filter_map(|r| async { r.ok() }).collect().await;
if entries.is_empty() {
tracing::debug!("CVE monitor: no SBOM entries for tenant '{tenant_id}', skipping");
tracing::debug!("CVE monitor: no SBOM entries, skipping");
return;
}
tracing::info!(
"CVE monitor: checking {} dependencies for new CVEs (tenant '{tenant_id}')",
"CVE monitor: checking {} dependencies for new CVEs",
entries.len()
);
@@ -348,7 +112,7 @@ 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.onboarded_targets().find_one(doc! { "_id": oid }).await {
if let Ok(Some(repo)) = agent.db.repositories().find_one(doc! { "_id": oid }).await {
repo_names.insert(rid.clone(), repo.name.clone());
}
}
@@ -396,7 +160,8 @@ async fn monitor_cves(agent: &ComplianceAgent, tenant_id: &str) {
for alert in &alerts {
let filter = doc! { "cve_id": &alert.cve_id, "repo_id": &alert.repo_id };
let update = doc! { "$setOnInsert": mongodb::bson::to_bson(alert).unwrap_or_default() };
let _ = db
let _ = agent
.db
.cve_alerts()
.update_one(filter, update)
.upsert(true)
@@ -409,7 +174,8 @@ async fn monitor_cves(agent: &ComplianceAgent, tenant_id: &str) {
continue;
}
if let Some(entry_id) = &entry.id {
let _ = db
let _ = agent
.db
.sbom_entries()
.update_one(
doc! { "_id": entry_id },
@@ -447,7 +213,8 @@ async fn monitor_cves(agent: &ComplianceAgent, tenant_id: &str) {
let update = doc! {
"$setOnInsert": mongodb::bson::to_bson(&notification).unwrap_or_default()
};
match db
match agent
.db
.cve_notifications()
.update_one(filter, update)
.upsert(true)
@@ -465,10 +232,8 @@ async fn monitor_cves(agent: &ComplianceAgent, tenant_id: &str) {
}
if new_notifications > 0 {
tracing::info!(
"CVE monitor: created {new_notifications} new notification(s) for tenant '{tenant_id}'"
);
tracing::info!("CVE monitor: created {new_notifications} new notification(s)");
} else {
tracing::info!("CVE monitor: no new CVEs found for tenant '{tenant_id}'");
tracing::info!("CVE monitor: no new CVEs found");
}
}
+10 -24
View File
@@ -14,30 +14,24 @@ type HmacSha256 = Hmac<Sha256>;
pub async fn handle_gitea_webhook(
Extension(agent): Extension<Arc<ComplianceAgent>>,
Path((tenant_id, repo_id)): Path<(String, String)>,
Path(repo_id): Path<String>,
headers: HeaderMap,
body: Bytes,
) -> StatusCode {
// Look up the repo in the tenant's database to get its webhook secret
// Look up the repo to get its webhook secret
let oid = match mongodb::bson::oid::ObjectId::parse_str(&repo_id) {
Ok(oid) => oid,
Err(_) => return StatusCode::NOT_FOUND,
};
let db = match agent.db_pool.for_tenant_id(&tenant_id).await {
Ok(db) => db,
Err(e) => {
tracing::warn!("Gitea webhook: cannot open tenant database '{tenant_id}': {e}");
return StatusCode::NOT_FOUND;
}
};
let repo = match db
.onboarded_targets()
let repo = match agent
.db
.repositories()
.find_one(mongodb::bson::doc! { "_id": oid })
.await
{
Ok(Some(repo)) => repo,
_ => {
tracing::warn!("Gitea webhook: repo {repo_id} not found in tenant '{tenant_id}'");
tracing::warn!("Gitea webhook: repo {repo_id} not found");
return StatusCode::NOT_FOUND;
}
};
@@ -72,21 +66,15 @@ pub async fn handle_gitea_webhook(
"push" => {
let agent_clone = (*agent).clone();
let repo_id = repo_id.clone();
let tenant_id = tenant_id.clone();
tokio::spawn(async move {
tracing::info!(
"Gitea push webhook: triggering scan for {repo_id} in tenant {tenant_id}"
);
if let Err(e) = agent_clone
.run_scan(&tenant_id, &repo_id, ScanTrigger::Webhook)
.await
{
tracing::info!("Gitea push webhook: triggering scan for {repo_id}");
if let Err(e) = agent_clone.run_scan(&repo_id, ScanTrigger::Webhook).await {
tracing::error!("Webhook-triggered scan failed: {e}");
}
});
StatusCode::OK
}
"pull_request" => handle_pull_request(agent, &tenant_id, &repo_id, &payload).await,
"pull_request" => handle_pull_request(agent, &repo_id, &payload).await,
_ => {
tracing::debug!("Gitea webhook: ignoring event '{event}'");
StatusCode::OK
@@ -96,7 +84,6 @@ pub async fn handle_gitea_webhook(
async fn handle_pull_request(
agent: Arc<ComplianceAgent>,
tenant_id: &str,
repo_id: &str,
payload: &serde_json::Value,
) -> StatusCode {
@@ -119,14 +106,13 @@ async fn handle_pull_request(
}
let repo_id = repo_id.to_string();
let tenant_id = tenant_id.to_string();
let head_sha = head_sha.to_string();
let base_sha = base_sha.to_string();
let agent_clone = (*agent).clone();
tokio::spawn(async move {
tracing::info!("Gitea PR webhook: reviewing PR #{pr_number} on {repo_id}");
if let Err(e) = agent_clone
.run_pr_review(&tenant_id, &repo_id, pr_number, &base_sha, &head_sha)
.run_pr_review(&repo_id, pr_number, &base_sha, &head_sha)
.await
{
tracing::error!("PR review failed for #{pr_number}: {e}");
+10 -24
View File
@@ -14,30 +14,24 @@ type HmacSha256 = Hmac<Sha256>;
pub async fn handle_github_webhook(
Extension(agent): Extension<Arc<ComplianceAgent>>,
Path((tenant_id, repo_id)): Path<(String, String)>,
Path(repo_id): Path<String>,
headers: HeaderMap,
body: Bytes,
) -> StatusCode {
// Look up the repo in the tenant's database to get its webhook secret
// Look up the repo to get its webhook secret
let oid = match mongodb::bson::oid::ObjectId::parse_str(&repo_id) {
Ok(oid) => oid,
Err(_) => return StatusCode::NOT_FOUND,
};
let db = match agent.db_pool.for_tenant_id(&tenant_id).await {
Ok(db) => db,
Err(e) => {
tracing::warn!("GitHub webhook: cannot open tenant database '{tenant_id}': {e}");
return StatusCode::NOT_FOUND;
}
};
let repo = match db
.onboarded_targets()
let repo = match agent
.db
.repositories()
.find_one(mongodb::bson::doc! { "_id": oid })
.await
{
Ok(Some(repo)) => repo,
_ => {
tracing::warn!("GitHub webhook: repo {repo_id} not found in tenant '{tenant_id}'");
tracing::warn!("GitHub webhook: repo {repo_id} not found");
return StatusCode::NOT_FOUND;
}
};
@@ -72,21 +66,15 @@ pub async fn handle_github_webhook(
"push" => {
let agent_clone = (*agent).clone();
let repo_id = repo_id.clone();
let tenant_id = tenant_id.clone();
tokio::spawn(async move {
tracing::info!(
"GitHub push webhook: triggering scan for {repo_id} in tenant {tenant_id}"
);
if let Err(e) = agent_clone
.run_scan(&tenant_id, &repo_id, ScanTrigger::Webhook)
.await
{
tracing::info!("GitHub push webhook: triggering scan for {repo_id}");
if let Err(e) = agent_clone.run_scan(&repo_id, ScanTrigger::Webhook).await {
tracing::error!("Webhook-triggered scan failed: {e}");
}
});
StatusCode::OK
}
"pull_request" => handle_pull_request(agent, &tenant_id, &repo_id, &payload).await,
"pull_request" => handle_pull_request(agent, &repo_id, &payload).await,
_ => {
tracing::debug!("GitHub webhook: ignoring event '{event}'");
StatusCode::OK
@@ -96,7 +84,6 @@ pub async fn handle_github_webhook(
async fn handle_pull_request(
agent: Arc<ComplianceAgent>,
tenant_id: &str,
repo_id: &str,
payload: &serde_json::Value,
) -> StatusCode {
@@ -118,14 +105,13 @@ async fn handle_pull_request(
}
let repo_id = repo_id.to_string();
let tenant_id = tenant_id.to_string();
let head_sha = head_sha.to_string();
let base_sha = base_sha.to_string();
let agent_clone = (*agent).clone();
tokio::spawn(async move {
tracing::info!("GitHub PR webhook: reviewing PR #{pr_number} on {repo_id}");
if let Err(e) = agent_clone
.run_pr_review(&tenant_id, &repo_id, pr_number, &base_sha, &head_sha)
.run_pr_review(&repo_id, pr_number, &base_sha, &head_sha)
.await
{
tracing::error!("PR review failed for #{pr_number}: {e}");
+10 -24
View File
@@ -10,30 +10,24 @@ use crate::agent::ComplianceAgent;
pub async fn handle_gitlab_webhook(
Extension(agent): Extension<Arc<ComplianceAgent>>,
Path((tenant_id, repo_id)): Path<(String, String)>,
Path(repo_id): Path<String>,
headers: HeaderMap,
body: Bytes,
) -> StatusCode {
// Look up the repo in the tenant's database to get its webhook secret
// Look up the repo to get its webhook secret
let oid = match mongodb::bson::oid::ObjectId::parse_str(&repo_id) {
Ok(oid) => oid,
Err(_) => return StatusCode::NOT_FOUND,
};
let db = match agent.db_pool.for_tenant_id(&tenant_id).await {
Ok(db) => db,
Err(e) => {
tracing::warn!("GitLab webhook: cannot open tenant database '{tenant_id}': {e}");
return StatusCode::NOT_FOUND;
}
};
let repo = match db
.onboarded_targets()
let repo = match agent
.db
.repositories()
.find_one(mongodb::bson::doc! { "_id": oid })
.await
{
Ok(Some(repo)) => repo,
_ => {
tracing::warn!("GitLab webhook: repo {repo_id} not found in tenant '{tenant_id}'");
tracing::warn!("GitLab webhook: repo {repo_id} not found");
return StatusCode::NOT_FOUND;
}
};
@@ -65,21 +59,15 @@ pub async fn handle_gitlab_webhook(
"push" => {
let agent_clone = (*agent).clone();
let repo_id = repo_id.clone();
let tenant_id = tenant_id.clone();
tokio::spawn(async move {
tracing::info!(
"GitLab push webhook: triggering scan for {repo_id} in tenant {tenant_id}"
);
if let Err(e) = agent_clone
.run_scan(&tenant_id, &repo_id, ScanTrigger::Webhook)
.await
{
tracing::info!("GitLab push webhook: triggering scan for {repo_id}");
if let Err(e) = agent_clone.run_scan(&repo_id, ScanTrigger::Webhook).await {
tracing::error!("Webhook-triggered scan failed: {e}");
}
});
StatusCode::OK
}
"merge_request" => handle_merge_request(agent, &tenant_id, &repo_id, &payload).await,
"merge_request" => handle_merge_request(agent, &repo_id, &payload).await,
_ => {
tracing::debug!("GitLab webhook: ignoring event '{event_type}'");
StatusCode::OK
@@ -89,7 +77,6 @@ pub async fn handle_gitlab_webhook(
async fn handle_merge_request(
agent: Arc<ComplianceAgent>,
tenant_id: &str,
repo_id: &str,
payload: &serde_json::Value,
) -> StatusCode {
@@ -114,14 +101,13 @@ async fn handle_merge_request(
}
let repo_id = repo_id.to_string();
let tenant_id = tenant_id.to_string();
let head_sha = head_sha.to_string();
let base_sha = base_sha.to_string();
let agent_clone = (*agent).clone();
tokio::spawn(async move {
tracing::info!("GitLab MR webhook: reviewing MR !{mr_iid} on {repo_id}");
if let Err(e) = agent_clone
.run_pr_review(&tenant_id, &repo_id, mr_iid, &base_sha, &head_sha)
.run_pr_review(&repo_id, mr_iid, &base_sha, &head_sha)
.await
{
tracing::error!("MR review failed for !{mr_iid}: {e}");
+4 -8
View File
@@ -9,21 +9,17 @@ use crate::webhooks::{gitea, github, gitlab};
pub async fn start_webhook_server(agent: &ComplianceAgent) -> Result<(), AgentError> {
let app = Router::new()
// Per-tenant per-repo webhook URLs: /webhook/{tenant_id}/{platform}/{repo_id}
// The tenant_id is resolved from the URL path because webhooks
// arrive without a JWT — they're authenticated via per-repo HMAC,
// not via the tenant gate. The dashboard surfaces the full URL
// including the tenant_id when the repo is registered.
// Per-repo webhook URLs: /webhook/{platform}/{repo_id}
.route(
"/webhook/{tenant_id}/github/{repo_id}",
"/webhook/github/{repo_id}",
post(github::handle_github_webhook),
)
.route(
"/webhook/{tenant_id}/gitlab/{repo_id}",
"/webhook/gitlab/{repo_id}",
post(gitlab::handle_gitlab_webhook),
)
.route(
"/webhook/{tenant_id}/gitea/{repo_id}",
"/webhook/gitea/{repo_id}",
post(gitea::handle_gitea_webhook),
)
.layer(Extension(Arc::new(agent.clone())));
+10 -26
View File
@@ -7,7 +7,7 @@ use std::sync::Arc;
use compliance_agent::agent::ComplianceAgent;
use compliance_agent::api;
use compliance_agent::database::DatabasePool;
use compliance_agent::database::Database;
use compliance_core::AgentConfig;
use secrecy::SecretString;
@@ -25,13 +25,13 @@ impl TestServer {
let mongodb_uri = std::env::var("TEST_MONGODB_URI")
.unwrap_or_else(|_| "mongodb://root:example@localhost:27017/?authSource=admin".into());
// Unique db-name prefix per run. Must fit the pool's 30-char cap
// (`<prefix>_<32 hex>` <= 63), so use a 16-hex-char suffix.
let db_name = format!("t_{}", &uuid::Uuid::new_v4().simple().to_string()[..16]);
// Unique database name per test run to avoid collisions
let db_name = format!("test_{}", uuid::Uuid::new_v4().simple());
let db_pool = DatabasePool::connect(&mongodb_uri, &db_name)
let db = Database::connect(&mongodb_uri, &db_name)
.await
.expect("Failed to build DatabasePool");
.expect("Failed to connect to MongoDB — is it running?");
db.ensure_indexes().await.expect("Failed to create indexes");
let config = AgentConfig {
mongodb_uri: mongodb_uri.clone(),
@@ -45,7 +45,6 @@ impl TestServer {
scan_schedule: String::new(),
cve_monitor_schedule: String::new(),
git_clone_base_path: "/tmp/compliance-scanner-tests/repos".into(),
artifact_store_base_path: "/tmp/compliance-scanner-tests/artifacts".into(),
ssh_key_path: "/tmp/compliance-scanner-tests/ssh/id_ed25519".into(),
github_token: None,
github_webhook_secret: None,
@@ -68,19 +67,13 @@ impl TestServer {
pentest_imap_tls: false,
pentest_imap_username: None,
pentest_imap_password: None,
admin_api_token: None,
tenant_registry_url: None,
};
let agent = ComplianceAgent::new(config, db_pool);
let agent = ComplianceAgent::new(config, db);
// Build the router with the agent extension. After M7.2-B every
// handler takes a TenantCtx extractor; without KC in the test
// harness, the dev-tenant injector mounts a synthetic context so
// tests run end-to-end against `<db_name>_dev`.
// Build the router with the agent extension
let app = api::routes::build_router()
.layer(axum::extract::Extension(Arc::new(agent)))
.layer(axum::middleware::from_fn(api::server::inject_dev_tenant))
.layer(tower_http::cors::CorsLayer::permissive());
// Bind to port 0 to get a random available port
@@ -163,19 +156,10 @@ impl TestServer {
&self.db_name
}
/// Drop every per-tenant database belonging to this test run.
/// Post-M7.2-D the agent never opens a `db_name` directly —
/// data lives only in `<db_name>_<tenant>` per-tenant databases.
/// Drop the test database on cleanup
pub async fn cleanup(&self) {
if let Ok(client) = mongodb::Client::with_uri_str(&self.mongodb_uri).await {
if let Ok(names) = client.list_database_names().await {
let prefix = format!("{}_", self.db_name);
for name in names {
if name.starts_with(&prefix) {
client.database(&name).drop().await.ok();
}
}
}
client.database(&self.db_name).drop().await.ok();
}
}
}
@@ -113,16 +113,15 @@ async fn delete_repo_cascades_to_dast_and_pentest_data() {
// Create a repo
let resp = server
.post(
"/api/v1/targets",
"/api/v1/repositories",
&json!({
"name": "cascade-test",
"target_type": "web_app",
"artifacts": [{ "kind": "git_repo", "source_ref": "https://github.com/example/cascade-test.git", "branch": "main" }],
"git_url": "https://github.com/example/cascade-test.git",
}),
)
.await;
let body: serde_json::Value = resp.json().await.unwrap();
let repo_id = body["data"]["_id"]["$oid"].as_str().unwrap().to_string();
let repo_id = body["data"]["id"].as_str().unwrap().to_string();
// Insert DAST target linked to repo
let target_id = insert_dast_target(&server, &repo_id, "cascade-target").await;
@@ -141,7 +140,9 @@ async fn delete_repo_cascades_to_dast_and_pentest_data() {
assert_eq!(count_docs(&server, "dast_findings").await, 1);
// Delete the repo
let resp = server.delete(&format!("/api/v1/targets/{repo_id}")).await;
let resp = server
.delete(&format!("/api/v1/repositories/{repo_id}"))
.await;
assert_eq!(resp.status(), 200);
// All downstream data should be gone
@@ -160,16 +161,15 @@ async fn delete_repo_cascades_sast_findings_and_sbom() {
// Create a repo
let resp = server
.post(
"/api/v1/targets",
"/api/v1/repositories",
&json!({
"name": "sast-cascade",
"target_type": "web_app",
"artifacts": [{ "kind": "git_repo", "source_ref": "https://github.com/example/sast-cascade.git", "branch": "main" }],
"git_url": "https://github.com/example/sast-cascade.git",
}),
)
.await;
let body: serde_json::Value = resp.json().await.unwrap();
let repo_id = body["data"]["_id"]["$oid"].as_str().unwrap().to_string();
let repo_id = body["data"]["id"].as_str().unwrap().to_string();
// Insert SAST finding and SBOM entry
let mongodb_uri = std::env::var("TEST_MONGODB_URI")
@@ -209,7 +209,9 @@ 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/targets/{repo_id}")).await;
server
.delete(&format!("/api/v1/repositories/{repo_id}"))
.await;
// Both should be gone
assert_eq!(count_docs(&server, "findings").await, 0);
@@ -2,5 +2,5 @@ mod cascade_delete;
mod dast;
mod findings;
mod health;
mod onboarding;
mod repositories;
mod stats;
@@ -1,115 +0,0 @@
use crate::common::TestServer;
use serde_json::json;
#[tokio::test]
async fn create_list_and_applicable_scans() {
let server = TestServer::start().await;
// Initially empty.
let resp = server.get("/api/v1/targets").await;
assert_eq!(resp.status(), 200);
let body: serde_json::Value = resp.json().await.unwrap();
assert_eq!(body["data"].as_array().unwrap().len(), 0);
// Create a web-app target with a git repo + a live URL.
let resp = server
.post(
"/api/v1/targets",
&json!({
"name": "acme-web",
"target_type": "web_app",
"artifacts": [
{ "kind": "git_repo", "source_ref": "https://git/acme.git", "branch": "main" },
{ "kind": "live_url", "source_ref": "https://acme.example.com" }
]
}),
)
.await;
assert_eq!(resp.status(), 200);
let body: serde_json::Value = resp.json().await.unwrap();
let id = body["data"]["_id"]["$oid"].as_str().unwrap().to_string();
assert!(!id.is_empty());
assert_eq!(body["data"]["artifacts"].as_array().unwrap().len(), 2);
// List returns it.
let resp = server.get("/api/v1/targets").await;
let body: serde_json::Value = resp.json().await.unwrap();
assert_eq!(body["data"].as_array().unwrap().len(), 1);
// Applicable scans: SAST present + DAST offered (live URL present), pentest supported.
let resp = server
.get(&format!("/api/v1/targets/{id}/applicable-scans"))
.await;
assert_eq!(resp.status(), 200);
let body: serde_json::Value = resp.json().await.unwrap();
let scans = body["data"]["scans"].as_array().unwrap();
let names: Vec<&str> = scans.iter().filter_map(|s| s["scan"].as_str()).collect();
assert!(names.contains(&"sast"));
assert!(names.contains(&"dast"));
assert_eq!(body["data"]["pentest_supported"], true);
server.cleanup().await;
}
#[tokio::test]
async fn detect_classifies_a_plc_target() {
let server = TestServer::start().await;
// A PLC project artifact is a strong kind-based signal.
let resp = server
.post(
"/api/v1/targets",
&json!({
"name": "line-controller",
"target_type": "backend_service", // deliberately wrong; detect should suggest PLC
"artifacts": [
{ "kind": "plc_project", "source_ref": "line.xml", "plc_format": "plcopen_xml" }
]
}),
)
.await;
let body: serde_json::Value = resp.json().await.unwrap();
let id = body["data"]["_id"]["$oid"].as_str().unwrap().to_string();
let resp = server
.post(&format!("/api/v1/targets/{id}/detect"), &json!({}))
.await;
assert_eq!(resp.status(), 200);
let body: serde_json::Value = resp.json().await.unwrap();
assert_eq!(body["data"]["classification"]["suggested"], "plc_sps");
server.cleanup().await;
}
#[tokio::test]
async fn add_artifact_and_delete_target() {
let server = TestServer::start().await;
let resp = server
.post(
"/api/v1/targets",
&json!({ "name": "svc", "target_type": "backend_service" }),
)
.await;
let body: serde_json::Value = resp.json().await.unwrap();
let id = body["data"]["_id"]["$oid"].as_str().unwrap().to_string();
// Attach a git repo.
let resp = server
.post(
&format!("/api/v1/targets/{id}/artifacts"),
&json!({ "kind": "git_repo", "source_ref": "https://git/svc.git" }),
)
.await;
assert_eq!(resp.status(), 200);
let body: serde_json::Value = resp.json().await.unwrap();
assert_eq!(body["data"]["artifacts"].as_array().unwrap().len(), 1);
// Delete it.
let resp = server.delete(&format!("/api/v1/targets/{id}")).await;
assert_eq!(resp.status(), 200);
let resp = server.get(&format!("/api/v1/targets/{id}")).await;
assert_eq!(resp.status(), 404);
server.cleanup().await;
}
@@ -0,0 +1,110 @@
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;
}
@@ -5,14 +5,13 @@ use serde_json::json;
async fn stats_overview_reflects_inserted_data() {
let server = TestServer::start().await;
// Add a target
// Add a repo
server
.post(
"/api/v1/targets",
"/api/v1/repositories",
&json!({
"name": "stats-repo",
"target_type": "web_app",
"artifacts": [{ "kind": "git_repo", "source_ref": "https://github.com/example/stats-repo.git", "branch": "main" }],
"git_url": "https://github.com/example/stats-repo.git",
}),
)
.await;
-283
View File
@@ -1,283 +0,0 @@
//! M7.2-A — `DatabasePool` isolation proof.
//!
//! Two `TenantContext`s, two databases, one client. Insert on A, query
//! on B → empty. Insert on B, query on A → only A's docs. Proves that
//! the per-tenant database split actually isolates at the driver level
//! and not at "we hope we filter."
//!
//! Requires MongoDB. Set `TEST_MONGODB_URI` to override the default
//! `mongodb://root:example@localhost:27017/?authSource=admin`.
#![allow(clippy::expect_used, clippy::unwrap_used)]
use compliance_agent::database::DatabasePool;
use compliance_core::models::{Artifact, OnboardedTarget, TargetType};
use compliance_core::{OrgRole, TenantContext, TenantStatus};
use mongodb::bson::doc;
fn ctx(tenant_id: &str, slug: &str) -> TenantContext {
TenantContext {
tenant_id: tenant_id.to_string(),
tenant_slug: slug.to_string(),
org_roles: vec![OrgRole::ItAdmin],
products: vec!["compliance-scanner".to_string()],
plan: "starter".to_string(),
status: TenantStatus::Active,
user_id: "u-1".to_string(),
user_name: None,
}
}
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]
async fn pool_isolates_tenants_at_driver_level() {
let uri = std::env::var("TEST_MONGODB_URI")
.unwrap_or_else(|_| "mongodb://root:example@localhost:27017/?authSource=admin".into());
// Unique per run so parallel test invocations don't collide. Kept
// short because Mongo caps db names at 63 bytes (prefix + tenant_id).
let prefix = format!("m72a_{}", short_id());
let pool = DatabasePool::connect(&uri, &prefix)
.await
.expect("Failed to connect to MongoDB — is it running?");
let acme = ctx("00000000-0000-0000-0000-00000000acme", "acme");
let globex = ctx("00000000-0000-0000-0000-0000globex000", "globex");
let acme_db = pool.for_tenant(&acme).await.expect("acme db");
let globex_db = pool.for_tenant(&globex).await.expect("globex db");
// Write distinct repos into each tenant's database.
acme_db
.onboarded_targets()
.insert_one(fixture_repo("acme-app", "git@example.com:acme/app.git"))
.await
.expect("insert acme");
globex_db
.onboarded_targets()
.insert_one(fixture_repo(
"globex-platform",
"git@example.com:globex/platform.git",
))
.await
.expect("insert globex");
// The point of the whole exercise: acme can ONLY see acme's repo
// and globex can ONLY see globex's, with no filter doc anywhere
// because the isolation is at the database handle, not in the query.
let acme_seen = collect(&acme_db).await;
let globex_seen = collect(&globex_db).await;
assert_eq!(acme_seen.len(), 1, "acme should see exactly its own repo");
assert_eq!(acme_seen[0].name, "acme-app");
assert_eq!(
globex_seen.len(),
1,
"globex should see exactly its own repo"
);
assert_eq!(globex_seen[0].name, "globex-platform");
// Sanity: the two databases really are different by name.
let acme_db_name = pool.tenant_db_name(&acme.tenant_id);
let globex_db_name = pool.tenant_db_name(&globex.tenant_id);
assert_ne!(acme_db_name, globex_db_name);
assert!(acme_db_name.starts_with(&prefix));
// Cleanup — drop both per-tenant databases.
pool.client()
.database(&acme_db_name)
.drop()
.await
.expect("drop acme");
pool.client()
.database(&globex_db_name)
.drop()
.await
.expect("drop globex");
}
#[tokio::test]
async fn for_tenant_is_idempotent_index_creation() {
let uri = std::env::var("TEST_MONGODB_URI")
.unwrap_or_else(|_| "mongodb://root:example@localhost:27017/?authSource=admin".into());
let prefix = format!("m72a_{}", short_id());
let pool = DatabasePool::connect(&uri, &prefix).await.expect("connect");
let acme = ctx("00000000-0000-0000-0000-00000000acme", "acme");
// Second call must not fail (ensure_indexes already ran, in-memory
// marker is set, Mongo's createIndex is idempotent by name anyway).
let _ = pool.for_tenant(&acme).await.expect("first call");
let _ = pool.for_tenant(&acme).await.expect("second call");
let _ = pool.for_tenant(&acme).await.expect("third call");
// Cleanup
let db_name = pool.tenant_db_name(&acme.tenant_id);
pool.client().database(&db_name).drop().await.expect("drop");
}
#[tokio::test]
async fn tenant_db_name_sanitizes_unsafe_characters() {
let uri = std::env::var("TEST_MONGODB_URI")
.unwrap_or_else(|_| "mongodb://root:example@localhost:27017/?authSource=admin".into());
let pool = DatabasePool::connect(&uri, "m72a_sanitize")
.await
.expect("connect");
// Mongo db names cannot contain `/ \ . " $ <space> NUL`. The pool
// must rewrite these without exploding on connect.
let funky = "te/n.a\\nt$id\" with spaces";
let name = pool.tenant_db_name(funky);
for c in ['/', '\\', '.', '"', '$', ' '] {
assert!(
!name.contains(c),
"sanitized db name still contains {c:?}: {name}"
);
}
}
#[tokio::test]
async fn admin_helpers_list_and_drop_tenant_dbs() {
let uri = std::env::var("TEST_MONGODB_URI")
.unwrap_or_else(|_| "mongodb://root:example@localhost:27017/?authSource=admin".into());
let prefix = format!("m72d_{}", short_id());
let pool = DatabasePool::connect(&uri, &prefix).await.expect("connect");
let acme = ctx("00000000-0000-0000-0000-00000000acme", "acme");
let globex = ctx("00000000-0000-0000-0000-0000globex000", "globex");
// Provision two tenants and write a doc into each so the databases
// actually materialize on the cluster (Mongo lazily creates 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
.onboarded_targets()
.insert_one(fixture_repo("acme-app", "git@example.com:acme/app.git"))
.await
.expect("insert acme");
globex_db
.onboarded_targets()
.insert_one(fixture_repo("globex-app", "git@example.com:globex/app.git"))
.await
.expect("insert globex");
// list_tenant_db_names sees both, filtered by prefix
let names = pool.list_tenant_db_names().await.expect("list tenants");
let acme_name = pool.tenant_db_name(&acme.tenant_id);
let globex_name = pool.tenant_db_name(&globex.tenant_id);
assert!(
names.contains(&acme_name),
"expected {acme_name} in {names:?}"
);
assert!(
names.contains(&globex_name),
"expected {globex_name} in {names:?}"
);
for name in &names {
assert!(name.starts_with(&format!("{prefix}_")));
}
// drop_tenant removes acme's DB
pool.drop_tenant(&acme.tenant_id)
.await
.expect("drop acme tenant");
let after = pool
.list_tenant_db_names()
.await
.expect("list tenants after drop");
assert!(
!after.contains(&acme_name),
"acme should be gone after drop, got {after:?}"
);
assert!(
after.contains(&globex_name),
"globex should still be present, got {after:?}"
);
// Cleanup remaining
pool.drop_tenant(&globex.tenant_id)
.await
.expect("drop globex tenant");
}
#[tokio::test]
async fn tenant_db_name_falls_back_to_hash_when_too_long() {
let uri = std::env::var("TEST_MONGODB_URI")
.unwrap_or_else(|_| "mongodb://root:example@localhost:27017/?authSource=admin".into());
let pool = DatabasePool::connect(&uri, "m72a_long")
.await
.expect("connect");
// 100-byte tenant_id would overflow the 63-byte db-name cap with
// any reasonable prefix. The pool must hash it down.
let huge = "x".repeat(100);
let name = pool.tenant_db_name(&huge);
assert!(name.len() <= 63, "hashed name should fit: {name}");
assert!(name.starts_with("m72a_long_"));
// The hash suffix is 32 hex chars (16-byte SHA-256 truncation).
let suffix = name.trim_start_matches("m72a_long_");
assert_eq!(
suffix.len(),
32,
"expected 32-hex suffix (16-byte hash), got {suffix:?}"
);
assert!(suffix.chars().all(|c| c.is_ascii_hexdigit()));
// Stable: same input → same output.
assert_eq!(name, pool.tenant_db_name(&huge));
// Different inputs → different outputs (collision check on a tiny
// sample — full birthday-resistance is a proof not a test).
let huge2 = "y".repeat(100);
assert_ne!(pool.tenant_db_name(&huge), pool.tenant_db_name(&huge2));
}
#[tokio::test]
async fn connect_rejects_overlong_db_prefix() {
let uri = std::env::var("TEST_MONGODB_URI")
.unwrap_or_else(|_| "mongodb://root:example@localhost:27017/?authSource=admin".into());
// MAX_PREFIX_LEN is 30 (= 63 - 1 - 32). A 31-char prefix MUST be
// rejected at construction so the hash-fallback path can never
// produce an over-long db name at runtime.
let too_long = "a".repeat(31);
let err = DatabasePool::connect(&uri, &too_long).await.unwrap_err();
let msg = format!("{err}");
assert!(
msg.contains("max is 30") || msg.contains(&too_long),
"error should explain the cap: {msg}"
);
// Exactly 30 chars is the inclusive bound — must succeed.
let just_right = "a".repeat(30);
let _ = DatabasePool::connect(&uri, &just_right)
.await
.expect("30-char prefix should be accepted");
}
/// Short UUID slug for keeping test prefixes well under Mongo's 63-byte
/// db-name cap.
fn short_id() -> String {
uuid::Uuid::new_v4().simple().to_string()[..8].to_string()
}
/// Drain a `repositories` find cursor on the given tenant database.
async fn collect(db: &compliance_agent::database::Database) -> Vec<OnboardedTarget> {
let mut cursor = db
.onboarded_targets()
.find(doc! {})
.await
.expect("find repositories");
let mut out = Vec::new();
while cursor.advance().await.expect("advance") {
out.push(cursor.deserialize_current().expect("deserialize"));
}
out
}
+4 -12
View File
@@ -63,24 +63,16 @@ 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/"];
/// Middleware that validates Bearer JWT tokens against Keycloak's JWKS
/// and attaches a `TenantContext` extension on success.
///
/// Skips validation for the health endpoint and any path under one of
/// the [`PUBLIC_PREFIXES`]. If `JwksState` is not present (Keycloak
/// not configured), requests pass through and downstream code must
/// handle the missing context.
/// Skips validation for the health endpoint.
/// If `JwksState` is not present (Keycloak not configured), requests
/// pass through and downstream code must handle the missing context.
pub async fn require_jwt_auth(mut request: Request, next: Next) -> Response {
let path = request.uri().path();
if PUBLIC_ENDPOINTS.contains(&path) || PUBLIC_PREFIXES.iter().any(|p| path.starts_with(p)) {
if PUBLIC_ENDPOINTS.contains(&path) {
return next.run(request).await;
}
-12
View File
@@ -24,9 +24,6 @@ pub struct AgentConfig {
pub scan_schedule: String,
pub cve_monitor_schedule: String,
pub git_clone_base_path: String,
/// Base directory for content-addressed artifact blobs and per-run working
/// dirs (`<base>/blobs/<sha[0:2]>/<sha>`, `<base>/work/<target>/<artifact>/`).
pub artifact_store_base_path: String,
pub ssh_key_path: String,
pub keycloak_url: Option<String>,
pub keycloak_realm: Option<String>,
@@ -40,15 +37,6 @@ pub struct AgentConfig {
pub pentest_imap_tls: bool,
pub pentest_imap_username: Option<String>,
pub pentest_imap_password: Option<SecretString>,
/// Static bearer for the cross-tenant admin endpoints under
/// `/api/v1/admin/*`. When `None`, those endpoints are not
/// mounted at all (defense-in-depth: ops endpoints never reach
/// any auth path if no operator has explicitly opted in).
pub admin_api_token: Option<SecretString>,
/// Live tenant-registry URL the scheduler consults for the list
/// 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>,
}
#[derive(Clone, Debug, Serialize, Deserialize)]
-1
View File
@@ -2,7 +2,6 @@ pub mod config;
pub mod db;
pub mod error;
pub mod models;
pub mod scan_matrix;
#[cfg(feature = "telemetry")]
pub mod telemetry;
pub mod tenant;
-69
View File
@@ -1,69 +0,0 @@
//! Per-tenant API tokens used by `compliance-mcp` to authenticate MCP
//! HTTP requests on behalf of LLM clients (Claude Desktop, Cursor,
//! ChatGPT, etc.) that can't run a Keycloak OIDC flow.
//!
//! Tokens are opaque strings of the form `mcpt_<44 url-safe random
//! chars>`. The raw value is shown to the user exactly once at
//! creation; the database only ever sees the SHA-256 hash. Lookups go
//! through the cross-tenant `<prefix>__admin.mcp_tokens` collection
//! and return the `tenant_id` the MCP server should route to.
use chrono::{DateTime, Utc};
use serde::{Deserialize, Serialize};
/// Persisted token metadata. `token_hash` is the SHA-256 hex of the
/// raw token; the raw token itself is never stored.
#[derive(Debug, Clone, Serialize, Deserialize)]
pub struct McpToken {
#[serde(rename = "_id", skip_serializing_if = "Option::is_none")]
pub id: Option<bson::oid::ObjectId>,
/// SHA-256 hex of the raw token. Unique index in the collection.
pub token_hash: String,
/// First 8 chars of the raw token — purely for UI display so users
/// can identify which token is which without re-issuing.
pub token_prefix: String,
/// Routes to `<db_prefix>_<tenant_id>` on MCP requests.
pub tenant_id: String,
/// User-given label, e.g. "Claude Desktop" or "Sharang's laptop".
pub name: String,
/// Keycloak `sub` of the user who created this token, for audit.
pub created_by: String,
#[serde(with = "super::serde_helpers::bson_datetime")]
pub created_at: DateTime<Utc>,
#[serde(default, with = "super::serde_helpers::opt_bson_datetime")]
pub last_used_at: Option<DateTime<Utc>>,
/// Soft-delete flag. A revoked token doc stays around for audit
/// but never authenticates.
#[serde(default)]
pub revoked: bool,
}
/// Public projection of a token — never includes the hash.
/// Returned by `GET /api/v1/mcp-tokens`.
#[derive(Debug, Clone, Serialize, Deserialize)]
pub struct McpTokenView {
pub id: String,
pub name: String,
/// `mcpt_xxxx…` so the user can identify which row is which.
pub token_prefix: String,
pub created_by: String,
#[serde(with = "super::serde_helpers::bson_datetime")]
pub created_at: DateTime<Utc>,
#[serde(default, with = "super::serde_helpers::opt_bson_datetime")]
pub last_used_at: Option<DateTime<Utc>>,
pub revoked: bool,
}
impl From<&McpToken> for McpTokenView {
fn from(t: &McpToken) -> Self {
Self {
id: t.id.map(|o| o.to_hex()).unwrap_or_default(),
name: t.name.clone(),
token_prefix: t.token_prefix.clone(),
created_by: t.created_by.clone(),
created_at: t.created_at,
last_used_at: t.last_used_at,
revoked: t.revoked,
}
}
}
+1 -10
View File
@@ -7,9 +7,7 @@ pub mod finding;
pub mod graph;
pub mod issue;
pub mod mcp;
pub mod mcp_token;
pub mod notification;
pub mod onboarding;
pub mod pentest;
pub mod repository;
pub mod sbom;
@@ -30,20 +28,13 @@ pub use graph::{
};
pub use issue::{IssueStatus, TrackerIssue, TrackerType};
pub use mcp::{McpServerConfig, McpServerStatus, McpTransport};
pub use mcp_token::{McpToken, McpTokenView};
pub use notification::{CveNotification, NotificationSeverity, NotificationStatus};
pub use onboarding::{
default_compliance_profile, Artifact, ArtifactAuth, ArtifactKind, Classification,
ComplianceFramework, ComplianceProfile, DetectedFact, ExternalRef, ExternalSystem,
GitArtifactConfig, IssueTrackerConfig, OnboardedTarget, PlcArtifactConfig, PlcFormat,
TargetScanConfig, TargetType, TargetTypeCandidate, WebArtifactConfig,
};
pub use pentest::{
AttackChainNode, AttackNodeStatus, AuthMode, CodeContextHint, Environment, IdentityProvider,
PentestAuthConfig, PentestConfig, PentestEvent, PentestMessage, PentestSession, PentestStats,
PentestStatus, PentestStrategy, SeverityDistribution, TestUserRecord, TesterInfo,
ToolCallRecord,
};
pub use repository::ScanTrigger;
pub use repository::{ScanTrigger, TrackedRepository};
pub use sbom::{SbomEntry, VulnRef};
pub use scan::{ScanPhase, ScanRun, ScanRunStatus, ScanType};
-756
View File
@@ -1,756 +0,0 @@
//! The unified onboarding model.
//!
//! An [`OnboardedTarget`] is the single source of truth for anything the scanner
//! can analyze. It records *what kind of software* the target is ([`TargetType`]),
//! the concrete [`Artifact`]s that were provided for it (a git repo, a firmware
//! image, a live URL, a PLC project, ...), the classifier's verdict, and the scan
//! configuration. It replaces the older git-only `TrackedRepository` and the
//! standalone `DastTarget`, both of which fold into this type as artifacts.
use std::collections::HashMap;
use chrono::{DateTime, Utc};
use serde::{Deserialize, Serialize};
use super::dast::{DastAuthConfig, DastTargetType};
use super::issue::TrackerType;
use super::pentest::{Environment, PentestConfig, PentestStrategy};
use super::scan::ScanType;
/// The family of software a target belongs to.
///
/// Targets look endlessly varied but fall into a small enumerable set classified
/// by where the analyzable signal lives. This drives the scan-applicability
/// matrix and the onboarding wizard's type selection.
#[derive(Debug, Clone, Copy, PartialEq, Eq, Hash, Serialize, Deserialize)]
#[serde(rename_all = "snake_case")]
pub enum TargetType {
/// Browser-facing web application (front end + server).
WebApp,
/// Headless backend service / API (REST, GraphQL, gRPC).
BackendService,
/// Desktop application (Windows/macOS/Linux GUI or CLI binary).
DesktopApp,
/// Android application (APK / AAB).
AndroidApp,
/// iOS application (IPA).
IosApp,
/// Bare-metal embedded firmware (no operating system).
FirmwareBareMetal,
/// Embedded firmware running on an RTOS (Zephyr, FreeRTOS, ...).
FirmwareRtos,
/// Embedded Linux built with Yocto / OpenEmbedded (BSP + image).
EmbeddedLinuxYocto,
/// Programmable logic controller software (IEC 61131-3, PLCopen / SPS).
PlcSps,
}
impl std::fmt::Display for TargetType {
fn fmt(&self, f: &mut std::fmt::Formatter<'_>) -> std::fmt::Result {
match self {
Self::WebApp => write!(f, "web_app"),
Self::BackendService => write!(f, "backend_service"),
Self::DesktopApp => write!(f, "desktop_app"),
Self::AndroidApp => write!(f, "android_app"),
Self::IosApp => write!(f, "ios_app"),
Self::FirmwareBareMetal => write!(f, "firmware_bare_metal"),
Self::FirmwareRtos => write!(f, "firmware_rtos"),
Self::EmbeddedLinuxYocto => write!(f, "embedded_linux_yocto"),
Self::PlcSps => write!(f, "plc_sps"),
}
}
}
/// The kind of artifact provided for a target.
///
/// Which scans are possible is a function of the target type *and* which of
/// these are present (SAST needs code, DAST needs a running URL, and so on).
#[derive(Debug, Clone, Copy, PartialEq, Eq, Serialize, Deserialize)]
#[serde(rename_all = "snake_case")]
pub enum ArtifactKind {
/// A git repository (cloned for static analysis).
GitRepo,
/// A source archive (zip / tarball) with no live git remote.
SourceArchive,
/// A firmware image or binary blob.
FirmwareImage,
/// A mobile package: Android APK/AAB or iOS IPA.
MobilePackage,
/// An OCI/Docker container image reference.
ContainerImage,
/// A reachable running instance (base URL / endpoint) for dynamic testing.
LiveUrl,
/// A PLC project: PLCopen XML or Structured Text source.
PlcProject,
/// Free-form plaintext describing the target (feeds classification only).
PlaintextDescription,
}
impl std::fmt::Display for ArtifactKind {
fn fmt(&self, f: &mut std::fmt::Formatter<'_>) -> std::fmt::Result {
match self {
Self::GitRepo => write!(f, "git_repo"),
Self::SourceArchive => write!(f, "source_archive"),
Self::FirmwareImage => write!(f, "firmware_image"),
Self::MobilePackage => write!(f, "mobile_package"),
Self::ContainerImage => write!(f, "container_image"),
Self::LiveUrl => write!(f, "live_url"),
Self::PlcProject => write!(f, "plc_project"),
Self::PlaintextDescription => write!(f, "plaintext_description"),
}
}
}
/// Credentials attached to an artifact.
///
/// This folds both `TrackedRepository`'s git auth (`auth_token` / `auth_username`
/// / SSH key) and `DastAuthConfig`'s HTTP auth (form / bearer / cookie) into one
/// shape so a single artifact carries whatever it needs to be fetched or probed.
#[derive(Debug, Clone, Default, Serialize, Deserialize)]
pub struct ArtifactAuth {
/// Auth method: `none` | `token` | `basic` | `bearer` | `cookie` | `form` | `ssh`.
#[serde(default)]
pub method: String,
/// Username (git user, basic-auth user, or `x-access-token` for PATs).
pub username: Option<String>,
/// The secret credential: PAT, password, or bearer token. Encrypted at rest.
pub secret: Option<String>,
/// Path to an SSH private key for git-over-SSH.
pub ssh_key_path: Option<String>,
/// Login URL for form-based authentication.
pub login_url: Option<String>,
/// Extra headers to send when authenticating / probing.
pub headers: Option<HashMap<String, String>>,
}
impl From<DastAuthConfig> for ArtifactAuth {
fn from(c: DastAuthConfig) -> Self {
Self {
method: c.method,
username: c.username,
// Prefer a bearer token; otherwise fall back to the password.
secret: c.token.or(c.password),
ssh_key_path: None,
login_url: c.login_url,
headers: c.headers,
}
}
}
/// Git-specific configuration for a [`ArtifactKind::GitRepo`] artifact.
#[derive(Debug, Clone, Serialize, Deserialize)]
pub struct GitArtifactConfig {
/// Branch to scan.
pub default_branch: String,
/// Commit SHA of the last completed scan (change-detection watermark).
pub last_scanned_commit: Option<String>,
/// Local clone path once the repo has been fetched.
pub local_path: Option<String>,
}
impl GitArtifactConfig {
/// Config for a fresh git artifact on the given branch.
pub fn on_branch(branch: impl Into<String>) -> Self {
Self {
default_branch: branch.into(),
last_scanned_commit: None,
local_path: None,
}
}
}
impl Default for GitArtifactConfig {
fn default() -> Self {
Self::on_branch("main")
}
}
/// Dynamic-analysis configuration for a [`ArtifactKind::LiveUrl`] artifact.
#[derive(Debug, Clone, Serialize, Deserialize)]
pub struct WebArtifactConfig {
/// Whether the endpoint is a web app, REST API, or GraphQL API.
pub target_kind: DastTargetType,
/// URL paths to exclude from crawling / scanning.
#[serde(default)]
pub excluded_paths: Vec<String>,
/// Maximum crawl depth.
pub max_crawl_depth: u32,
/// Rate limit in requests per second.
pub rate_limit: u32,
/// Whether destructive methods (DELETE / PUT) are permitted.
#[serde(default)]
pub allow_destructive: bool,
}
impl Default for WebArtifactConfig {
fn default() -> Self {
Self {
target_kind: DastTargetType::WebApp,
excluded_paths: Vec::new(),
max_crawl_depth: 3,
rate_limit: 10,
allow_destructive: false,
}
}
}
/// The source format of a PLC project artifact.
#[derive(Debug, Clone, Copy, PartialEq, Eq, Serialize, Deserialize)]
#[serde(rename_all = "snake_case")]
pub enum PlcFormat {
/// PLCopen XML project export.
PlcopenXml,
/// IEC 61131-3 Structured Text source.
StructuredText,
/// A CODESYS project archive (`.projectarchive` — a zip bundling the project
/// plus its referenced libraries and runtime; the source of the control-app SBOM).
ProjectArchive,
}
/// PLC-specific configuration for a [`ArtifactKind::PlcProject`] artifact.
#[derive(Debug, Clone, Serialize, Deserialize)]
pub struct PlcArtifactConfig {
/// The project source format.
pub format: PlcFormat,
}
/// A single fact discovered about a target by ingest or classification
/// (e.g. `language=rust`, `build_system=cmake`, `mcu=stm32f429`).
#[derive(Debug, Clone, Serialize, Deserialize)]
pub struct DetectedFact {
/// The fact name.
pub key: String,
/// The fact value.
pub value: String,
/// What produced the fact (e.g. `tramiton`, `language-fingerprint`).
pub source: String,
}
impl DetectedFact {
/// Build a fact from its parts.
pub fn new(
key: impl Into<String>,
value: impl Into<String>,
source: impl Into<String>,
) -> Self {
Self {
key: key.into(),
value: value.into(),
source: source.into(),
}
}
}
/// One concrete thing provided for a target: code, a binary, a URL, etc.
#[derive(Debug, Clone, Serialize, Deserialize)]
pub struct Artifact {
/// Stable per-artifact id (UUID v4) — scan steps reference this.
pub id: String,
/// What kind of artifact this is.
pub kind: ArtifactKind,
/// The source reference: git URL, blob id, live URL, or image ref.
pub source_ref: String,
/// Optional human-friendly label.
pub display_name: Option<String>,
/// Content-addressed storage path once ingested (blobs only).
pub stored_path: Option<String>,
/// SHA-256 of the ingested content (git artifacts store the head SHA).
pub content_hash: Option<String>,
/// Size of the stored blob in bytes.
pub size_bytes: Option<u64>,
/// Credentials for fetching or probing this artifact.
pub auth: Option<ArtifactAuth>,
/// Git configuration (present for [`ArtifactKind::GitRepo`]).
pub git: Option<GitArtifactConfig>,
/// Dynamic-analysis configuration (present for [`ArtifactKind::LiveUrl`]).
pub web: Option<WebArtifactConfig>,
/// PLC configuration (present for [`ArtifactKind::PlcProject`]).
pub plc: Option<PlcArtifactConfig>,
/// Facts discovered about this artifact by ingest / classification.
#[serde(default)]
pub detected: Vec<DetectedFact>,
/// When this artifact was last ingested.
#[serde(default, with = "super::serde_helpers::opt_bson_datetime")]
pub ingested_at: Option<DateTime<Utc>>,
}
impl Artifact {
/// A bare artifact of the given kind and source reference.
fn bare(kind: ArtifactKind, source_ref: impl Into<String>) -> Self {
Self {
id: uuid::Uuid::new_v4().to_string(),
kind,
source_ref: source_ref.into(),
display_name: None,
stored_path: None,
content_hash: None,
size_bytes: None,
auth: None,
git: None,
web: None,
plc: None,
detected: Vec::new(),
ingested_at: None,
}
}
/// A git-repository artifact tracking the given branch.
pub fn git_repo(url: impl Into<String>, branch: impl Into<String>) -> Self {
let mut a = Self::bare(ArtifactKind::GitRepo, url);
a.git = Some(GitArtifactConfig::on_branch(branch));
a
}
/// A live-URL artifact with default crawl settings.
pub fn live_url(url: impl Into<String>) -> Self {
let mut a = Self::bare(ArtifactKind::LiveUrl, url);
a.web = Some(WebArtifactConfig::default());
a
}
/// A firmware-image artifact referenced by name (blob ingested later).
pub fn firmware_image(source_ref: impl Into<String>) -> Self {
Self::bare(ArtifactKind::FirmwareImage, source_ref)
}
/// A source-archive artifact referenced by name (blob ingested later).
pub fn source_archive(source_ref: impl Into<String>) -> Self {
Self::bare(ArtifactKind::SourceArchive, source_ref)
}
/// A mobile-package artifact (APK/AAB/IPA) referenced by name.
pub fn mobile_package(source_ref: impl Into<String>) -> Self {
Self::bare(ArtifactKind::MobilePackage, source_ref)
}
/// A container-image artifact referenced by OCI ref.
pub fn container_image(source_ref: impl Into<String>) -> Self {
Self::bare(ArtifactKind::ContainerImage, source_ref)
}
/// A PLC-project artifact in the given format.
pub fn plc_project(source_ref: impl Into<String>, format: PlcFormat) -> Self {
let mut a = Self::bare(ArtifactKind::PlcProject, source_ref);
a.plc = Some(PlcArtifactConfig { format });
a
}
/// A plaintext-description artifact (classification input only).
pub fn plaintext(text: impl Into<String>) -> Self {
Self::bare(ArtifactKind::PlaintextDescription, text)
}
}
/// One ranked candidate produced by the classifier.
#[derive(Debug, Clone, Serialize, Deserialize)]
pub struct TargetTypeCandidate {
/// The candidate target type.
pub target_type: TargetType,
/// Confidence in `[0.0, 1.0]`.
pub confidence: f32,
/// Why this candidate was proposed.
pub rationale: String,
}
/// The classifier's verdict for a target: a suggested type plus ranked
/// alternatives and the facts the decision rested on.
#[derive(Debug, Clone, Serialize, Deserialize)]
pub struct Classification {
/// The top-ranked target type.
pub suggested: TargetType,
/// All candidates, sorted by descending confidence.
#[serde(default)]
pub candidates: Vec<TargetTypeCandidate>,
/// Facts gathered during classification.
#[serde(default)]
pub facts: Vec<DetectedFact>,
/// Which classifiers contributed (e.g. `["tramiton", "language-fingerprint"]`).
#[serde(default)]
pub detected_by: Vec<String>,
/// When classification ran.
#[serde(with = "super::serde_helpers::bson_datetime")]
pub detected_at: DateTime<Utc>,
/// Whether a human confirmed the suggestion.
#[serde(default)]
pub confirmed: bool,
}
/// Issue-tracker linkage, migrated from `TrackedRepository`'s `tracker_*` fields.
#[derive(Debug, Clone, Default, Serialize, Deserialize)]
pub struct IssueTrackerConfig {
/// The tracker platform.
pub tracker_type: Option<TrackerType>,
/// Tracker owner / organization.
pub owner: Option<String>,
/// Tracker repository / project.
pub repo: Option<String>,
/// Per-target tracker access token.
pub token: Option<String>,
}
/// How a target should be scanned.
///
/// `enabled_scans` / `disabled_scans` override the scan-applicability matrix
/// defaults; the pentest and tracker blocks reuse the existing wizard config.
#[derive(Debug, Clone, Default, Serialize, Deserialize)]
pub struct TargetScanConfig {
/// Scans explicitly turned on (empty means "use matrix defaults").
#[serde(default)]
pub enabled_scans: Vec<ScanType>,
/// Scans explicitly turned off.
#[serde(default)]
pub disabled_scans: Vec<ScanType>,
/// Target environment (gates destructive / active testing).
#[serde(default)]
pub environment: Environment,
/// Whether destructive tests are permitted for this target.
#[serde(default)]
pub allow_destructive: bool,
/// Pentest strategy selector.
pub strategy: Option<PentestStrategy>,
/// Full pentest wizard configuration.
pub pentest: Option<PentestConfig>,
/// Issue-tracker linkage.
pub issue_tracker: Option<IssueTrackerConfig>,
}
/// A sibling product in the company suite that may already hold authoritative
/// data for a target. compliance-scanner reconciles with these rather than
/// recomputing what they already know.
#[derive(Debug, Clone, Copy, PartialEq, Eq, Serialize, Deserialize)]
#[serde(rename_all = "snake_case")]
pub enum ExternalSystem {
/// Reproducible-build & firmware compliance engine (build plan, SBOM, VEX,
/// attestation).
Tramiton,
/// Code assistant (downstream remediation consumer).
Werkpilot,
/// Compliance-controls RAG (atomic controls derived from laws).
BreakpilotCompliance,
}
impl std::fmt::Display for ExternalSystem {
fn fmt(&self, f: &mut std::fmt::Formatter<'_>) -> std::fmt::Result {
match self {
Self::Tramiton => write!(f, "tramiton"),
Self::Werkpilot => write!(f, "werkpilot"),
Self::BreakpilotCompliance => write!(f, "breakpilot_compliance"),
}
}
}
/// A link from this target to a record in a sibling product, used to reconcile
/// existing evidence instead of recomputing it.
///
/// For tramiton, `project_id` is the shared cross-product key and
/// `subject_sha256` matches a firmware artifact's [`Artifact::content_hash`]
/// (which equals tramiton's `Artifact.sha256`).
#[derive(Debug, Clone, Serialize, Deserialize)]
pub struct ExternalRef {
/// Which sibling product this reference points at.
pub system: ExternalSystem,
/// The sibling product's project identifier, if known.
pub project_id: Option<String>,
/// Content digest of the subject artifact (firmware sha256), if known.
pub subject_sha256: Option<String>,
/// Reconciliation status: `linked` | `reconciled` | `unavailable`.
#[serde(default)]
pub status: String,
/// Opaque, offline-verifiable entitlement grant (e.g. tramiton's signed
/// `LicenseGrant`), if the tenant provided one.
pub license_grant: Option<String>,
/// When evidence was last reconciled from this system.
#[serde(default, with = "super::serde_helpers::opt_bson_datetime")]
pub last_reconciled_at: Option<DateTime<Utc>>,
}
impl ExternalRef {
/// A freshly linked (not yet reconciled) reference to a sibling system.
pub fn linked(system: ExternalSystem) -> Self {
Self {
system,
project_id: None,
subject_sha256: None,
status: "linked".to_string(),
license_grant: None,
last_reconciled_at: None,
}
}
}
/// A regulatory / standards framework a target must comply with. Drives which
/// controls the mapping engine pulls from the [`crate::traits::ControlsProvider`].
#[derive(Debug, Clone, Copy, PartialEq, Eq, Serialize, Deserialize)]
#[serde(rename_all = "snake_case")]
pub enum ComplianceFramework {
/// EU Cyber Resilience Act.
Cra,
/// IEC 62443 (industrial automation & control systems security).
Iec62443,
/// EU General Data Protection Regulation.
Gdpr,
/// SOC 2.
Soc2,
/// ISO/IEC 27001.
Iso27001,
/// EU Radio Equipment Directive (RED) cybersecurity articles.
RedDirective,
}
impl std::fmt::Display for ComplianceFramework {
fn fmt(&self, f: &mut std::fmt::Formatter<'_>) -> std::fmt::Result {
match self {
Self::Cra => write!(f, "cra"),
Self::Iec62443 => write!(f, "iec_62443"),
Self::Gdpr => write!(f, "gdpr"),
Self::Soc2 => write!(f, "soc2"),
Self::Iso27001 => write!(f, "iso_27001"),
Self::RedDirective => write!(f, "red_directive"),
}
}
}
/// The compliance scope of a target: which frameworks apply and, optionally, the
/// jurisdiction. Captured at onboarding (with per-target-type defaults from
/// [`default_compliance_profile`]).
#[derive(Debug, Clone, Default, Serialize, Deserialize)]
pub struct ComplianceProfile {
/// Applicable frameworks.
#[serde(default)]
pub frameworks: Vec<ComplianceFramework>,
/// Free-form jurisdiction (e.g. `eu`, `us`, `de`).
pub jurisdiction: Option<String>,
}
/// The sensible default compliance scope for a target type. Firmware / PLC /
/// embedded default to CRA + IEC 62443; software defaults to GDPR + SOC 2.
pub fn default_compliance_profile(target_type: TargetType) -> ComplianceProfile {
use ComplianceFramework::{Cra, Gdpr, Iec62443, Soc2};
let frameworks = match target_type {
TargetType::PlcSps
| TargetType::FirmwareBareMetal
| TargetType::FirmwareRtos
| TargetType::EmbeddedLinuxYocto => vec![Cra, Iec62443],
TargetType::WebApp | TargetType::BackendService => vec![Gdpr, Soc2],
TargetType::DesktopApp | TargetType::AndroidApp | TargetType::IosApp => {
vec![Gdpr, Cra]
}
};
ComplianceProfile {
frameworks,
jurisdiction: None,
}
}
/// A target onboarded for scanning: the unified replacement for the legacy
/// `TrackedRepository` (SAST) and `DastTarget` (DAST) records.
#[derive(Debug, Clone, Serialize, Deserialize)]
pub struct OnboardedTarget {
/// Mongo id. Preserved from the legacy record during migration so every
/// downstream collection keyed by `repo_id` / `target_id` keeps resolving.
#[serde(rename = "_id", skip_serializing_if = "Option::is_none")]
pub id: Option<bson::oid::ObjectId>,
/// Human-friendly name.
#[serde(default)]
pub name: String,
/// The software family this target belongs to.
pub target_type: TargetType,
/// Optional free-form description (also a classification input).
pub description: Option<String>,
/// The artifacts provided for this target.
#[serde(default)]
pub artifacts: Vec<Artifact>,
/// The classifier's verdict, once run.
pub classification: Option<Classification>,
/// How this target should be scanned.
#[serde(default)]
pub scan_config: TargetScanConfig,
/// The compliance scope (applicable frameworks / jurisdiction).
#[serde(default)]
pub compliance_profile: ComplianceProfile,
/// Links to sibling products (tramiton, ...) holding reconcilable evidence.
#[serde(default)]
pub external_refs: Vec<ExternalRef>,
/// Cron schedule for recurring scans, if any.
pub scan_schedule: Option<String>,
/// Whether inbound webhooks are enabled for this target.
#[serde(default)]
pub webhook_enabled: bool,
/// HMAC secret for verifying inbound webhooks.
#[serde(default, skip_serializing_if = "Option::is_none")]
pub webhook_secret: Option<String>,
/// Cached count of findings across this target's scans.
#[serde(default)]
pub findings_count: u32,
/// Creation timestamp.
#[serde(
default = "chrono::Utc::now",
with = "super::serde_helpers::bson_datetime"
)]
pub created_at: DateTime<Utc>,
/// Last-update timestamp.
#[serde(
default = "chrono::Utc::now",
with = "super::serde_helpers::bson_datetime"
)]
pub updated_at: DateTime<Utc>,
}
impl OnboardedTarget {
/// A new target of the given type with a freshly generated webhook secret.
pub fn new(name: String, target_type: TargetType) -> Self {
let now = Utc::now();
let webhook_secret = uuid::Uuid::new_v4().to_string().replace('-', "");
Self {
id: None,
name,
target_type,
description: None,
artifacts: Vec::new(),
classification: None,
scan_config: TargetScanConfig::default(),
compliance_profile: default_compliance_profile(target_type),
external_refs: Vec::new(),
scan_schedule: None,
webhook_enabled: false,
webhook_secret: Some(webhook_secret),
findings_count: 0,
created_at: now,
updated_at: now,
}
}
/// The first artifact of the given kind, if present.
pub fn first_of(&self, kind: ArtifactKind) -> Option<&Artifact> {
self.artifacts.iter().find(|a| a.kind == kind)
}
/// Whether the target has at least one artifact of the given kind.
pub fn has(&self, kind: ArtifactKind) -> bool {
self.artifacts.iter().any(|a| a.kind == kind)
}
/// The primary code artifact (git repo or source archive), if any.
pub fn code_artifact(&self) -> Option<&Artifact> {
self.artifacts
.iter()
.find(|a| matches!(a.kind, ArtifactKind::GitRepo | ArtifactKind::SourceArchive))
}
/// The live-URL artifact, if any.
pub fn live_url(&self) -> Option<&Artifact> {
self.first_of(ArtifactKind::LiveUrl)
}
}
#[cfg(test)]
#[allow(clippy::expect_used, clippy::unwrap_used)]
mod tests {
use super::*;
fn sample_target() -> OnboardedTarget {
let mut t = OnboardedTarget::new("acme-web".to_string(), TargetType::WebApp);
t.artifacts.push(Artifact::git_repo(
"https://git.example.com/acme.git",
"main",
));
t.artifacts
.push(Artifact::live_url("https://acme.example.com"));
t
}
#[test]
fn onboarded_target_bson_round_trip() {
let t = sample_target();
let b = bson::to_bson(&t).expect("serialize");
let back: OnboardedTarget = bson::from_bson(b.clone()).expect("deserialize");
let b2 = bson::to_bson(&back).expect("re-serialize");
assert_eq!(b, b2);
}
#[test]
fn enum_display_is_snake_case() {
assert_eq!(
TargetType::FirmwareBareMetal.to_string(),
"firmware_bare_metal"
);
assert_eq!(TargetType::PlcSps.to_string(), "plc_sps");
assert_eq!(ArtifactKind::PlcProject.to_string(), "plc_project");
assert_eq!(ArtifactKind::MobilePackage.to_string(), "mobile_package");
}
#[test]
fn helpers_locate_artifacts() {
let t = sample_target();
assert!(t.has(ArtifactKind::GitRepo));
assert!(t.live_url().is_some());
assert!(t.code_artifact().is_some());
assert!(!t.has(ArtifactKind::FirmwareImage));
assert_eq!(
t.first_of(ArtifactKind::GitRepo).map(|a| a.kind),
Some(ArtifactKind::GitRepo)
);
}
#[test]
fn new_target_generates_webhook_secret() {
let t = OnboardedTarget::new("t".to_string(), TargetType::BackendService);
let secret = t.webhook_secret.expect("secret present");
assert_eq!(secret.len(), 32);
assert!(!secret.contains('-'));
}
#[test]
fn dast_auth_folds_into_artifact_auth() {
let dast = DastAuthConfig {
method: "bearer".to_string(),
login_url: Some("https://x/login".to_string()),
username: Some("user".to_string()),
password: Some("pw".to_string()),
token: Some("tok".to_string()),
headers: None,
};
let auth = ArtifactAuth::from(dast);
assert_eq!(auth.method, "bearer");
// Bearer token wins over password.
assert_eq!(auth.secret.as_deref(), Some("tok"));
assert_eq!(auth.login_url.as_deref(), Some("https://x/login"));
}
#[test]
fn each_artifact_gets_a_unique_id() {
let a = Artifact::firmware_image("fw.bin");
let b = Artifact::firmware_image("fw.bin");
assert_ne!(a.id, b.id);
}
#[test]
fn firmware_default_profile_is_cra_and_62443() {
let p = default_compliance_profile(TargetType::FirmwareBareMetal);
assert!(p.frameworks.contains(&ComplianceFramework::Cra));
assert!(p.frameworks.contains(&ComplianceFramework::Iec62443));
}
#[test]
fn webapp_default_profile_is_gdpr_and_soc2() {
let p = default_compliance_profile(TargetType::WebApp);
assert!(p.frameworks.contains(&ComplianceFramework::Gdpr));
assert!(p.frameworks.contains(&ComplianceFramework::Soc2));
}
#[test]
fn new_target_gets_default_profile_and_no_external_refs() {
let t = OnboardedTarget::new("fw".to_string(), TargetType::FirmwareRtos);
assert!(!t.compliance_profile.frameworks.is_empty());
assert!(t.external_refs.is_empty());
}
#[test]
fn external_ref_linked_defaults() {
let r = ExternalRef::linked(ExternalSystem::Tramiton);
assert_eq!(r.system, ExternalSystem::Tramiton);
assert_eq!(r.status, "linked");
assert!(r.project_id.is_none());
assert!(r.last_reconciled_at.is_none());
}
}
+93 -2
View File
@@ -1,6 +1,8 @@
use serde::{Deserialize, Serialize};
use chrono::{DateTime, Utc};
use serde::{Deserialize, Deserializer, Serialize};
use super::issue::TrackerType;
/// What initiated a scan.
#[derive(Debug, Clone, Serialize, Deserialize, PartialEq, Eq)]
#[serde(rename_all = "snake_case")]
pub enum ScanTrigger {
@@ -8,3 +10,92 @@ 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,
}
}
}
+1 -24
View File
@@ -3,7 +3,7 @@ use serde::{Deserialize, Serialize};
use super::repository::ScanTrigger;
#[derive(Debug, Clone, Copy, Serialize, Deserialize, PartialEq, Eq)]
#[derive(Debug, Clone, Serialize, Deserialize, PartialEq, Eq)]
#[serde(rename_all = "lowercase")]
pub enum ScanType {
Sast,
@@ -16,17 +16,6 @@ pub enum ScanType {
SecretDetection,
Lint,
CodeReview,
/// Static analysis of a firmware image (unpack + component CVE).
FirmwareStatic,
/// Control-logic security analysis of PLC / SPS programs.
PlcControlLogic,
/// Static analysis of a mobile package (APK / AAB / IPA).
MobileStatic,
/// Static analysis of a container image.
ContainerScan,
/// Dynamic probing of a running PLC/SPS device over industrial protocols
/// (Modbus/TCP, OPC UA, …) for exposed/unauthenticated control access.
IcsProbe,
}
impl std::fmt::Display for ScanType {
@@ -42,11 +31,6 @@ impl std::fmt::Display for ScanType {
Self::SecretDetection => write!(f, "secret_detection"),
Self::Lint => write!(f, "lint"),
Self::CodeReview => write!(f, "code_review"),
Self::FirmwareStatic => write!(f, "firmware_static"),
Self::PlcControlLogic => write!(f, "plc_control_logic"),
Self::MobileStatic => write!(f, "mobile_static"),
Self::ContainerScan => write!(f, "container_scan"),
Self::IcsProbe => write!(f, "ics_probe"),
}
}
}
@@ -63,8 +47,6 @@ pub enum ScanRunStatus {
#[serde(rename_all = "snake_case")]
pub enum ScanPhase {
ChangeDetection,
ArtifactIngest,
Classification,
Sast,
SbomGeneration,
CveScanning,
@@ -73,14 +55,9 @@ pub enum ScanPhase {
LintScanning,
CodeReview,
GraphBuilding,
FirmwareStatic,
PlcAnalysis,
MobileStatic,
ContainerScan,
LlmTriage,
IssueCreation,
DastScanning,
IcsProbe,
Completed,
}
-556
View File
@@ -1,556 +0,0 @@
//! The scan-applicability matrix.
//!
//! Which scans are possible for a target is a function of its [`TargetType`] and
//! which [`ArtifactKind`]s are actually present: SAST needs code, DAST needs a
//! running URL, firmware-static analysis needs a firmware image, and so on. This
//! module encodes that as a table — one rule set per target type — and resolves
//! it against a concrete [`OnboardedTarget`] into a list of [`ScanOption`]s the
//! onboarding wizard and the scan pipeline both consume.
use crate::models::{ArtifactKind, OnboardedTarget, ScanType, TargetType};
/// What an artifact a scan needs in order to run.
#[derive(Debug, Clone, Copy, PartialEq, Eq)]
pub enum ArtifactRequirement {
/// Source code — a git repo or a source archive.
Code,
/// A reachable running instance (any live URL / endpoint, scheme-agnostic —
/// e.g. the ICS probe works off the host:port of a modbus:// or http:// ref).
RunningUrl,
/// A reachable **web** endpoint — a live URL with an http(s) scheme. DAST is
/// an HTTP crawler, so a modbus:// / opc.tcp:// endpoint does not satisfy it.
HttpUrl,
/// A firmware image / binary blob.
Firmware,
/// A PLC project (PLCopen XML or Structured Text).
Plc,
/// A mobile package (APK / AAB / IPA).
Mobile,
/// A container image.
Container,
/// No specific artifact required.
Any,
}
/// A static rule: this scan applies to a target type, needs this artifact, and
/// defaults on/off. The rationale explains the entry to the user.
#[derive(Debug, Clone, Copy)]
pub struct ScanRule {
/// The scan this rule governs.
pub scan: ScanType,
/// Whether the scan is on by default (only when its artifact is present).
pub default_on: bool,
/// Human-readable explanation of what the scan does here.
pub rationale: &'static str,
/// The artifact the scan consumes.
pub requires: ArtifactRequirement,
}
impl ScanRule {
const fn new(
scan: ScanType,
default_on: bool,
rationale: &'static str,
requires: ArtifactRequirement,
) -> Self {
Self {
scan,
default_on,
rationale,
requires,
}
}
}
/// A resolved scan choice for a specific target: a rule intersected with the
/// artifacts actually present. `blocked_reason` is `Some` when the required
/// artifact is missing.
#[derive(Debug, Clone)]
pub struct ScanOption {
/// The scan.
pub scan: ScanType,
/// Whether to pre-select the scan (false when blocked).
pub default_on: bool,
/// Why the scan is offered.
pub rationale: String,
/// The artifact kind the scan needs, if any specific one.
pub required_artifact: Option<ArtifactKind>,
/// Set when the required artifact is absent, explaining the block.
pub blocked_reason: Option<String>,
}
/// The SAST umbrella: every static-analysis sub-scan that runs over source code.
fn sast_umbrella() -> Vec<ScanRule> {
use ArtifactRequirement::Code;
vec![
ScanRule::new(
ScanType::Sast,
true,
"Static analysis (Semgrep) over source",
Code,
),
ScanRule::new(
ScanType::Sbom,
true,
"Software bill of materials from source",
Code,
),
ScanRule::new(
ScanType::Cve,
true,
"Match dependencies against known CVEs",
Code,
),
ScanRule::new(
ScanType::SecretDetection,
true,
"Scan source for committed secrets",
Code,
),
ScanRule::new(ScanType::Lint, true, "Language linters over source", Code),
ScanRule::new(
ScanType::Gdpr,
true,
"GDPR data-handling pattern checks",
Code,
),
ScanRule::new(
ScanType::OAuth,
true,
"OAuth misconfiguration patterns",
Code,
),
ScanRule::new(
ScanType::Graph,
true,
"Build the code graph for impact analysis",
Code,
),
ScanRule::new(
ScanType::CodeReview,
false,
"LLM code review over changed source",
Code,
),
]
}
/// The rule set for a target type. Scans that are never applicable to a type are
/// simply absent (e.g. DAST is not listed for a PLC target).
pub fn rules_for(target_type: TargetType) -> Vec<ScanRule> {
use ArtifactRequirement::{Firmware, HttpUrl, Mobile, Plc, RunningUrl};
match target_type {
TargetType::WebApp | TargetType::BackendService => {
let mut r = sast_umbrella();
r.push(ScanRule::new(
ScanType::Dast,
true,
"Dynamic scan of the running endpoint",
HttpUrl,
));
r
}
TargetType::DesktopApp => sast_umbrella(),
TargetType::AndroidApp | TargetType::IosApp => {
let mut r = sast_umbrella();
r.push(ScanRule::new(
ScanType::MobileStatic,
true,
"Static analysis of the mobile package (manifest, permissions, libs)",
Mobile,
));
r
}
TargetType::FirmwareBareMetal | TargetType::FirmwareRtos => {
let mut r = sast_umbrella();
r.push(ScanRule::new(
ScanType::FirmwareStatic,
true,
"Unpack and statically analyze the firmware image",
Firmware,
));
r.push(ScanRule::new(
ScanType::Sbom,
true,
"SBOM from the firmware image (binwalk / tramiton)",
Firmware,
));
r.push(ScanRule::new(
ScanType::Cve,
true,
"Match firmware components against known CVEs",
Firmware,
));
r
}
TargetType::EmbeddedLinuxYocto => {
let mut r = sast_umbrella();
r.push(ScanRule::new(
ScanType::FirmwareStatic,
true,
"EMBA / binwalk static analysis of the image",
Firmware,
));
r.push(ScanRule::new(
ScanType::Sbom,
true,
"SBOM from image layers / recipes",
Firmware,
));
r.push(ScanRule::new(
ScanType::Cve,
true,
"Match image components against known CVEs",
Firmware,
));
r.push(ScanRule::new(
ScanType::Dast,
false,
"Dynamic scan of exposed network services (if any)",
HttpUrl,
));
r
}
TargetType::PlcSps => {
// A PLC/SPS device is a composite: the control application *and* the
// device it runs on (firmware/OS + reachable runtime services). The
// control-logic scan runs on the PLC project; the firmware and DAST
// scans light up only when a firmware image / running endpoint is
// attached (e.g. a CODESYS runtime on a Yocto image with WebVisu).
// Firmware-image SBOM/CVE *execution* is shared with the firmware
// families and tracked in #151/#128; DAST over a WebVisu/OPC-UA
// endpoint uses the existing DAST path.
vec![
ScanRule::new(
ScanType::PlcControlLogic,
true,
"Control-logic security rules over the PLC program",
Plc,
),
// Device-level scans are offered but opt-in (default-off): they
// apply only when a firmware image is attached, and firmware-image
// SBOM/CVE *execution* is shared with the firmware families and
// still landing (#151/#128), so they must not silently auto-run.
ScanRule::new(
ScanType::FirmwareStatic,
false,
"Static analysis of the device firmware image (OS + runtime)",
Firmware,
),
ScanRule::new(
ScanType::Sbom,
false,
"SBOM from the device firmware image (OS packages + CODESYS runtime)",
Firmware,
),
ScanRule::new(
ScanType::Cve,
false,
"Match device firmware components against known CVEs",
Firmware,
),
ScanRule::new(
ScanType::Dast,
false,
"Dynamic scan of the running device (WebVisu / exposed services)",
HttpUrl,
),
ScanRule::new(
ScanType::IcsProbe,
false,
"Probe the running device over industrial protocols (Modbus/TCP, …)",
RunningUrl,
),
]
}
}
}
/// Whether an active penetration test is applicable to this target type.
///
/// Pentest runs as its own session (not a [`ScanType`] scan) and needs a
/// reachable running target, so it is offered only for the network-reachable
/// families.
pub fn supports_pentest(target_type: TargetType) -> bool {
matches!(
target_type,
TargetType::WebApp
| TargetType::BackendService
| TargetType::AndroidApp
| TargetType::IosApp
| TargetType::EmbeddedLinuxYocto
// A PLC/SPS device exposes reachable runtime services (WebVisu, OPC UA,
// the CODESYS programming protocol), so an active pentest applies.
| TargetType::PlcSps
)
}
/// The representative artifact kind a requirement is satisfied by.
fn representative_kind(req: ArtifactRequirement) -> Option<ArtifactKind> {
match req {
ArtifactRequirement::Code => Some(ArtifactKind::GitRepo),
ArtifactRequirement::RunningUrl | ArtifactRequirement::HttpUrl => {
Some(ArtifactKind::LiveUrl)
}
ArtifactRequirement::Firmware => Some(ArtifactKind::FirmwareImage),
ArtifactRequirement::Plc => Some(ArtifactKind::PlcProject),
ArtifactRequirement::Mobile => Some(ArtifactKind::MobilePackage),
ArtifactRequirement::Container => Some(ArtifactKind::ContainerImage),
ArtifactRequirement::Any => None,
}
}
/// Whether a live-URL reference is an http(s) web endpoint (vs. an industrial
/// endpoint like `modbus://` / `opc.tcp://`, which DAST cannot crawl).
fn is_http_url(source_ref: &str) -> bool {
let s = source_ref.trim();
s.starts_with("http://") || s.starts_with("https://")
}
/// Whether the target carries an artifact that satisfies the requirement.
fn requirement_satisfied(req: ArtifactRequirement, target: &OnboardedTarget) -> bool {
match req {
ArtifactRequirement::Code => target.code_artifact().is_some(),
ArtifactRequirement::RunningUrl => target.has(ArtifactKind::LiveUrl),
ArtifactRequirement::HttpUrl => target
.artifacts
.iter()
.any(|a| a.kind == ArtifactKind::LiveUrl && is_http_url(&a.source_ref)),
ArtifactRequirement::Firmware => target.has(ArtifactKind::FirmwareImage),
// A PLC project artifact, or a code artifact (git repo / source archive)
// holding the control logic as PLCopen XML / ST exports — the common way
// CODESYS projects are version-controlled.
ArtifactRequirement::Plc => {
target.has(ArtifactKind::PlcProject) || target.code_artifact().is_some()
}
ArtifactRequirement::Mobile => target.has(ArtifactKind::MobilePackage),
ArtifactRequirement::Container => target.has(ArtifactKind::ContainerImage),
ArtifactRequirement::Any => true,
}
}
/// Resolve the matrix for a concrete target into the scans it can run, marking
/// any whose required artifact is missing as blocked.
pub fn applicable_scans(target: &OnboardedTarget) -> Vec<ScanOption> {
rules_for(target.target_type)
.into_iter()
.map(|rule| {
let satisfied = requirement_satisfied(rule.requires, target);
let required_artifact = representative_kind(rule.requires);
let blocked_reason = if satisfied {
None
} else if rule.requires == ArtifactRequirement::HttpUrl {
// A live URL may be present but non-HTTP (e.g. modbus://): be
// specific so the user knows DAST needs a web endpoint.
Some("no http(s) live URL — DAST needs a web endpoint".to_string())
} else {
Some(match required_artifact {
Some(kind) => format!("no {kind} artifact provided"),
None => "required artifact missing".to_string(),
})
};
ScanOption {
scan: rule.scan,
default_on: rule.default_on && satisfied,
rationale: rule.rationale.to_string(),
required_artifact,
blocked_reason,
}
})
.collect()
}
#[cfg(test)]
#[allow(clippy::expect_used, clippy::unwrap_used)]
mod tests {
use super::*;
use crate::models::{Artifact, PlcFormat};
fn target_with(target_type: TargetType, artifacts: Vec<Artifact>) -> OnboardedTarget {
let mut t = OnboardedTarget::new("t".to_string(), target_type);
t.artifacts = artifacts;
t
}
fn option<'a>(opts: &'a [ScanOption], scan: ScanType) -> Option<&'a ScanOption> {
opts.iter().find(|o| o.scan == scan)
}
#[test]
fn webapp_with_code_and_url_offers_sast_and_dast() {
let t = target_with(
TargetType::WebApp,
vec![
Artifact::git_repo("u", "main"),
Artifact::live_url("http://x"),
],
);
let opts = applicable_scans(&t);
let sast = option(&opts, ScanType::Sast).expect("sast offered");
assert!(sast.default_on && sast.blocked_reason.is_none());
let dast = option(&opts, ScanType::Dast).expect("dast offered");
assert!(dast.default_on && dast.blocked_reason.is_none());
}
#[test]
fn webapp_without_url_blocks_dast() {
let t = target_with(TargetType::WebApp, vec![Artifact::git_repo("u", "main")]);
let opts = applicable_scans(&t);
let dast = option(&opts, ScanType::Dast).expect("dast listed");
assert!(!dast.default_on);
assert!(dast.blocked_reason.is_some());
assert_eq!(dast.required_artifact, Some(ArtifactKind::LiveUrl));
}
#[test]
fn firmware_offers_firmware_static_and_not_dast() {
let t = target_with(
TargetType::FirmwareBareMetal,
vec![Artifact::firmware_image("fw.bin")],
);
let opts = applicable_scans(&t);
let fw = option(&opts, ScanType::FirmwareStatic).expect("firmware static offered");
assert!(fw.default_on && fw.blocked_reason.is_none());
assert!(option(&opts, ScanType::Dast).is_none());
}
#[test]
fn plc_control_logic_is_default_on_and_device_scans_block_without_artifacts() {
// A PLC project alone: control-logic runs; the device-level scans are
// offered but blocked until a firmware image / running endpoint is added.
let t = target_with(
TargetType::PlcSps,
vec![Artifact::plc_project("p.xml", PlcFormat::PlcopenXml)],
);
let opts = applicable_scans(&t);
let plc = option(&opts, ScanType::PlcControlLogic).expect("control-logic offered");
assert!(plc.default_on && plc.blocked_reason.is_none());
for scan in [ScanType::FirmwareStatic, ScanType::Sbom, ScanType::Cve] {
let o = option(&opts, scan).expect("device scan offered");
assert!(
!o.default_on,
"{scan} must not pre-select without a firmware image"
);
assert!(o.blocked_reason.is_some());
}
let dast = option(&opts, ScanType::Dast).expect("dast offered");
assert!(!dast.default_on);
assert!(dast.blocked_reason.is_some());
}
#[test]
fn plc_control_logic_is_satisfied_by_a_git_repo() {
// A CODESYS project version-controlled in git (PLCopen XML / ST exports),
// no uploaded PlcProject artifact.
let t = target_with(TargetType::PlcSps, vec![Artifact::git_repo("u", "main")]);
let opts = applicable_scans(&t);
let plc = option(&opts, ScanType::PlcControlLogic).expect("control-logic offered");
assert!(
plc.default_on && plc.blocked_reason.is_none(),
"a git repo should satisfy PLC control-logic"
);
}
#[test]
fn plc_composite_lights_up_device_scans_with_firmware_and_url() {
// A CODESYS-on-Yocto device: PLC project + firmware image + WebVisu URL.
let t = target_with(
TargetType::PlcSps,
vec![
Artifact::plc_project("p.xml", PlcFormat::PlcopenXml),
Artifact::firmware_image("device.img"),
Artifact::live_url("http://plc.local/webvisu"),
],
);
let opts = applicable_scans(&t);
for scan in [
ScanType::PlcControlLogic,
ScanType::FirmwareStatic,
ScanType::Sbom,
ScanType::Cve,
] {
let o = option(&opts, scan).expect("scan offered");
assert!(o.blocked_reason.is_none(), "{scan} should be unblocked");
}
// Control-logic auto-runs; the device-level scans are unblocked but opt-in
// (default-off) until firmware-image execution lands (#151/#128).
assert!(option(&opts, ScanType::PlcControlLogic).unwrap().default_on);
assert!(!option(&opts, ScanType::Sbom).unwrap().default_on);
assert!(!option(&opts, ScanType::Dast).unwrap().default_on);
assert!(option(&opts, ScanType::Dast)
.unwrap()
.blocked_reason
.is_none());
}
#[test]
fn plc_with_modbus_url_offers_ics_probe_but_blocks_dast() {
// A soft-PLC reachable only over Modbus/TCP (no WebVisu). The ICS probe
// is applicable (it works off host:port), but DAST — an HTTP crawler —
// must be blocked so it isn't offered/run against a non-web endpoint.
let t = target_with(
TargetType::PlcSps,
vec![Artifact::live_url("modbus://plc-sim:502")],
);
let opts = applicable_scans(&t);
let ics = option(&opts, ScanType::IcsProbe).expect("ics probe offered");
assert!(
ics.blocked_reason.is_none(),
"ICS probe should be unblocked for a modbus:// endpoint"
);
assert!(!ics.default_on, "ICS probe stays opt-in (default-off)");
let dast = option(&opts, ScanType::Dast).expect("dast listed");
assert!(
dast.blocked_reason.is_some(),
"DAST must be blocked without an http(s) endpoint"
);
assert!(!dast.default_on);
}
#[test]
fn plc_with_http_webvisu_offers_both_dast_and_ics_probe() {
// A PLC exposing a WebVisu over HTTP: both DAST (web) and the ICS probe
// (OT ports on the same host) are applicable.
let t = target_with(
TargetType::PlcSps,
vec![Artifact::live_url("http://plc.local/webvisu")],
);
let opts = applicable_scans(&t);
assert!(option(&opts, ScanType::Dast)
.expect("dast offered")
.blocked_reason
.is_none());
assert!(option(&opts, ScanType::IcsProbe)
.expect("ics probe offered")
.blocked_reason
.is_none());
}
#[test]
fn pentest_support_matches_reachable_families() {
assert!(supports_pentest(TargetType::WebApp));
assert!(supports_pentest(TargetType::BackendService));
assert!(supports_pentest(TargetType::EmbeddedLinuxYocto));
// A PLC/SPS device is network-reachable (WebVisu / OPC UA / 11740).
assert!(supports_pentest(TargetType::PlcSps));
assert!(!supports_pentest(TargetType::FirmwareBareMetal));
assert!(!supports_pentest(TargetType::DesktopApp));
}
#[test]
fn every_target_type_has_at_least_one_rule() {
for tt in [
TargetType::WebApp,
TargetType::BackendService,
TargetType::DesktopApp,
TargetType::AndroidApp,
TargetType::IosApp,
TargetType::FirmwareBareMetal,
TargetType::FirmwareRtos,
TargetType::EmbeddedLinuxYocto,
TargetType::PlcSps,
] {
assert!(!rules_for(tt).is_empty(), "{tt} has no rules");
}
}
}
-51
View File
@@ -1,51 +0,0 @@
//! The target-classification port.
//!
//! A [`TargetClassifier`] inspects a target's artifacts (and optionally their
//! ingested working directories) and proposes one or more [`ClassifierVerdict`]s
//! — a target type, a confidence, and the facts the decision rested on. Concrete
//! classifiers live in the agent (language/build-system fingerprinting, a
//! firmware detector backed by tramiton, etc.); a registry merges and ranks
//! their verdicts. This mirrors the [`crate::traits::Scanner`] port so the two
//! read the same way.
use std::collections::HashMap;
use std::path::PathBuf;
use crate::error::CoreError;
use crate::models::{Artifact, DetectedFact, TargetType};
/// Everything a classifier needs to reason about a target.
pub struct ClassificationInput<'a> {
/// The artifacts declared for the target.
pub artifacts: &'a [Artifact],
/// Ingested working paths, keyed by [`Artifact::id`]. Absent for artifacts
/// with no on-disk form (e.g. a live URL).
pub working_paths: &'a HashMap<String, PathBuf>,
/// Free-form description of the target, if provided.
pub description: Option<&'a str>,
}
/// A single classifier's proposal for a target.
pub struct ClassifierVerdict {
/// The proposed target type.
pub target_type: TargetType,
/// Confidence in `[0.0, 1.0]`.
pub confidence: f32,
/// Facts that informed the proposal.
pub facts: Vec<DetectedFact>,
/// Human-readable explanation.
pub rationale: String,
}
/// A source of target-type classification.
#[allow(async_fn_in_trait)]
pub trait TargetClassifier: Send + Sync {
/// Stable identifier for this classifier (recorded in `detected_by`).
fn name(&self) -> &str;
/// Propose zero or more ranked verdicts for the given input.
async fn classify(
&self,
input: &ClassificationInput<'_>,
) -> Result<Vec<ClassifierVerdict>, CoreError>;
}
-45
View File
@@ -1,45 +0,0 @@
//! The compliance-controls provider port.
//!
//! The mapping engine turns findings into compliance status against a corpus of
//! controls. That corpus is pluggable: the built-in OSCAL catalog by default, or
//! a tenant-owned RAG of atomic controls derived from laws
//! (`breakpilot-compliance`) when available. A [`ControlsProvider`] abstracts the
//! source so the mapping engine does not hardcode a catalog.
use crate::error::CoreError;
use crate::models::ComplianceFramework;
/// A control retrieved from a controls corpus.
#[derive(Debug, Clone)]
pub struct Control {
/// Stable control identifier (e.g. an OSCAL control id or a RAG chunk id).
pub id: String,
/// The framework this control belongs to.
pub framework: ComplianceFramework,
/// Short human-readable title.
pub title: String,
/// The control text / requirement.
pub text: String,
/// Free-form source reference (catalog name, law citation, ...).
pub source: Option<String>,
}
/// A query for relevant controls.
pub struct ControlQuery<'a> {
/// Frameworks in scope for the target.
pub frameworks: &'a [ComplianceFramework],
/// Free-text describing what to map (a finding summary, a component, ...).
pub context: &'a str,
/// Maximum number of controls to return.
pub limit: usize,
}
/// A source of compliance controls (built-in OSCAL catalog, breakpilot RAG, ...).
#[allow(async_fn_in_trait)]
pub trait ControlsProvider: Send + Sync {
/// Stable identifier for this provider.
fn name(&self) -> &str;
/// Retrieve the controls most relevant to the query.
async fn controls(&self, query: &ControlQuery<'_>) -> Result<Vec<Control>, CoreError>;
}
-58
View File
@@ -1,58 +0,0 @@
//! The external-evidence provider port.
//!
//! A sibling product (tramiton, for firmware) may already hold authoritative
//! analysis for an artifact. An [`EvidenceProvider`] lets compliance-scanner
//! *reconcile* that evidence — a build plan, an SBOM, a VEX document, a
//! reproducible-build lock, an attestation — instead of recomputing it. The key
//! used to match is the artifact content digest (a firmware sha256, which equals
//! [`crate::models::Artifact::content_hash`]).
//!
//! Concrete providers live in the agent (a tramiton CLI shell-out today, a cloud
//! client later) plus a deterministic mock for tests, so nothing here depends on
//! an external binary.
use std::path::Path;
use crate::error::CoreError;
use crate::models::{Artifact, ExternalSystem};
/// A single reconcilable evidence document fetched from a sibling product.
#[derive(Debug, Clone)]
pub struct EvidenceDocument {
/// What the document is: `build_plan` | `sbom` | `vex` | `lock` | `attestation`.
pub kind: String,
/// The document's format (e.g. `cyclonedx-1.5`, `openvex-0.2.0`, `toml`, `json`).
pub format: String,
/// The raw document payload.
pub content: String,
}
/// The evidence a provider could return for a target's artifact.
#[derive(Debug, Clone, Default)]
pub struct ReconciledEvidence {
/// The sibling's project identifier, if resolved.
pub project_id: Option<String>,
/// The subject content digest the evidence pertains to.
pub subject_sha256: Option<String>,
/// The documents fetched (any of build plan / SBOM / VEX / lock / attestation).
pub documents: Vec<EvidenceDocument>,
}
/// A source of externally-held, reconcilable evidence for an artifact.
#[allow(async_fn_in_trait)]
pub trait EvidenceProvider: Send + Sync {
/// Which sibling product this provider integrates.
fn system(&self) -> ExternalSystem;
/// Whether this provider can handle the given artifact + working path
/// (e.g. tramiton handles firmware images / embedded source trees).
fn handles(&self, artifact: &Artifact, working_path: Option<&Path>) -> bool;
/// Reconcile existing evidence for the artifact, keyed by its content digest.
/// Returns `Ok(None)` when the provider has nothing for this artifact.
async fn reconcile(
&self,
artifact: &Artifact,
working_path: Option<&Path>,
) -> Result<Option<ReconciledEvidence>, CoreError>;
}
-6
View File
@@ -1,16 +1,10 @@
pub mod classifier;
pub mod controls;
pub mod dast_agent;
pub mod evidence;
pub mod graph_builder;
pub mod issue_tracker;
pub mod pentest_tool;
pub mod scanner;
pub use classifier::{ClassificationInput, ClassifierVerdict, TargetClassifier};
pub use controls::{Control, ControlQuery, ControlsProvider};
pub use dast_agent::{DastAgent, DastContext, DiscoveredEndpoint, EndpointParameter};
pub use evidence::{EvidenceDocument, EvidenceProvider, ReconciledEvidence};
pub use graph_builder::{LanguageParser, ParseOutput};
pub use issue_tracker::IssueTracker;
pub use pentest_tool::{PentestTool, PentestToolContext, PentestToolResult};
+2 -6
View File
@@ -10,10 +10,8 @@ pub enum Route {
#[layout(AppShell)]
#[route("/")]
OverviewPage {},
#[route("/targets")]
TargetsPage {},
#[route("/onboard")]
OnboardingPage {},
#[route("/repositories")]
RepositoriesPage {},
#[route("/findings")]
FindingsPage {},
#[route("/findings/:id")]
@@ -46,8 +44,6 @@ pub enum Route {
PentestSessionPage { session_id: String },
#[route("/mcp-servers")]
McpServersPage {},
#[route("/mcp-tokens")]
McpTokensPage {},
}
const FAVICON: Asset = asset!("/assets/favicon.svg");
@@ -4,9 +4,8 @@ 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_ssh_public_key;
use crate::infrastructure::repositories::{fetch_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 \
@@ -40,7 +39,7 @@ 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_targets().await.ok() });
let existing_repos = use_resource(|| async { fetch_repositories(1).await.ok() });
// SSH key state for private repos
let mut ssh_public_key = use_signal(String::new);
@@ -212,25 +211,7 @@ pub fn PentestWizard(show: Signal<bool>) -> Element {
Some(Some(data)) => data
.data
.iter()
.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))
})
.map(|r| (r.git_url.clone(), r.name.clone()))
.collect(),
_ => Vec::new(),
}
@@ -24,15 +24,10 @@ pub fn Sidebar() -> Element {
icon: rsx! { Icon { icon: BsSpeedometer2, width: 18, height: 18 } },
},
NavItem {
label: "Targets",
route: Route::TargetsPage {},
label: "Repositories",
route: Route::RepositoriesPage {},
icon: rsx! { Icon { icon: BsFolder2Open, width: 18, height: 18 } },
},
NavItem {
label: "Onboard",
route: Route::OnboardingPage {},
icon: rsx! { Icon { icon: BsPlusCircle, width: 18, height: 18 } },
},
NavItem {
label: "Findings",
route: Route::FindingsPage {},
@@ -1,210 +0,0 @@
//! Authenticated HTTP client for talking to the compliance-agent.
//!
//! Every dashboard server function that hits `comp-dev.meghsakha.com/api/v1/*`
//! must go through here so the Keycloak access token from the user's
//! session is attached as `Authorization: Bearer <token>`. Without it
//! the agent's M7.1 `require_jwt_auth` middleware rejects with 401
//! "Missing authorization header".
//!
//! When Keycloak is not configured (dev convenience), the helper
//! returns an unauthenticated builder — matching the agent's
//! pass-through behavior in the same state.
//!
//! **Token refresh**: KC access tokens are short-lived (5 min default
//! in the certifai realm). Before attaching, we decode the JWT's `exp`
//! claim and proactively refresh via the stored refresh_token if the
//! access token is expired or about to expire. The session is updated
//! with the new pair. If refresh fails, we send the (stale) token
//! anyway — the agent's 401 will surface to the UI, which can prompt
//! re-login.
use base64::{engine::general_purpose::URL_SAFE_NO_PAD, Engine};
use dioxus::prelude::ServerFnError;
use dioxus_fullstack::FullstackContext;
use reqwest::Method;
use super::auth::LOGGED_IN_USER_SESS_KEY;
use super::server_state::ServerState;
use super::user_state::UserStateInner;
/// Seconds before the JWT's `exp` time at which we consider it stale
/// enough to refresh. Covers clock skew + the round-trip to the agent
/// so the token doesn't expire mid-flight.
const REFRESH_SKEW_SECS: i64 = 30;
/// Build a `RequestBuilder` for `<agent_api_url><path>` with the
/// session's access token attached. `path` should include a leading
/// `/`, e.g. `"/api/v1/repositories"`.
pub async fn agent_request(
method: Method,
path: &str,
) -> Result<reqwest::RequestBuilder, ServerFnError> {
let state: ServerState = FullstackContext::extract().await?;
let url = format!("{}{}", state.agent_api_url, path);
let mut req = reqwest::Client::new().request(method, &url);
req = attach_token(req, &state).await?;
Ok(req)
}
/// Same as [`agent_request`] but for `GET`. Convenience for the common case.
pub async fn agent_get(path: &str) -> Result<reqwest::RequestBuilder, ServerFnError> {
agent_request(Method::GET, path).await
}
/// Attach the session's bearer token if Keycloak is configured AND the
/// session has a logged-in user. Refresh the token proactively if it's
/// expired or about to expire. Persists refreshed tokens back into the
/// session.
async fn attach_token(
req: reqwest::RequestBuilder,
state: &ServerState,
) -> Result<reqwest::RequestBuilder, ServerFnError> {
if state.keycloak.is_none() {
return Ok(req);
}
let session: tower_sessions::Session = FullstackContext::extract().await?;
let user: Option<UserStateInner> = session
.get(LOGGED_IN_USER_SESS_KEY)
.await
.map_err(|e| ServerFnError::new(format!("session read failed: {e}")))?;
let Some(mut user) = user else {
return Ok(req);
};
if token_needs_refresh(&user.access_token) {
tracing::debug!("Access token expired or near-expiring; refreshing");
match refresh_tokens(state, &user.refresh_token).await {
Ok((new_access, new_refresh)) => {
user.access_token = new_access;
if let Some(rt) = new_refresh {
user.refresh_token = rt;
}
if let Err(e) = session.insert(LOGGED_IN_USER_SESS_KEY, &user).await {
tracing::warn!("Failed to persist refreshed tokens: {e}");
}
}
Err(e) => {
tracing::warn!("Token refresh failed: {e}; sending current token anyway");
// Fall through — the agent will 401 and the UI will
// prompt re-login. Better than failing the request at
// the dashboard layer with no helpful UX cue.
}
}
}
Ok(req.bearer_auth(user.access_token))
}
/// Decode the JWT's payload (no signature verification — the agent
/// does that) and check the `exp` claim. Treats malformed tokens as
/// expired so the refresh path runs.
fn token_needs_refresh(jwt: &str) -> bool {
let Some(payload_b64) = jwt.split('.').nth(1) else {
return true;
};
let Ok(bytes) = URL_SAFE_NO_PAD.decode(payload_b64) else {
return true;
};
#[derive(serde::Deserialize)]
struct ExpClaim {
exp: i64,
}
let Ok(claims) = serde_json::from_slice::<ExpClaim>(&bytes) else {
return true;
};
let now = chrono::Utc::now().timestamp();
claims.exp - REFRESH_SKEW_SECS <= now
}
/// Exchange a refresh_token for a new access_token. Returns the new
/// access_token and (optionally) the new refresh_token KC issued.
/// KC may rotate refresh_tokens on use; we honor whatever it sends.
async fn refresh_tokens(
state: &ServerState,
refresh_token: &str,
) -> Result<(String, Option<String>), String> {
let kc = state
.keycloak
.ok_or_else(|| "Keycloak not configured".to_string())?;
if refresh_token.is_empty() {
return Err("no refresh_token in session".to_string());
}
#[derive(serde::Deserialize)]
struct TokenResp {
access_token: String,
refresh_token: Option<String>,
}
let resp = reqwest::Client::new()
.post(kc.token_endpoint())
.form(&[
("grant_type", "refresh_token"),
("client_id", kc.client_id.as_str()),
("refresh_token", refresh_token),
])
.send()
.await
.map_err(|e| format!("refresh request failed: {e}"))?;
if !resp.status().is_success() {
let status = resp.status();
let body = resp.text().await.unwrap_or_default();
return Err(format!("refresh rejected ({status}): {body}"));
}
let r: TokenResp = resp
.json()
.await
.map_err(|e| format!("refresh response parse failed: {e}"))?;
Ok((r.access_token, r.refresh_token))
}
#[cfg(test)]
mod tests {
use super::*;
use base64::Engine;
/// Build a JWT-shaped string (header.payload.sig) with the given
/// payload. Signature is bogus — we never verify it locally.
fn make_jwt(payload: &serde_json::Value) -> String {
let payload_b64 = URL_SAFE_NO_PAD.encode(serde_json::to_vec(payload).unwrap());
format!("hdr.{payload_b64}.sig")
}
#[test]
fn token_needs_refresh_true_when_expired() {
let exp = chrono::Utc::now().timestamp() - 60;
let jwt = make_jwt(&serde_json::json!({ "exp": exp }));
assert!(token_needs_refresh(&jwt));
}
#[test]
fn token_needs_refresh_true_within_skew_window() {
// 10 seconds left; less than the 30s skew → must refresh.
let exp = chrono::Utc::now().timestamp() + 10;
let jwt = make_jwt(&serde_json::json!({ "exp": exp }));
assert!(token_needs_refresh(&jwt));
}
#[test]
fn token_needs_refresh_false_with_plenty_of_life() {
let exp = chrono::Utc::now().timestamp() + 600;
let jwt = make_jwt(&serde_json::json!({ "exp": exp }));
assert!(!token_needs_refresh(&jwt));
}
#[test]
fn token_needs_refresh_true_on_malformed_jwt() {
assert!(token_needs_refresh(""));
assert!(token_needs_refresh("not.a.jwt"));
assert!(token_needs_refresh("only-one-segment"));
assert!(token_needs_refresh("hdr.not-base64!.sig"));
}
#[test]
fn token_needs_refresh_true_when_exp_missing() {
let jwt = make_jwt(&serde_json::json!({ "sub": "abc" }));
assert!(token_needs_refresh(&jwt));
}
}
+35 -26
View File
@@ -61,21 +61,23 @@ pub async fn send_chat_message(
message: String,
history: Vec<ChatHistoryMessage>,
) -> Result<ChatApiResponse, ServerFnError> {
// Chat uses a longer timeout because the LLM round-trip can be slow;
// agent_request doesn't expose a per-call timeout so we layer one on.
let resp = super::agent_client::agent_request(
reqwest::Method::POST,
&format!("/api/v1/chat/{repo_id}"),
)
.await?
.timeout(std::time::Duration::from_secs(120))
.json(&serde_json::json!({
"message": message,
"history": history,
}))
.send()
.await
.map_err(|e| ServerFnError::new(format!("Request failed: {e}")))?;
let state: super::server_state::ServerState =
dioxus_fullstack::FullstackContext::extract().await?;
let url = format!("{}/api/v1/chat/{repo_id}", state.agent_api_url);
let client = reqwest::Client::builder()
.timeout(std::time::Duration::from_secs(120))
.build()
.map_err(|e| ServerFnError::new(e.to_string()))?;
let resp = client
.post(&url)
.json(&serde_json::json!({
"message": message,
"history": history,
}))
.send()
.await
.map_err(|e| ServerFnError::new(format!("Request failed: {e}")))?;
let text = resp
.text()
@@ -89,14 +91,19 @@ pub async fn send_chat_message(
#[server]
pub async fn trigger_embedding_build(repo_id: String) -> Result<(), ServerFnError> {
super::agent_client::agent_request(
reqwest::Method::POST,
&format!("/api/v1/chat/{repo_id}/build-embeddings"),
)
.await?
.send()
.await
.map_err(|e| ServerFnError::new(e.to_string()))?;
let state: super::server_state::ServerState =
dioxus_fullstack::FullstackContext::extract().await?;
let url = format!(
"{}/api/v1/chat/{repo_id}/build-embeddings",
state.agent_api_url
);
let client = reqwest::Client::new();
client
.post(&url)
.send()
.await
.map_err(|e| ServerFnError::new(e.to_string()))?;
Ok(())
}
@@ -104,9 +111,11 @@ pub async fn trigger_embedding_build(repo_id: String) -> Result<(), ServerFnErro
pub async fn fetch_embedding_status(
repo_id: String,
) -> Result<EmbeddingStatusResponse, ServerFnError> {
let resp = super::agent_client::agent_get(&format!("/api/v1/chat/{repo_id}/status"))
.await?
.send()
let state: super::server_state::ServerState =
dioxus_fullstack::FullstackContext::extract().await?;
let url = format!("{}/api/v1/chat/{repo_id}/status", state.agent_api_url);
let resp = reqwest::get(&url)
.await
.map_err(|e| ServerFnError::new(e.to_string()))?;
let body: EmbeddingStatusResponse = resp
+34 -22
View File
@@ -26,9 +26,10 @@ pub struct DastFindingDetailResponse {
#[server]
pub async fn fetch_dast_targets() -> Result<DastTargetsResponse, ServerFnError> {
let resp = super::agent_client::agent_get("/api/v1/dast/targets")
.await?
.send()
let state: super::server_state::ServerState =
dioxus_fullstack::FullstackContext::extract().await?;
let url = format!("{}/api/v1/dast/targets", state.agent_api_url);
let resp = reqwest::get(&url)
.await
.map_err(|e| ServerFnError::new(e.to_string()))?;
let body: DastTargetsResponse = resp
@@ -40,9 +41,10 @@ pub async fn fetch_dast_targets() -> Result<DastTargetsResponse, ServerFnError>
#[server]
pub async fn fetch_dast_scan_runs() -> Result<DastScanRunsResponse, ServerFnError> {
let resp = super::agent_client::agent_get("/api/v1/dast/scan-runs")
.await?
.send()
let state: super::server_state::ServerState =
dioxus_fullstack::FullstackContext::extract().await?;
let url = format!("{}/api/v1/dast/scan-runs", state.agent_api_url);
let resp = reqwest::get(&url)
.await
.map_err(|e| ServerFnError::new(e.to_string()))?;
let body: DastScanRunsResponse = resp
@@ -54,9 +56,10 @@ pub async fn fetch_dast_scan_runs() -> Result<DastScanRunsResponse, ServerFnErro
#[server]
pub async fn fetch_dast_findings() -> Result<DastFindingsResponse, ServerFnError> {
let resp = super::agent_client::agent_get("/api/v1/dast/findings")
.await?
.send()
let state: super::server_state::ServerState =
dioxus_fullstack::FullstackContext::extract().await?;
let url = format!("{}/api/v1/dast/findings", state.agent_api_url);
let resp = reqwest::get(&url)
.await
.map_err(|e| ServerFnError::new(e.to_string()))?;
let body: DastFindingsResponse = resp
@@ -70,9 +73,10 @@ pub async fn fetch_dast_findings() -> Result<DastFindingsResponse, ServerFnError
pub async fn fetch_dast_finding_detail(
id: String,
) -> Result<DastFindingDetailResponse, ServerFnError> {
let resp = super::agent_client::agent_get(&format!("/api/v1/dast/findings/{id}"))
.await?
.send()
let state: super::server_state::ServerState =
dioxus_fullstack::FullstackContext::extract().await?;
let url = format!("{}/api/v1/dast/findings/{id}", state.agent_api_url);
let resp = reqwest::get(&url)
.await
.map_err(|e| ServerFnError::new(e.to_string()))?;
let body: DastFindingDetailResponse = resp
@@ -84,8 +88,12 @@ pub async fn fetch_dast_finding_detail(
#[server]
pub async fn add_dast_target(name: String, base_url: String) -> Result<(), ServerFnError> {
super::agent_client::agent_request(reqwest::Method::POST, "/api/v1/dast/targets")
.await?
let state: super::server_state::ServerState =
dioxus_fullstack::FullstackContext::extract().await?;
let url = format!("{}/api/v1/dast/targets", state.agent_api_url);
let client = reqwest::Client::new();
client
.post(&url)
.json(&serde_json::json!({
"name": name,
"base_url": base_url,
@@ -98,13 +106,17 @@ pub async fn add_dast_target(name: String, base_url: String) -> Result<(), Serve
#[server]
pub async fn trigger_dast_scan(target_id: String) -> Result<(), ServerFnError> {
super::agent_client::agent_request(
reqwest::Method::POST,
&format!("/api/v1/dast/targets/{target_id}/scan"),
)
.await?
.send()
.await
.map_err(|e| ServerFnError::new(e.to_string()))?;
let state: super::server_state::ServerState =
dioxus_fullstack::FullstackContext::extract().await?;
let url = format!(
"{}/api/v1/dast/targets/{target_id}/scan",
state.agent_api_url
);
let client = reqwest::Client::new();
client
.post(&url)
.send()
.await
.map_err(|e| ServerFnError::new(e.to_string()))?;
Ok(())
}
@@ -19,6 +19,10 @@ 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")
}
@@ -24,35 +24,39 @@ pub struct FindingsQuery {
#[server]
pub async fn fetch_findings(query: FindingsQuery) -> Result<FindingsListResponse, ServerFnError> {
let mut path = format!("/api/v1/findings?page={}&limit=20", query.page);
let state: super::server_state::ServerState =
dioxus_fullstack::FullstackContext::extract().await?;
let mut url = format!(
"{}/api/v1/findings?page={}&limit=20",
state.agent_api_url, query.page
);
if !query.severity.is_empty() {
path.push_str(&format!("&severity={}", query.severity));
url.push_str(&format!("&severity={}", query.severity));
}
if !query.scan_type.is_empty() {
path.push_str(&format!("&scan_type={}", query.scan_type));
url.push_str(&format!("&scan_type={}", query.scan_type));
}
if !query.status.is_empty() {
path.push_str(&format!("&status={}", query.status));
url.push_str(&format!("&status={}", query.status));
}
if !query.repo_id.is_empty() {
path.push_str(&format!("&repo_id={}", query.repo_id));
url.push_str(&format!("&repo_id={}", query.repo_id));
}
if !query.q.is_empty() {
path.push_str(&format!(
url.push_str(&format!(
"&q={}",
url::form_urlencoded::byte_serialize(query.q.as_bytes()).collect::<String>()
));
}
if !query.sort_by.is_empty() {
path.push_str(&format!("&sort_by={}", query.sort_by));
url.push_str(&format!("&sort_by={}", query.sort_by));
}
if !query.sort_order.is_empty() {
path.push_str(&format!("&sort_order={}", query.sort_order));
url.push_str(&format!("&sort_order={}", query.sort_order));
}
let resp = super::agent_client::agent_get(&path)
.await?
.send()
let resp = reqwest::get(&url)
.await
.map_err(|e| ServerFnError::new(e.to_string()))?;
let body: FindingsListResponse = resp
@@ -64,9 +68,11 @@ pub async fn fetch_findings(query: FindingsQuery) -> Result<FindingsListResponse
#[server]
pub async fn fetch_finding_detail(id: String) -> Result<Finding, ServerFnError> {
let resp = super::agent_client::agent_get(&format!("/api/v1/findings/{id}"))
.await?
.send()
let state: super::server_state::ServerState =
dioxus_fullstack::FullstackContext::extract().await?;
let url = format!("{}/api/v1/findings/{id}", state.agent_api_url);
let resp = reqwest::get(&url)
.await
.map_err(|e| ServerFnError::new(e.to_string()))?;
let body: serde_json::Value = resp
@@ -80,15 +86,18 @@ pub async fn fetch_finding_detail(id: String) -> Result<Finding, ServerFnError>
#[server]
pub async fn update_finding_status(id: String, status: String) -> Result<(), ServerFnError> {
super::agent_client::agent_request(
reqwest::Method::PATCH,
&format!("/api/v1/findings/{id}/status"),
)
.await?
.json(&serde_json::json!({ "status": status }))
.send()
.await
.map_err(|e| ServerFnError::new(e.to_string()))?;
let state: super::server_state::ServerState =
dioxus_fullstack::FullstackContext::extract().await?;
let url = format!("{}/api/v1/findings/{id}/status", state.agent_api_url);
let client = reqwest::Client::new();
client
.patch(&url)
.json(&serde_json::json!({ "status": status }))
.send()
.await
.map_err(|e| ServerFnError::new(e.to_string()))?;
Ok(())
}
@@ -97,25 +106,34 @@ pub async fn bulk_update_finding_status(
ids: Vec<String>,
status: String,
) -> Result<(), ServerFnError> {
super::agent_client::agent_request(reqwest::Method::PATCH, "/api/v1/findings/bulk-status")
.await?
let state: super::server_state::ServerState =
dioxus_fullstack::FullstackContext::extract().await?;
let url = format!("{}/api/v1/findings/bulk-status", state.agent_api_url);
let client = reqwest::Client::new();
client
.patch(&url)
.json(&serde_json::json!({ "ids": ids, "status": status }))
.send()
.await
.map_err(|e| ServerFnError::new(e.to_string()))?;
Ok(())
}
#[server]
pub async fn update_finding_feedback(id: String, feedback: String) -> Result<(), ServerFnError> {
super::agent_client::agent_request(
reqwest::Method::PATCH,
&format!("/api/v1/findings/{id}/feedback"),
)
.await?
.json(&serde_json::json!({ "feedback": feedback }))
.send()
.await
.map_err(|e| ServerFnError::new(e.to_string()))?;
let state: super::server_state::ServerState =
dioxus_fullstack::FullstackContext::extract().await?;
let url = format!("{}/api/v1/findings/{id}/feedback", state.agent_api_url);
let client = reqwest::Client::new();
client
.patch(&url)
.json(&serde_json::json!({ "feedback": feedback }))
.send()
.await
.map_err(|e| ServerFnError::new(e.to_string()))?;
Ok(())
}
@@ -50,9 +50,10 @@ pub struct SearchResponse {
#[server]
pub async fn fetch_graph(repo_id: String) -> Result<GraphDataResponse, ServerFnError> {
let resp = super::agent_client::agent_get(&format!("/api/v1/graph/{repo_id}"))
.await?
.send()
let state: super::server_state::ServerState =
dioxus_fullstack::FullstackContext::extract().await?;
let url = format!("{}/api/v1/graph/{repo_id}", state.agent_api_url);
let resp = reqwest::get(&url)
.await
.map_err(|e| ServerFnError::new(e.to_string()))?;
let body: GraphDataResponse = resp
@@ -67,12 +68,15 @@ pub async fn fetch_impact(
repo_id: String,
finding_id: String,
) -> Result<ImpactResponse, ServerFnError> {
let resp =
super::agent_client::agent_get(&format!("/api/v1/graph/{repo_id}/impact/{finding_id}"))
.await?
.send()
.await
.map_err(|e| ServerFnError::new(e.to_string()))?;
let state: super::server_state::ServerState =
dioxus_fullstack::FullstackContext::extract().await?;
let url = format!(
"{}/api/v1/graph/{repo_id}/impact/{finding_id}",
state.agent_api_url
);
let resp = reqwest::get(&url)
.await
.map_err(|e| ServerFnError::new(e.to_string()))?;
let body: ImpactResponse = resp
.json()
.await
@@ -82,9 +86,10 @@ pub async fn fetch_impact(
#[server]
pub async fn fetch_communities(repo_id: String) -> Result<CommunitiesResponse, ServerFnError> {
let resp = super::agent_client::agent_get(&format!("/api/v1/graph/{repo_id}/communities"))
.await?
.send()
let state: super::server_state::ServerState =
dioxus_fullstack::FullstackContext::extract().await?;
let url = format!("{}/api/v1/graph/{repo_id}/communities", state.agent_api_url);
let resp = reqwest::get(&url)
.await
.map_err(|e| ServerFnError::new(e.to_string()))?;
let body: CommunitiesResponse = resp
@@ -99,13 +104,15 @@ pub async fn fetch_file_content(
repo_id: String,
file_path: String,
) -> Result<FileContentResponse, ServerFnError> {
let resp = super::agent_client::agent_get(&format!(
"/api/v1/graph/{repo_id}/file-content?path={file_path}"
))
.await?
.send()
.await
.map_err(|e| ServerFnError::new(e.to_string()))?;
let state: super::server_state::ServerState =
dioxus_fullstack::FullstackContext::extract().await?;
let url = format!(
"{}/api/v1/graph/{repo_id}/file-content?path={file_path}",
state.agent_api_url
);
let resp = reqwest::get(&url)
.await
.map_err(|e| ServerFnError::new(e.to_string()))?;
let body: FileContentResponse = resp
.json()
.await
@@ -115,13 +122,15 @@ pub async fn fetch_file_content(
#[server]
pub async fn search_nodes(repo_id: String, query: String) -> Result<SearchResponse, ServerFnError> {
let resp = super::agent_client::agent_get(&format!(
"/api/v1/graph/{repo_id}/search?q={query}&limit=50"
))
.await?
.send()
.await
.map_err(|e| ServerFnError::new(e.to_string()))?;
let state: super::server_state::ServerState =
dioxus_fullstack::FullstackContext::extract().await?;
let url = format!(
"{}/api/v1/graph/{repo_id}/search?q={query}&limit=50",
state.agent_api_url
);
let resp = reqwest::get(&url)
.await
.map_err(|e| ServerFnError::new(e.to_string()))?;
let body: SearchResponse = resp
.json()
.await
@@ -131,13 +140,14 @@ pub async fn search_nodes(repo_id: String, query: String) -> Result<SearchRespon
#[server]
pub async fn trigger_graph_build(repo_id: String) -> Result<(), ServerFnError> {
super::agent_client::agent_request(
reqwest::Method::POST,
&format!("/api/v1/graph/{repo_id}/build"),
)
.await?
.send()
.await
.map_err(|e| ServerFnError::new(e.to_string()))?;
let state: super::server_state::ServerState =
dioxus_fullstack::FullstackContext::extract().await?;
let url = format!("{}/api/v1/graph/{repo_id}/build", state.agent_api_url);
let client = reqwest::Client::new();
client
.post(&url)
.send()
.await
.map_err(|e| ServerFnError::new(e.to_string()))?;
Ok(())
}
@@ -12,9 +12,11 @@ pub struct IssuesListResponse {
#[server]
pub async fn fetch_issues(page: u64) -> Result<IssuesListResponse, ServerFnError> {
let resp = super::agent_client::agent_get(&format!("/api/v1/issues?page={page}&limit=20"))
.await?
.send()
let state: super::server_state::ServerState =
dioxus_fullstack::FullstackContext::extract().await?;
let url = format!("{}/api/v1/issues?page={page}&limit=20", state.agent_api_url);
let resp = reqwest::get(&url)
.await
.map_err(|e| ServerFnError::new(e.to_string()))?;
let body: IssuesListResponse = resp
@@ -1,90 +0,0 @@
//! Server-functions for the MCP-tokens management UI.
//!
//! These wrap the agent's `/api/v1/mcp-tokens` CRUD endpoints. The raw
//! token returned by `create_mcp_token` is only visible at creation
//! time — the agent's storage never holds the plaintext.
use dioxus::prelude::*;
use serde::{Deserialize, Serialize};
#[derive(Debug, Clone, Serialize, Deserialize, Default)]
pub struct McpTokenView {
pub id: String,
pub name: String,
pub token_prefix: String,
pub created_by: String,
pub created_at: serde_json::Value,
#[serde(default)]
pub last_used_at: Option<serde_json::Value>,
#[serde(default)]
pub revoked: bool,
}
#[derive(Debug, Clone, Serialize, Deserialize, Default)]
pub struct McpTokensListResponse {
pub data: Vec<McpTokenView>,
}
#[derive(Debug, Clone, Serialize, Deserialize, Default)]
pub struct CreateMcpTokenResponse {
/// Raw token. Shown ONCE — the user must copy it now.
pub token: String,
pub view: McpTokenView,
}
#[server]
pub async fn fetch_mcp_tokens() -> Result<McpTokensListResponse, ServerFnError> {
let resp = super::agent_client::agent_get("/api/v1/mcp-tokens")
.await?
.send()
.await
.map_err(|e| ServerFnError::new(e.to_string()))?;
let body: McpTokensListResponse = resp
.json()
.await
.map_err(|e| ServerFnError::new(e.to_string()))?;
Ok(body)
}
#[server]
pub async fn create_mcp_token(name: String) -> Result<CreateMcpTokenResponse, ServerFnError> {
if name.trim().is_empty() {
return Err(ServerFnError::new("Name is required"));
}
let resp = super::agent_client::agent_request(reqwest::Method::POST, "/api/v1/mcp-tokens")
.await?
.json(&serde_json::json!({ "name": name.trim() }))
.send()
.await
.map_err(|e| ServerFnError::new(e.to_string()))?;
if !resp.status().is_success() {
let body = resp.text().await.unwrap_or_default();
return Err(ServerFnError::new(format!(
"Failed to create token: {body}"
)));
}
let body: CreateMcpTokenResponse = resp
.json()
.await
.map_err(|e| ServerFnError::new(e.to_string()))?;
Ok(body)
}
#[server]
pub async fn revoke_mcp_token(id: String) -> Result<(), ServerFnError> {
let resp = super::agent_client::agent_request(
reqwest::Method::DELETE,
&format!("/api/v1/mcp-tokens/{id}"),
)
.await?
.send()
.await
.map_err(|e| ServerFnError::new(e.to_string()))?;
if !resp.status().is_success() {
let body = resp.text().await.unwrap_or_default();
return Err(ServerFnError::new(format!(
"Failed to revoke token: {body}"
)));
}
Ok(())
}
@@ -8,9 +8,7 @@ pub mod graph;
pub mod help_chat;
pub mod issues;
pub mod mcp;
pub mod mcp_tokens;
pub mod notifications;
pub mod onboarding;
pub mod pentest;
#[allow(clippy::too_many_arguments)]
pub mod repositories;
@@ -20,8 +18,6 @@ pub mod stats;
// Server-only modules
#[cfg(feature = "server")]
mod agent_client;
#[cfg(feature = "server")]
mod auth;
#[cfg(feature = "server")]
mod auth_middleware;
@@ -32,9 +32,11 @@ pub struct NotificationCountResponse {
#[server]
pub async fn fetch_notification_count() -> Result<u64, ServerFnError> {
let resp = super::agent_client::agent_get("/api/v1/notifications/count")
.await?
.send()
let state: super::server_state::ServerState =
dioxus_fullstack::FullstackContext::extract().await?;
let url = format!("{}/api/v1/notifications/count", state.agent_api_url);
let resp = reqwest::get(&url)
.await
.map_err(|e| ServerFnError::new(e.to_string()))?;
let body: NotificationCountResponse = resp
@@ -46,9 +48,11 @@ pub async fn fetch_notification_count() -> Result<u64, ServerFnError> {
#[server]
pub async fn fetch_notifications() -> Result<NotificationListResponse, ServerFnError> {
let resp = super::agent_client::agent_get("/api/v1/notifications?limit=20")
.await?
.send()
let state: super::server_state::ServerState =
dioxus_fullstack::FullstackContext::extract().await?;
let url = format!("{}/api/v1/notifications?limit=20", state.agent_api_url);
let resp = reqwest::get(&url)
.await
.map_err(|e| ServerFnError::new(e.to_string()))?;
let body: NotificationListResponse = resp
@@ -60,8 +64,12 @@ pub async fn fetch_notifications() -> Result<NotificationListResponse, ServerFnE
#[server]
pub async fn mark_all_notifications_read() -> Result<(), ServerFnError> {
super::agent_client::agent_request(reqwest::Method::POST, "/api/v1/notifications/read-all")
.await?
let state: super::server_state::ServerState =
dioxus_fullstack::FullstackContext::extract().await?;
let url = format!("{}/api/v1/notifications/read-all", state.agent_api_url);
reqwest::Client::new()
.post(&url)
.send()
.await
.map_err(|e| ServerFnError::new(e.to_string()))?;
@@ -70,13 +78,14 @@ pub async fn mark_all_notifications_read() -> Result<(), ServerFnError> {
#[server]
pub async fn dismiss_notification(id: String) -> Result<(), ServerFnError> {
super::agent_client::agent_request(
reqwest::Method::PATCH,
&format!("/api/v1/notifications/{id}/dismiss"),
)
.await?
.send()
.await
.map_err(|e| ServerFnError::new(e.to_string()))?;
let state: super::server_state::ServerState =
dioxus_fullstack::FullstackContext::extract().await?;
let url = format!("{}/api/v1/notifications/{id}/dismiss", state.agent_api_url);
reqwest::Client::new()
.patch(&url)
.send()
.await
.map_err(|e| ServerFnError::new(e.to_string()))?;
Ok(())
}

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