Compare commits

..
Author SHA1 Message Date
Sharang ParnerkarandClaude Opus 4.8 f8861419cb test(plc): add realistic OpenPLC-style traffic-light sample
CI / Check (pull_request) Successful in 5m20s
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
Second demo fixture (public-sample shape) to complement the all-rules
pump_station.st: a timed pedestrian-crossing state machine adapted from
the OpenPLC traffic-light example, extended with a SCADA/Modbus uplink and
a maintenance override. Mostly sound control logic with three planted,
field-realistic defects (hardcoded SCADA password, cleartext Modbus master,
maintenance mode that drops the pedestrian safety permit).

The regression test asserts the scanner surfaces those defects while staying
quiet on the guarded duty-cycle division and the JMP-free CASE machine —
demonstrating low false positives on real-world-shaped code.

Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com>
2026-07-16 10:25:31 +02:00
Sharang ParnerkarandClaude Opus 4.8 5e983d699f fix(plc): drop redundant watchdog clause in safety-bypass rule
CI / Check (pull_request) Has been cancelled
CI / Detect Changes (pull_request) Has been cancelled
CI / Deploy Agent (pull_request) Has been cancelled
CI / Deploy Dashboard (pull_request) Has been cancelled
CI / Deploy Docs (pull_request) Has been cancelled
CI / Deploy MCP (pull_request) Has been cancelled
CI clippy (rust 1.94.0, overly_complex_bool_expr) flagged the disabling
check as a logic bug: the `watchdog && matches!(value, Int(0))` term is
fully subsumed by the preceding `matches!(value, Int(0))`. Simplify to
`Bool(false) || Int(0)` — behavior is unchanged (a safety/watchdog signal
driven to FALSE or 0 is still a bypass), and `watchdog` stays used in the
outer guard. All 5 PLC tests still pass.

Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com>
2026-07-16 10:20:54 +02:00
Sharang ParnerkarandClaude Opus 4.8 fcd49ecdf7 feat(pipeline): PLC/SPS control-logic security scanner (IEC 61131-3)
CI / Check (pull_request) Failing after 2m31s
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
Implements ScanType::PlcControlLogic — the missing piece for PlcSps targets,
which previously classified but ran no scan.

New `pipeline::plc`:
- A real IEC 61131-3 Structured Text front end: lexer + recursive-descent parser
  → AST (POUs, typed VAR sections, statements, expressions). Tolerant recovery so
  odd constructs never sink a file.
- PLCopen XML extractor: pulls each ST POU's interface vars + `<ST>` body and
  reconstructs equivalent ST, so raw `.st` files and PLCopen projects share one
  analysis path.
- Eight semantic, guard-aware rules over the AST → findings: hardcoded
  credentials, default/weak passwords, safety-interlock/watchdog bypass, array
  indexed by unvalidated input, division without a zero-guard (suppressed when an
  enclosing `IF <d> <> 0` proves it), insecure comm (auth/encryption disabled),
  and cleartext OT protocol ports, plus unstructured JMP. Each carries CWE +
  remediation.
- `PlcControlLogicScanner` (Scanner impl) walks the project tree and emits
  `Finding`s (dedup fingerprint, file, line, severity).

Wired into `run_target_pipeline`: when the scan plan includes PlcControlLogic,
`run_plc_scan` ingests the PlcProject artifact, analyzes it, and persists the
findings (findings_count handled by run_target).

Demo fixtures under examples/plc-demo/ (a vulnerable pump-station `.st` + a
PLCopen `conveyor.xml`). Tests: parser, all-rules-fire, guarded-clean-is-quiet,
and an end-to-end tree scan — 5 passing.

Adds `roxmltree` (read-only XML) for PLCopen parsing.

Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com>
2026-07-16 09:52:42 +02:00
sharang a981311413 refactor: rip out the legacy TrackedRepository / repositories path (#161)
CI / Check (push) Has been skipped
CI / Detect Changes (push) Successful in 3s
CI / Deploy Agent (push) Successful in 8m20s
CI / Deploy Dashboard (push) Successful in 3m13s
CI / Deploy Docs (push) Has been skipped
CI / Deploy MCP (push) Successful in 2m7s
2026-07-16 07:25:45 +00:00
sharang 87f240b26f feat(onboarding): input validation + editable targets (#160)
CI / Check (push) Has been skipped
CI / Detect Changes (push) Successful in 3s
CI / Deploy Agent (push) Successful in 4m6s
CI / Deploy Dashboard (push) Successful in 3m11s
CI / Deploy Docs (push) Has been skipped
CI / Deploy MCP (push) Has been skipped
2026-07-13 17:57:48 +00:00
57 changed files with 2985 additions and 2131 deletions
Generated
+15 -8
View File
@@ -679,6 +679,7 @@ dependencies = [
"rand 0.9.2", "rand 0.9.2",
"regex", "regex",
"reqwest", "reqwest",
"roxmltree",
"secrecy", "secrecy",
"serde", "serde",
"serde_json", "serde_json",
@@ -2103,7 +2104,7 @@ source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "39cab71617ae0d63f51a36d69f866391735b51691dbda63cf6f96d042b63efeb" checksum = "39cab71617ae0d63f51a36d69f866391735b51691dbda63cf6f96d042b63efeb"
dependencies = [ dependencies = [
"libc", "libc",
"windows-sys 0.52.0", "windows-sys 0.61.2",
] ]
[[package]] [[package]]
@@ -3698,7 +3699,7 @@ version = "0.50.3"
source = "registry+https://github.com/rust-lang/crates.io-index" source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "7957b9740744892f114936ab4a57b3f487491bbeafaf8083688b16841a4240e5" checksum = "7957b9740744892f114936ab4a57b3f487491bbeafaf8083688b16841a4240e5"
dependencies = [ dependencies = [
"windows-sys 0.60.2", "windows-sys 0.61.2",
] ]
[[package]] [[package]]
@@ -4628,6 +4629,12 @@ dependencies = [
"syn", "syn",
] ]
[[package]]
name = "roxmltree"
version = "0.20.0"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "6c20b6793b5c2fa6553b250154b78d6d0db37e72700ae35fad9387a46f487c97"
[[package]] [[package]]
name = "rust-stemmers" name = "rust-stemmers"
version = "1.2.0" version = "1.2.0"
@@ -4679,7 +4686,7 @@ dependencies = [
"errno", "errno",
"libc", "libc",
"linux-raw-sys 0.4.15", "linux-raw-sys 0.4.15",
"windows-sys 0.52.0", "windows-sys 0.59.0",
] ]
[[package]] [[package]]
@@ -4692,7 +4699,7 @@ dependencies = [
"errno", "errno",
"libc", "libc",
"linux-raw-sys 0.12.1", "linux-raw-sys 0.12.1",
"windows-sys 0.52.0", "windows-sys 0.61.2",
] ]
[[package]] [[package]]
@@ -5215,7 +5222,7 @@ version = "0.8.9"
source = "registry+https://github.com/rust-lang/crates.io-index" source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "c1c97747dbf44bb1ca44a561ece23508e99cb592e862f22222dcf42f51d1e451" checksum = "c1c97747dbf44bb1ca44a561ece23508e99cb592e862f22222dcf42f51d1e451"
dependencies = [ dependencies = [
"heck 0.4.1", "heck 0.5.0",
"proc-macro2", "proc-macro2",
"quote", "quote",
"syn", "syn",
@@ -5570,10 +5577,10 @@ source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "82a72c767771b47409d2345987fda8628641887d5466101319899796367354a0" checksum = "82a72c767771b47409d2345987fda8628641887d5466101319899796367354a0"
dependencies = [ dependencies = [
"fastrand", "fastrand",
"getrandom 0.3.4", "getrandom 0.4.1",
"once_cell", "once_cell",
"rustix 1.1.4", "rustix 1.1.4",
"windows-sys 0.52.0", "windows-sys 0.61.2",
] ]
[[package]] [[package]]
@@ -6746,7 +6753,7 @@ version = "0.1.11"
source = "registry+https://github.com/rust-lang/crates.io-index" source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "c2a7b1c03c876122aa43f3020e6c3c3ee5c05081c9a00739faf7503aeba10d22" checksum = "c2a7b1c03c876122aa43f3020e6c3c3ee5c05081c9a00739faf7503aeba10d22"
dependencies = [ dependencies = [
"windows-sys 0.48.0", "windows-sys 0.61.2",
] ]
[[package]] [[package]]
+2
View File
@@ -42,6 +42,8 @@ tokio-cron-scheduler = "0.13"
dotenvy = "0.15" dotenvy = "0.15"
hmac = "0.12" hmac = "0.12"
walkdir = "2" walkdir = "2"
# Read-only XML tree parsing for PLCopen project files (POU extraction).
roxmltree = "0.20"
base64 = "0.22" base64 = "0.22"
urlencoding = "2" urlencoding = "2"
futures-util = "0.3" futures-util = "0.3"
+13 -19
View File
@@ -63,21 +63,12 @@ impl ComplianceAgent {
let db = self.db_pool.for_tenant_id(tenant_id).await?; let db = self.db_pool.for_tenant_id(tenant_id).await?;
let orchestrator = let orchestrator =
PipelineOrchestrator::new(self.config.clone(), db, self.llm.clone(), self.http.clone()); PipelineOrchestrator::new(self.config.clone(), db, self.llm.clone(), self.http.clone());
if self.config.unified_pipeline {
orchestrator.run_target(repo_id, trigger).await orchestrator.run_target(repo_id, trigger).await
} else {
orchestrator.run(repo_id, trigger).await
}
} }
/// Run a scan for an onboarded target through the unified pipeline, /// Alias for [`Self::run_scan`] — every scan runs the unified onboarded-target
/// unconditionally. /// pipeline. Kept as a distinct name for the `/targets/{id}/scan` endpoint's
/// /// intent.
/// Unlike [`Self::run_scan`], this does *not* consult the
/// `unified_pipeline` transition flag: the caller (the `/targets/{id}/scan`
/// endpoint) operates on `onboarded_targets` by construction, so it must
/// always dispatch to `run_target` regardless of how the legacy paths
/// (scheduler, webhooks, `/repositories/{id}/scan`) are configured.
pub async fn run_target_scan( pub async fn run_target_scan(
&self, &self,
tenant_id: &str, tenant_id: &str,
@@ -100,16 +91,19 @@ impl ComplianceAgent {
head_sha: &str, head_sha: &str,
) -> Result<(), crate::error::AgentError> { ) -> Result<(), crate::error::AgentError> {
let db = self.db_pool.for_tenant_id(tenant_id).await?; let db = self.db_pool.for_tenant_id(tenant_id).await?;
let repo = db let oid = mongodb::bson::oid::ObjectId::parse_str(repo_id)
.repositories() .map_err(|e| crate::error::AgentError::Other(e.to_string()))?;
.find_one(mongodb::bson::doc! { let target = db
"_id": mongodb::bson::oid::ObjectId::parse_str(repo_id) .onboarded_targets()
.map_err(|e| crate::error::AgentError::Other(e.to_string()))? .find_one(mongodb::bson::doc! { "_id": oid })
})
.await? .await?
.ok_or_else(|| { .ok_or_else(|| {
crate::error::AgentError::Other(format!("Repository {repo_id} not found")) crate::error::AgentError::Other(format!("Target {repo_id} not found"))
})?; })?;
let code = target.code_artifact().ok_or_else(|| {
crate::error::AgentError::Other(format!("Target {repo_id} has no code artifact"))
})?;
let repo = crate::pipeline::repo_view::RepoView::from_target(&target, code);
let orchestrator = let orchestrator =
PipelineOrchestrator::new(self.config.clone(), db, self.llm.clone(), self.http.clone()); PipelineOrchestrator::new(self.config.clone(), db, self.llm.clone(), self.http.clone());
+12 -4
View File
@@ -146,7 +146,7 @@ pub async fn build_embeddings(
let agent_clone = (*agent).clone(); let agent_clone = (*agent).clone();
tokio::spawn(async move { tokio::spawn(async move {
let repo = match db let repo = match db
.repositories() .onboarded_targets()
.find_one(doc! { "_id": mongodb::bson::oid::ObjectId::parse_str(&repo_id).ok() }) .find_one(doc! { "_id": mongodb::bson::oid::ObjectId::parse_str(&repo_id).ok() })
.await .await
{ {
@@ -194,14 +194,22 @@ pub async fn build_embeddings(
} }
}; };
let code = match repo.code_artifact() {
Some(c) => c,
None => {
tracing::error!("Target {repo_id} has no code artifact for embedding build");
return;
}
};
let view = crate::pipeline::repo_view::RepoView::from_target(&repo, code);
let creds = crate::pipeline::git::RepoCredentials { let creds = crate::pipeline::git::RepoCredentials {
ssh_key_path: Some(agent_clone.config.ssh_key_path.clone()), ssh_key_path: Some(agent_clone.config.ssh_key_path.clone()),
auth_token: repo.auth_token.clone(), auth_token: view.auth_token.clone(),
auth_username: repo.auth_username.clone(), auth_username: view.auth_username.clone(),
}; };
let git_ops = let git_ops =
crate::pipeline::git::GitOps::new(&agent_clone.config.git_clone_base_path, creds); crate::pipeline::git::GitOps::new(&agent_clone.config.git_clone_base_path, creds);
let repo_path = match git_ops.clone_or_fetch(&repo.git_url, &repo.name) { let repo_path = match git_ops.clone_or_fetch(&view.git_url, &view.name) {
Ok(p) => p, Ok(p) => p,
Err(e) => { Err(e) => {
tracing::error!("Failed to clone repo for embedding build: {e}"); tracing::error!("Failed to clone repo for embedding build: {e}");
+13 -5
View File
@@ -255,7 +255,7 @@ pub async fn get_file_content(
// Look up the repository to get repo name // Look up the repository to get repo name
let repo = db let repo = db
.repositories() .onboarded_targets()
.find_one(doc! { "_id": mongodb::bson::oid::ObjectId::parse_str(&repo_id).ok() }) .find_one(doc! { "_id": mongodb::bson::oid::ObjectId::parse_str(&repo_id).ok() })
.await .await
.map_err(|_| StatusCode::INTERNAL_SERVER_ERROR)? .map_err(|_| StatusCode::INTERNAL_SERVER_ERROR)?
@@ -317,7 +317,7 @@ pub async fn trigger_build(
let agent_clone = (*agent).clone(); let agent_clone = (*agent).clone();
tokio::spawn(async move { tokio::spawn(async move {
let repo = match db let repo = match db
.repositories() .onboarded_targets()
.find_one(doc! { "_id": mongodb::bson::oid::ObjectId::parse_str(&repo_id).ok() }) .find_one(doc! { "_id": mongodb::bson::oid::ObjectId::parse_str(&repo_id).ok() })
.await .await
{ {
@@ -328,14 +328,22 @@ pub async fn trigger_build(
} }
}; };
let code = match repo.code_artifact() {
Some(c) => c,
None => {
tracing::error!("Target {repo_id} has no code artifact for graph build");
return;
}
};
let view = crate::pipeline::repo_view::RepoView::from_target(&repo, code);
let creds = crate::pipeline::git::RepoCredentials { let creds = crate::pipeline::git::RepoCredentials {
ssh_key_path: Some(agent_clone.config.ssh_key_path.clone()), ssh_key_path: Some(agent_clone.config.ssh_key_path.clone()),
auth_token: repo.auth_token.clone(), auth_token: view.auth_token.clone(),
auth_username: repo.auth_username.clone(), auth_username: view.auth_username.clone(),
}; };
let git_ops = let git_ops =
crate::pipeline::git::GitOps::new(&agent_clone.config.git_clone_base_path, creds); crate::pipeline::git::GitOps::new(&agent_clone.config.git_clone_base_path, creds);
let repo_path = match git_ops.clone_or_fetch(&repo.git_url, &repo.name) { let repo_path = match git_ops.clone_or_fetch(&view.git_url, &view.name) {
Ok(p) => p, Ok(p) => p,
Err(e) => { Err(e) => {
tracing::error!("Failed to clone repo for graph build: {e}"); tracing::error!("Failed to clone repo for graph build: {e}");
+13 -1
View File
@@ -10,6 +10,18 @@ pub async fn health() -> Json<serde_json::Value> {
Json(serde_json::json!({ "status": "ok" })) 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)] #[tracing::instrument(skip_all)]
pub async fn stats_overview( pub async fn stats_overview(
axum::extract::Extension(agent): AgentExt, axum::extract::Extension(agent): AgentExt,
@@ -19,7 +31,7 @@ pub async fn stats_overview(
let db = &db; let db = &db;
let total_repositories = db let total_repositories = db
.repositories() .onboarded_targets()
.count_documents(doc! {}) .count_documents(doc! {})
.await .await
.unwrap_or(0); .unwrap_or(0);
-2
View File
@@ -12,7 +12,6 @@ pub mod notifications;
pub mod onboarding; pub mod onboarding;
pub mod pentest_handlers; pub mod pentest_handlers;
pub use pentest_handlers as pentest; pub use pentest_handlers as pentest;
pub mod repos;
pub mod sbom; pub mod sbom;
pub mod scans; pub mod scans;
@@ -21,6 +20,5 @@ pub use dto::*;
pub use findings::*; pub use findings::*;
pub use health::*; pub use health::*;
pub use issues::*; pub use issues::*;
pub use repos::*;
pub use sbom::*; pub use sbom::*;
pub use scans::*; pub use scans::*;
+107 -6
View File
@@ -246,15 +246,116 @@ pub async fn delete_target(
.delete_one(doc! { "_id": oid }) .delete_one(doc! { "_id": oid })
.await .await
.map_err(|_| StatusCode::INTERNAL_SERVER_ERROR)?; .map_err(|_| StatusCode::INTERNAL_SERVER_ERROR)?;
// Cascade the collections keyed by repo_id == target id (best-effort). // Cascade all data keyed by repo_id == target id (best-effort).
let by_repo = doc! { "repo_id": &id }; let db = &db;
let _ = db.findings().delete_many(by_repo.clone()).await; let _ = db.findings().delete_many(doc! { "repo_id": &id }).await;
let _ = db.scan_runs().delete_many(by_repo.clone()).await; let _ = db.sbom_entries().delete_many(doc! { "repo_id": &id }).await;
let _ = db.sbom_entries().delete_many(by_repo.clone()).await; let _ = db.scan_runs().delete_many(doc! { "repo_id": &id }).await;
let _ = db.cve_alerts().delete_many(by_repo).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" }))) 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). /// POST /api/v1/targets/{id}/artifacts — attach an artifact (by reference).
#[tracing::instrument(skip_all, fields(target_id = %id))] #[tracing::instrument(skip_all, fields(target_id = %id))]
pub async fn add_artifact( pub async fn add_artifact(
@@ -113,14 +113,14 @@ pub async fn create_session(
session.config = Some(config.clone()); session.config = Some(config.clone());
session.repo_id = target.repo_id.clone(); session.repo_id = target.repo_id.clone();
// Resolve repo_id from git_repo_url if provided // Resolve repo_id (target id) from git_repo_url if provided
if let Some(ref git_url) = config.git_repo_url { if let Some(ref git_url) = config.git_repo_url {
if let Ok(Some(repo)) = db if let Ok(Some(target)) = db
.repositories() .onboarded_targets()
.find_one(doc! { "git_url": git_url }) .find_one(doc! { "artifacts.source_ref": git_url })
.await .await
{ {
session.repo_id = repo.id.map(|oid| oid.to_hex()); session.repo_id = target.id.map(|oid| oid.to_hex());
} }
} }
@@ -380,17 +380,20 @@ pub async fn lookup_repo(
) -> Result<Json<ApiResponse<serde_json::Value>>, StatusCode> { ) -> Result<Json<ApiResponse<serde_json::Value>>, StatusCode> {
let db = tenant_db(&agent, &tenant).await?; let db = tenant_db(&agent, &tenant).await?;
let repo = db let repo = db
.repositories() .onboarded_targets()
.find_one(doc! { "git_url": &params.url }) .find_one(doc! { "artifacts.source_ref": &params.url })
.await .await
.map_err(|_| StatusCode::INTERNAL_SERVER_ERROR)?; .map_err(|_| StatusCode::INTERNAL_SERVER_ERROR)?;
let data = match repo { let data = match repo {
Some(r) => serde_json::json!({ Some(r) => {
let git = r.code_artifact().and_then(|c| c.git.as_ref());
serde_json::json!({
"name": r.name, "name": r.name,
"default_branch": r.default_branch, "default_branch": git.map(|g| g.default_branch.clone()),
"last_scanned_commit": r.last_scanned_commit, "last_scanned_commit": git.and_then(|g| g.last_scanned_commit.clone()),
}), })
}
None => serde_json::Value::Null, None => serde_json::Value::Null,
}; };
-339
View File
@@ -1,339 +0,0 @@
use axum::extract::{Extension, Path, Query};
use axum::http::StatusCode;
use axum::Json;
use mongodb::bson::doc;
use super::dto::*;
use compliance_core::models::*;
use compliance_core::tenant_ctx::TenantCtx;
#[tracing::instrument(skip_all)]
pub async fn list_repositories(
Extension(agent): AgentExt,
tenant: TenantCtx,
Query(params): Query<PaginationParams>,
) -> ApiResult<Vec<TrackedRepository>> {
let db = tenant_db(&agent, &tenant).await?;
let db = &db;
let skip = (params.page.saturating_sub(1)) * params.limit as u64;
let total = db
.repositories()
.count_documents(doc! {})
.await
.unwrap_or(0);
let repos = match db
.repositories()
.find(doc! {})
.skip(skip)
.limit(params.limit)
.await
{
Ok(cursor) => collect_cursor_async(cursor).await,
Err(e) => {
tracing::warn!("Failed to fetch repositories: {e}");
Vec::new()
}
};
Ok(Json(ApiResponse {
data: repos,
total: Some(total),
page: Some(params.page),
}))
}
#[tracing::instrument(skip_all)]
pub async fn add_repository(
Extension(agent): AgentExt,
tenant: TenantCtx,
Json(req): Json<AddRepositoryRequest>,
) -> Result<Json<ApiResponse<TrackedRepository>>, (StatusCode, String)> {
// Validate repository access before saving
let creds = crate::pipeline::git::RepoCredentials {
ssh_key_path: Some(agent.config.ssh_key_path.clone()),
auth_token: req.auth_token.clone(),
auth_username: req.auth_username.clone(),
};
if let Err(e) = crate::pipeline::git::GitOps::test_access(&req.git_url, &creds) {
return Err((
StatusCode::BAD_REQUEST,
format!("Cannot access repository: {e}"),
));
}
let mut repo = TrackedRepository::new(req.name, req.git_url);
repo.default_branch = req.default_branch;
repo.auth_token = req.auth_token;
repo.auth_username = req.auth_username;
repo.tracker_type = req.tracker_type;
repo.tracker_owner = req.tracker_owner;
repo.tracker_repo = req.tracker_repo;
repo.tracker_token = req.tracker_token;
repo.scan_schedule = req.scan_schedule;
let db = tenant_db(&agent, &tenant)
.await
.map_err(|s| (s, "failed to acquire tenant database".to_string()))?;
db.repositories().insert_one(&repo).await.map_err(|_| {
(
StatusCode::CONFLICT,
"Repository already exists".to_string(),
)
})?;
Ok(Json(ApiResponse {
data: repo,
total: None,
page: None,
}))
}
#[tracing::instrument(skip_all, fields(repo_id = %id))]
pub async fn update_repository(
Extension(agent): AgentExt,
tenant: TenantCtx,
Path(id): Path<String>,
Json(req): Json<UpdateRepositoryRequest>,
) -> Result<Json<serde_json::Value>, StatusCode> {
let oid = mongodb::bson::oid::ObjectId::parse_str(&id).map_err(|_| StatusCode::BAD_REQUEST)?;
let db = tenant_db(&agent, &tenant).await?;
let mut set_doc = doc! { "updated_at": mongodb::bson::DateTime::now() };
if let Some(name) = &req.name {
set_doc.insert("name", name);
}
if let Some(branch) = &req.default_branch {
set_doc.insert("default_branch", branch);
}
if let Some(token) = &req.auth_token {
set_doc.insert("auth_token", token);
}
if let Some(username) = &req.auth_username {
set_doc.insert("auth_username", username);
}
if let Some(tracker_type) = &req.tracker_type {
set_doc.insert("tracker_type", tracker_type.to_string());
}
if let Some(owner) = &req.tracker_owner {
set_doc.insert("tracker_owner", owner);
}
if let Some(repo) = &req.tracker_repo {
set_doc.insert("tracker_repo", repo);
}
if let Some(token) = &req.tracker_token {
set_doc.insert("tracker_token", token);
}
if let Some(schedule) = &req.scan_schedule {
set_doc.insert("scan_schedule", schedule);
}
let result = db
.repositories()
.update_one(doc! { "_id": oid }, doc! { "$set": set_doc })
.await
.map_err(|e| {
tracing::warn!("Failed to update repository: {e}");
StatusCode::INTERNAL_SERVER_ERROR
})?;
if result.matched_count == 0 {
return Err(StatusCode::NOT_FOUND);
}
Ok(Json(serde_json::json!({ "status": "updated" })))
}
#[tracing::instrument(skip_all)]
pub async fn get_ssh_public_key(
Extension(agent): AgentExt,
) -> Result<Json<serde_json::Value>, StatusCode> {
let public_path = format!("{}.pub", agent.config.ssh_key_path);
let public_key = std::fs::read_to_string(&public_path).map_err(|_| StatusCode::NOT_FOUND)?;
Ok(Json(serde_json::json!({ "public_key": public_key.trim() })))
}
#[tracing::instrument(skip_all, fields(repo_id = %id))]
pub async fn trigger_scan(
Extension(agent): AgentExt,
tenant: TenantCtx,
Path(id): Path<String>,
) -> Result<Json<serde_json::Value>, StatusCode> {
let agent_clone = (*agent).clone();
let tenant_id = tenant.0.tenant_id.clone();
tokio::spawn(async move {
if let Err(e) = agent_clone
.run_scan(&tenant_id, &id, ScanTrigger::Manual)
.await
{
tracing::error!("Manual scan failed for {id}: {e}");
}
});
Ok(Json(serde_json::json!({ "status": "scan_triggered" })))
}
/// Return the webhook secret for a repository (used by dashboard to display it)
pub async fn get_webhook_config(
Extension(agent): AgentExt,
tenant: TenantCtx,
Path(id): Path<String>,
) -> Result<Json<serde_json::Value>, StatusCode> {
let oid = mongodb::bson::oid::ObjectId::parse_str(&id).map_err(|_| StatusCode::BAD_REQUEST)?;
let db = tenant_db(&agent, &tenant).await?;
let repo = db
.repositories()
.find_one(doc! { "_id": oid })
.await
.map_err(|_| StatusCode::INTERNAL_SERVER_ERROR)?
.ok_or(StatusCode::NOT_FOUND)?;
let tracker_type = repo
.tracker_type
.as_ref()
.map(|t| t.to_string())
.unwrap_or_else(|| "gitea".to_string());
Ok(Json(serde_json::json!({
"webhook_secret": repo.webhook_secret,
"tracker_type": tracker_type,
})))
}
#[tracing::instrument(skip_all, fields(repo_id = %id))]
pub async fn delete_repository(
Extension(agent): AgentExt,
tenant: TenantCtx,
Path(id): Path<String>,
) -> Result<Json<serde_json::Value>, StatusCode> {
let oid = mongodb::bson::oid::ObjectId::parse_str(&id).map_err(|_| StatusCode::BAD_REQUEST)?;
let db = tenant_db(&agent, &tenant).await?;
let db = &db;
// Delete the repository
let result = db
.repositories()
.delete_one(doc! { "_id": oid })
.await
.map_err(|_| StatusCode::INTERNAL_SERVER_ERROR)?;
if result.deleted_count == 0 {
return Err(StatusCode::NOT_FOUND);
}
// Cascade delete all related data
let _ = db.findings().delete_many(doc! { "repo_id": &id }).await;
let _ = db.sbom_entries().delete_many(doc! { "repo_id": &id }).await;
let _ = db.scan_runs().delete_many(doc! { "repo_id": &id }).await;
let _ = db.cve_alerts().delete_many(doc! { "repo_id": &id }).await;
let _ = db
.tracker_issues()
.delete_many(doc! { "repo_id": &id })
.await;
let _ = db.graph_nodes().delete_many(doc! { "repo_id": &id }).await;
let _ = db.graph_edges().delete_many(doc! { "repo_id": &id }).await;
let _ = db.graph_builds().delete_many(doc! { "repo_id": &id }).await;
let _ = db
.impact_analyses()
.delete_many(doc! { "repo_id": &id })
.await;
let _ = db
.code_embeddings()
.delete_many(doc! { "repo_id": &id })
.await;
let _ = db
.embedding_builds()
.delete_many(doc! { "repo_id": &id })
.await;
// Cascade delete DAST targets linked to this repo, and all their downstream data
// (scan runs, findings, pentest sessions, attack chains, messages)
if let Ok(mut cursor) = db.dast_targets().find(doc! { "repo_id": &id }).await {
use futures_util::StreamExt;
while let Some(Ok(target)) = cursor.next().await {
let target_id = target.id.map(|oid| oid.to_hex()).unwrap_or_default();
if !target_id.is_empty() {
cascade_delete_dast_target(db, &target_id).await;
}
}
}
// Also delete pentest sessions linked directly to this repo (not via target)
if let Ok(mut cursor) = db.pentest_sessions().find(doc! { "repo_id": &id }).await {
use futures_util::StreamExt;
while let Some(Ok(session)) = cursor.next().await {
let session_id = session.id.map(|oid| oid.to_hex()).unwrap_or_default();
if !session_id.is_empty() {
let _ = db
.attack_chain_nodes()
.delete_many(doc! { "session_id": &session_id })
.await;
let _ = db
.pentest_messages()
.delete_many(doc! { "session_id": &session_id })
.await;
// Delete DAST findings produced by this session
let _ = db
.dast_findings()
.delete_many(doc! { "session_id": &session_id })
.await;
}
}
}
let _ = db
.pentest_sessions()
.delete_many(doc! { "repo_id": &id })
.await;
Ok(Json(serde_json::json!({ "status": "deleted" })))
}
/// Cascade-delete a DAST target and all its downstream data.
async fn cascade_delete_dast_target(db: &crate::database::Database, target_id: &str) {
// Delete pentest sessions for this target (and their attack chains + messages)
if let Ok(mut cursor) = db
.pentest_sessions()
.find(doc! { "target_id": target_id })
.await
{
use futures_util::StreamExt;
while let Some(Ok(session)) = cursor.next().await {
let session_id = session.id.map(|oid| oid.to_hex()).unwrap_or_default();
if !session_id.is_empty() {
let _ = db
.attack_chain_nodes()
.delete_many(doc! { "session_id": &session_id })
.await;
let _ = db
.pentest_messages()
.delete_many(doc! { "session_id": &session_id })
.await;
let _ = db
.dast_findings()
.delete_many(doc! { "session_id": &session_id })
.await;
}
}
}
let _ = db
.pentest_sessions()
.delete_many(doc! { "target_id": target_id })
.await;
// Delete DAST scan runs and their findings
let _ = db
.dast_findings()
.delete_many(doc! { "target_id": target_id })
.await;
let _ = db
.dast_scan_runs()
.delete_many(doc! { "target_id": target_id })
.await;
// Delete the target itself
if let Ok(oid) = mongodb::bson::oid::ObjectId::parse_str(target_id) {
let _ = db.dast_targets().delete_one(doc! { "_id": oid }).await;
}
}
-14
View File
@@ -11,20 +11,6 @@ pub fn build_router() -> Router {
"/api/v1/settings/ssh-public-key", "/api/v1/settings/ssh-public-key",
get(handlers::get_ssh_public_key), get(handlers::get_ssh_public_key),
) )
.route("/api/v1/repositories", get(handlers::list_repositories))
.route("/api/v1/repositories", post(handlers::add_repository))
.route(
"/api/v1/repositories/{id}/scan",
post(handlers::trigger_scan),
)
.route(
"/api/v1/repositories/{id}",
delete(handlers::delete_repository).patch(handlers::update_repository),
)
.route(
"/api/v1/repositories/{id}/webhook-config",
get(handlers::get_webhook_config),
)
// Unified onboarding targets (#131). // Unified onboarding targets (#131).
.route( .route(
"/api/v1/targets", "/api/v1/targets",
-6
View File
@@ -47,12 +47,6 @@ pub fn load_config() -> Result<AgentConfig, AgentError> {
.unwrap_or_else(|| "/tmp/compliance-scanner/repos".to_string()), .unwrap_or_else(|| "/tmp/compliance-scanner/repos".to_string()),
artifact_store_base_path: env_var_opt("ARTIFACT_STORE_BASE_PATH") artifact_store_base_path: env_var_opt("ARTIFACT_STORE_BASE_PATH")
.unwrap_or_else(|| "/data/compliance-scanner/artifacts".to_string()), .unwrap_or_else(|| "/data/compliance-scanner/artifacts".to_string()),
// Defaults ON: the unified onboarded-target pipeline is now the primary
// path (no legacy `repositories` data in production). Set
// `UNIFIED_PIPELINE=0` to fall back to the legacy repository pipeline.
unified_pipeline: env_var_opt("UNIFIED_PIPELINE")
.map(|v| v == "1" || v.eq_ignore_ascii_case("true"))
.unwrap_or(true),
ssh_key_path: env_var_opt("SSH_KEY_PATH") ssh_key_path: env_var_opt("SSH_KEY_PATH")
.unwrap_or_else(|| "/data/compliance-scanner/ssh/id_ed25519".to_string()), .unwrap_or_else(|| "/data/compliance-scanner/ssh/id_ed25519".to_string()),
keycloak_url: env_var_opt("KEYCLOAK_URL"), keycloak_url: env_var_opt("KEYCLOAK_URL"),
-14
View File
@@ -249,16 +249,6 @@ impl Database {
} }
pub async fn ensure_indexes(&self) -> Result<(), AgentError> { 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 // findings: unique fingerprint
self.findings() self.findings()
.create_index( .create_index(
@@ -479,10 +469,6 @@ impl Database {
Ok(()) Ok(())
} }
pub fn repositories(&self) -> Collection<TrackedRepository> {
self.inner.collection("repositories")
}
pub fn findings(&self) -> Collection<Finding> { pub fn findings(&self) -> Collection<Finding> {
self.inner.collection("findings") self.inner.collection("findings")
} }
-1
View File
@@ -8,7 +8,6 @@ pub mod database;
pub mod error; pub mod error;
pub mod ingest; pub mod ingest;
pub mod llm; pub mod llm;
pub mod migrate;
pub mod pentest; pub mod pentest;
pub mod pipeline; pub mod pipeline;
pub mod rag; pub mod rag;
+1 -54
View File
@@ -1,50 +1,4 @@
use compliance_agent::{agent, api, config, database, migrate, scheduler, ssh, webhooks}; use compliance_agent::{agent, api, config, database, scheduler, ssh, webhooks};
/// Run the `migrate onboarding` subcommand and exit. Backfills (or reverts) the
/// unified `onboarded_targets` collection per tenant.
///
/// Usage: `compliance-agent migrate onboarding [--all | --tenant <id>] [--dry-run] [--revert]`
async fn run_migration(
args: &[String],
pool: &database::DatabasePool,
) -> Result<(), compliance_agent::error::AgentError> {
if args.get(2).map(String::as_str) != Some("onboarding") {
eprintln!(
"usage: compliance-agent migrate onboarding [--all | --tenant <id>] [--dry-run] [--revert]"
);
std::process::exit(2);
}
let has = |flag: &str| args.iter().any(|a| a == flag);
let dry_run = has("--dry-run");
let revert = has("--revert");
let tenant = args
.iter()
.position(|a| a == "--tenant")
.and_then(|i| args.get(i + 1))
.cloned();
let tenants: Vec<String> = if has("--all") {
pool.list_tenant_ids().await?
} else if let Some(t) = tenant {
vec![t]
} else {
eprintln!("specify --all or --tenant <id>");
std::process::exit(2);
};
for tenant_id in tenants {
let db = pool.for_tenant_id(&tenant_id).await?;
if revert {
migrate::onboarding::revert(&db).await?;
println!("[{tenant_id}] reverted onboarding backfill");
} else {
let report = migrate::onboarding::backfill_onboarded_targets(&db, dry_run).await?;
let prefix = if dry_run { "(dry-run) " } else { "" };
println!("[{tenant_id}] {prefix}{report:?}");
}
}
Ok(())
}
#[tokio::main] #[tokio::main]
async fn main() -> Result<(), Box<dyn std::error::Error>> { async fn main() -> Result<(), Box<dyn std::error::Error>> {
@@ -77,13 +31,6 @@ async fn main() -> Result<(), Box<dyn std::error::Error>> {
let db_pool = let db_pool =
database::DatabasePool::connect(&config.mongodb_uri, &config.mongodb_database).await?; database::DatabasePool::connect(&config.mongodb_uri, &config.mongodb_database).await?;
// One-shot subcommands run and exit without starting the servers.
let args: Vec<String> = std::env::args().collect();
if args.get(1).map(String::as_str) == Some("migrate") {
run_migration(&args, &db_pool).await?;
return Ok(());
}
let agent = agent::ComplianceAgent::new(config.clone(), db_pool); let agent = agent::ComplianceAgent::new(config.clone(), db_pool);
tracing::info!("Starting scheduler..."); tracing::info!("Starting scheduler...");
-8
View File
@@ -1,8 +0,0 @@
//! One-time data migrations.
//!
//! Currently just the onboarding backfill ([`onboarding`]), which folds the
//! legacy `repositories` and `dast_targets` collections into the unified
//! `onboarded_targets` collection, preserving `_id` so every downstream record
//! keyed by `repo_id` / `target_id` keeps resolving.
pub mod onboarding;
-406
View File
@@ -1,406 +0,0 @@
//! Backfill: legacy `repositories` + `dast_targets` → `onboarded_targets`.
//!
//! The transforms here are **id-preserving**: an [`OnboardedTarget`] keeps the
//! same `_id` as the `TrackedRepository` / `DastTarget` it came from, so every
//! downstream collection keyed by that hex id (findings, sbom, scan_runs,
//! graph, dast_*, pentest_*) keeps resolving with zero row rewrites, and
//! existing webhook URLs keep working. The mapping functions are pure and unit
//! tested; the DB orchestration (idempotent per-tenant backfill + revert) is a
//! thin driver over them.
use compliance_core::models::{
Artifact, ArtifactKind, DastTarget, DastTargetType, GitArtifactConfig, IssueTrackerConfig,
OnboardedTarget, TargetType, TrackedRepository, WebArtifactConfig,
};
use futures_util::TryStreamExt;
use mongodb::bson::{doc, Document};
use crate::database::Database;
use crate::error::AgentError;
/// Marker id in `schema_migrations` recording that the backfill has run.
const MIGRATION_MARKER: &str = "onboarding_backfill_v1";
/// Summary of a backfill run.
#[derive(Debug, Clone, Default, PartialEq, Eq)]
pub struct MigrationReport {
/// Repositories turned into onboarded targets.
pub repos_migrated: u64,
/// DAST targets folded into an existing (repo-linked) target as a LiveUrl.
pub dast_targets_folded: u64,
/// DAST targets with no repo link, migrated as standalone targets.
pub dast_targets_standalone: u64,
/// Records skipped because a target with that `_id` already existed.
pub skipped_existing: u64,
}
/// Map a legacy `DastTargetType` to a unified [`TargetType`]. REST/GraphQL APIs
/// are backend services; a browser app is a web app.
fn target_type_for_dast(kind: &DastTargetType) -> TargetType {
match kind {
DastTargetType::WebApp => TargetType::WebApp,
DastTargetType::RestApi | DastTargetType::GraphQl => TargetType::BackendService,
}
}
/// Build the LiveUrl artifact for a DAST target (its base URL + crawl config +
/// auth). Shared by fold-in and standalone migration.
pub fn dast_to_artifact(dast: &DastTarget) -> Artifact {
let mut artifact = Artifact::live_url(dast.base_url.clone());
artifact.web = Some(WebArtifactConfig {
target_kind: dast.target_type.clone(),
excluded_paths: dast.excluded_paths.clone(),
max_crawl_depth: dast.max_crawl_depth,
rate_limit: dast.rate_limit,
allow_destructive: dast.allow_destructive,
});
artifact.auth = dast.auth_config.clone().map(Into::into);
artifact
}
/// Map a `TrackedRepository` to an onboarded target, preserving `_id`. The git
/// remote becomes a `GitRepo` artifact carrying the repo's branch, watermark,
/// and auth; tracker config folds into `scan_config`.
///
/// `target_type` is a safe default (`BackendService`) — the classifier can
/// refine it later; `classification` is left `None` (unconfirmed).
pub fn repo_to_target(repo: &TrackedRepository) -> OnboardedTarget {
let mut target = OnboardedTarget::new(repo.name.clone(), TargetType::BackendService);
target.id = repo.id;
let mut artifact = Artifact::git_repo(repo.git_url.clone(), repo.default_branch.clone());
artifact.git = Some(GitArtifactConfig {
default_branch: repo.default_branch.clone(),
last_scanned_commit: repo.last_scanned_commit.clone(),
local_path: repo.local_path.clone(),
});
if repo.auth_token.is_some() || repo.auth_username.is_some() {
artifact.auth = Some(compliance_core::models::ArtifactAuth {
method: "token".to_string(),
username: repo.auth_username.clone(),
secret: repo.auth_token.clone(),
..Default::default()
});
}
target.artifacts.push(artifact);
if repo.tracker_type.is_some() {
target.scan_config.issue_tracker = Some(IssueTrackerConfig {
tracker_type: repo.tracker_type.clone(),
owner: repo.tracker_owner.clone(),
repo: repo.tracker_repo.clone(),
token: repo.tracker_token.clone(),
});
}
target.scan_schedule = repo.scan_schedule.clone();
target.webhook_enabled = repo.webhook_enabled;
target.webhook_secret = repo.webhook_secret.clone();
target.findings_count = repo.findings_count;
target.created_at = repo.created_at;
target.updated_at = repo.updated_at;
target
}
/// Append a DAST target's LiveUrl artifact onto an existing (repo-derived)
/// target. If the repo default was `BackendService` but the DAST target is a
/// browser web app, promote the type to `WebApp`.
pub fn fold_dast_into_target(target: &mut OnboardedTarget, dast: &DastTarget) {
if matches!(dast.target_type, DastTargetType::WebApp)
&& target.target_type == TargetType::BackendService
{
target.target_type = TargetType::WebApp;
}
if !target.has(ArtifactKind::LiveUrl) {
target.artifacts.push(dast_to_artifact(dast));
}
}
/// Map a repo-less DAST target to a standalone onboarded target, preserving `_id`.
pub fn dast_to_standalone_target(dast: &DastTarget) -> OnboardedTarget {
let mut target =
OnboardedTarget::new(dast.name.clone(), target_type_for_dast(&dast.target_type));
target.id = dast.id;
target.artifacts.push(dast_to_artifact(dast));
target.created_at = dast.created_at;
target.updated_at = dast.updated_at;
target
}
/// Whether the onboarding backfill has already been applied to this database.
pub async fn already_applied(db: &Database) -> Result<bool, AgentError> {
let found = db
.collection_named::<Document>("schema_migrations")
.find_one(doc! { "_id": MIGRATION_MARKER })
.await?;
Ok(found.is_some())
}
/// Backfill `onboarded_targets` from `repositories` + `dast_targets` for one
/// tenant database.
///
/// Id-preserving and **idempotent**: targets that already exist (by `_id`) are
/// skipped, so re-running is safe. With `dry_run`, computes the report without
/// writing. The legacy collections are never deleted; the only mutation outside
/// `onboarded_targets` is the history relink of folded DAST targets, which is
/// logged so [`revert`] can undo it.
pub async fn backfill_onboarded_targets(
db: &Database,
dry_run: bool,
) -> Result<MigrationReport, AgentError> {
let mut report = MigrationReport::default();
// 1. repositories -> onboarded_targets (preserve _id, skip existing).
let mut repos = db.repositories().find(doc! {}).await?;
while let Some(repo) = repos.try_next().await? {
let Some(id) = repo.id else { continue };
if db
.onboarded_targets()
.find_one(doc! { "_id": id })
.await?
.is_some()
{
report.skipped_existing += 1;
continue;
}
if !dry_run {
db.onboarded_targets()
.insert_one(repo_to_target(&repo))
.await?;
}
report.repos_migrated += 1;
}
// 2. dast_targets -> fold into the linked repo target, or migrate standalone.
let mut dasts = db.dast_targets().find(doc! {}).await?;
while let Some(dast) = dasts.try_next().await? {
let Some(dast_id) = dast.id else { continue };
let repo_oid = dast
.repo_id
.as_deref()
.and_then(|r| mongodb::bson::oid::ObjectId::parse_str(r).ok());
let linked = match repo_oid {
Some(oid) => db.onboarded_targets().find_one(doc! { "_id": oid }).await?,
None => None,
};
match (linked, repo_oid) {
// Fold into an existing repo-derived target.
(Some(mut target), Some(oid)) => {
if target.has(ArtifactKind::LiveUrl) {
report.skipped_existing += 1; // already folded on a prior run
continue;
}
fold_dast_into_target(&mut target, &dast);
if !dry_run {
db.onboarded_targets()
.replace_one(doc! { "_id": oid }, &target)
.await?;
relink_history(db, &dast_id.to_hex(), &oid.to_hex()).await?;
}
report.dast_targets_folded += 1;
}
// No linked repo target: migrate as a standalone target (keeps _id).
_ => {
if db
.onboarded_targets()
.find_one(doc! { "_id": dast_id })
.await?
.is_some()
{
report.skipped_existing += 1;
continue;
}
if !dry_run {
db.onboarded_targets()
.insert_one(dast_to_standalone_target(&dast))
.await?;
}
report.dast_targets_standalone += 1;
}
}
}
if !dry_run {
db.collection_named::<Document>("schema_migrations")
.update_one(
doc! { "_id": MIGRATION_MARKER },
doc! { "$set": { "applied_at": mongodb::bson::DateTime::now() } },
)
.upsert(true)
.await?;
}
Ok(report)
}
/// Relink DAST scan runs and pentest sessions from the old DAST target id to the
/// unified target id, logging each move so [`revert`] can undo it.
///
/// Note: if multiple DAST targets fold into the same repo target, revert
/// restores only the last-logged mapping — a rare edge. The source collections
/// (`repositories`, `dast_targets`) are never deleted, so no data is lost.
async fn relink_history(db: &Database, old_id: &str, new_id: &str) -> Result<(), AgentError> {
db.dast_scan_runs()
.update_many(
doc! { "target_id": old_id },
doc! { "$set": { "target_id": new_id } },
)
.await?;
db.pentest_sessions()
.update_many(
doc! { "target_id": old_id },
doc! { "$set": { "target_id": new_id } },
)
.await?;
db.collection_named::<Document>("onboarding_migration_log")
.insert_one(doc! { "old_target_id": old_id, "new_target_id": new_id })
.await?;
Ok(())
}
/// Undo the backfill: replay the relink log in reverse, drop `onboarded_targets`
/// and the log, and clear the marker. The legacy collections are untouched, so
/// this restores the pre-migration state.
pub async fn revert(db: &Database) -> Result<(), AgentError> {
let log = db.collection_named::<Document>("onboarding_migration_log");
let mut cursor = log.find(doc! {}).await?;
while let Some(entry) = cursor.try_next().await? {
if let (Ok(old), Ok(new)) = (
entry.get_str("old_target_id"),
entry.get_str("new_target_id"),
) {
db.dast_scan_runs()
.update_many(
doc! { "target_id": new },
doc! { "$set": { "target_id": old } },
)
.await?;
db.pentest_sessions()
.update_many(
doc! { "target_id": new },
doc! { "$set": { "target_id": old } },
)
.await?;
}
}
db.onboarded_targets().drop().await?;
log.drop().await?;
db.collection_named::<Document>("schema_migrations")
.delete_one(doc! { "_id": MIGRATION_MARKER })
.await?;
Ok(())
}
#[cfg(test)]
#[allow(clippy::expect_used, clippy::unwrap_used)]
mod tests {
use super::*;
use compliance_core::models::{DastAuthConfig, TrackerType};
fn repo() -> TrackedRepository {
let mut r = TrackedRepository::new("acme".to_string(), "https://git/acme.git".to_string());
r.id = Some(mongodb::bson::oid::ObjectId::new());
r.default_branch = "develop".to_string();
r.last_scanned_commit = Some("abc123".to_string());
r.auth_token = Some("pat".to_string());
r.auth_username = Some("bob".to_string());
r.tracker_type = Some(TrackerType::Gitea);
r.tracker_owner = Some("acme".to_string());
r.findings_count = 7;
r
}
fn dast(repo_id: Option<String>, kind: DastTargetType) -> DastTarget {
let mut d = DastTarget::new(
"acme-web".to_string(),
"https://acme.example.com".to_string(),
kind,
);
d.id = Some(mongodb::bson::oid::ObjectId::new());
d.repo_id = repo_id;
d.max_crawl_depth = 5;
d.auth_config = Some(DastAuthConfig {
method: "bearer".to_string(),
login_url: None,
username: None,
password: None,
token: Some("tok".to_string()),
headers: None,
});
d
}
#[test]
fn repo_maps_preserving_id_and_git_artifact() {
let r = repo();
let t = repo_to_target(&r);
assert_eq!(t.id, r.id); // id preserved
assert_eq!(t.findings_count, 7);
assert_eq!(t.scan_schedule, r.scan_schedule);
let git = t.code_artifact().expect("git artifact");
assert_eq!(git.kind, ArtifactKind::GitRepo);
assert_eq!(git.source_ref, "https://git/acme.git");
let gc = git.git.as_ref().expect("git config");
assert_eq!(gc.default_branch, "develop");
assert_eq!(gc.last_scanned_commit.as_deref(), Some("abc123"));
let auth = git.auth.as_ref().expect("auth");
assert_eq!(auth.secret.as_deref(), Some("pat"));
assert_eq!(auth.username.as_deref(), Some("bob"));
assert_eq!(
t.scan_config
.issue_tracker
.as_ref()
.and_then(|it| it.tracker_type.clone()),
Some(TrackerType::Gitea)
);
}
#[test]
fn standalone_dast_maps_preserving_id_and_live_url() {
let d = dast(None, DastTargetType::WebApp);
let t = dast_to_standalone_target(&d);
assert_eq!(t.id, d.id);
assert_eq!(t.target_type, TargetType::WebApp);
let url = t.live_url().expect("live url");
assert_eq!(url.source_ref, "https://acme.example.com");
let web = url.web.as_ref().expect("web config");
assert_eq!(web.max_crawl_depth, 5);
assert_eq!(
url.auth.as_ref().and_then(|a| a.secret.clone()),
Some("tok".to_string())
);
}
#[test]
fn rest_api_dast_maps_to_backend_service() {
let d = dast(None, DastTargetType::RestApi);
assert_eq!(
dast_to_standalone_target(&d).target_type,
TargetType::BackendService
);
}
#[test]
fn fold_adds_live_url_and_promotes_webapp() {
let mut t = repo_to_target(&repo());
assert_eq!(t.target_type, TargetType::BackendService);
fold_dast_into_target(&mut t, &dast(Some("x".to_string()), DastTargetType::WebApp));
assert_eq!(t.target_type, TargetType::WebApp); // promoted
assert!(t.has(ArtifactKind::LiveUrl));
assert!(t.has(ArtifactKind::GitRepo));
}
#[test]
fn fold_is_idempotent_on_live_url() {
let mut t = repo_to_target(&repo());
let d = dast(Some("x".to_string()), DastTargetType::WebApp);
fold_dast_into_target(&mut t, &d);
fold_dast_into_target(&mut t, &d);
let live_urls = t
.artifacts
.iter()
.filter(|a| a.kind == ArtifactKind::LiveUrl)
.count();
assert_eq!(live_urls, 1);
}
}
-1
View File
@@ -342,7 +342,6 @@ mod tests {
pentest_imap_password: None, pentest_imap_password: None,
admin_api_token: None, admin_api_token: None,
tenant_registry_url: None, tenant_registry_url: None,
unified_pipeline: false,
} }
} }
+1 -1
View File
@@ -138,7 +138,7 @@ impl GitOps {
/// Build credentials from agent config + per-repo overrides /// Build credentials from agent config + per-repo overrides
pub fn make_repo_credentials( pub fn make_repo_credentials(
config: &compliance_core::AgentConfig, config: &compliance_core::AgentConfig,
repo: &compliance_core::models::TrackedRepository, repo: &crate::pipeline::repo_view::RepoView,
) -> RepoCredentials { ) -> RepoCredentials {
RepoCredentials { RepoCredentials {
ssh_key_path: Some(config.ssh_key_path.clone()), ssh_key_path: Some(config.ssh_key_path.clone()),
@@ -1,5 +1,6 @@
use mongodb::bson::doc; use mongodb::bson::doc;
use crate::pipeline::repo_view::RepoView;
use compliance_core::models::*; use compliance_core::models::*;
use super::orchestrator::{extract_base_url, PipelineOrchestrator}; use super::orchestrator::{extract_base_url, PipelineOrchestrator};
@@ -10,7 +11,7 @@ use crate::trackers;
impl PipelineOrchestrator { impl PipelineOrchestrator {
/// Build an issue tracker client from a repository's tracker configuration. /// Build an issue tracker client from a repository's tracker configuration.
/// Returns `None` if the repo has no tracker configured. /// Returns `None` if the repo has no tracker configured.
pub(super) fn build_tracker(&self, repo: &TrackedRepository) -> Option<TrackerDispatch> { pub(super) fn build_tracker(&self, repo: &RepoView) -> Option<TrackerDispatch> {
let tracker_type = repo.tracker_type.as_ref()?; let tracker_type = repo.tracker_type.as_ref()?;
// Per-repo token takes precedence, fall back to global config // Per-repo token takes precedence, fall back to global config
match tracker_type { match tracker_type {
@@ -81,7 +82,7 @@ impl PipelineOrchestrator {
#[tracing::instrument(skip_all, fields(repo_id = %repo_id))] #[tracing::instrument(skip_all, fields(repo_id = %repo_id))]
pub(super) async fn create_tracker_issues( pub(super) async fn create_tracker_issues(
&self, &self,
repo: &TrackedRepository, repo: &RepoView,
repo_id: &str, repo_id: &str,
new_findings: &[Finding], new_findings: &[Finding],
) -> Result<(), AgentError> { ) -> Result<(), AgentError> {
+2
View File
@@ -10,7 +10,9 @@ pub mod lint;
pub mod orchestrator; pub mod orchestrator;
pub mod patterns; pub mod patterns;
pub mod plan; pub mod plan;
pub mod plc;
mod pr_review; mod pr_review;
pub mod repo_view;
pub mod sbom; pub mod sbom;
pub mod semgrep; pub mod semgrep;
mod tracker_dispatch; mod tracker_dispatch;
+59 -114
View File
@@ -16,6 +16,7 @@ use crate::pipeline::gitleaks::GitleaksScanner;
use crate::pipeline::lint::LintScanner; use crate::pipeline::lint::LintScanner;
use crate::pipeline::patterns::{GdprPatternScanner, OAuthPatternScanner}; use crate::pipeline::patterns::{GdprPatternScanner, OAuthPatternScanner};
use crate::pipeline::plan::build_scan_plan; use crate::pipeline::plan::build_scan_plan;
use crate::pipeline::repo_view::RepoView;
use crate::pipeline::sbom::SbomScanner; use crate::pipeline::sbom::SbomScanner;
use crate::pipeline::semgrep::SemgrepScanner; use crate::pipeline::semgrep::SemgrepScanner;
@@ -51,72 +52,8 @@ impl PipelineOrchestrator {
} }
} }
#[tracing::instrument(skip_all, fields(repo_id = %repo_id, trigger = ?trigger))]
pub async fn run(&self, repo_id: &str, trigger: ScanTrigger) -> Result<(), AgentError> {
// Look up the repository
let repo = self
.db
.repositories()
.find_one(doc! { "_id": mongodb::bson::oid::ObjectId::parse_str(repo_id).map_err(|e| AgentError::Other(e.to_string()))? })
.await?
.ok_or_else(|| AgentError::Other(format!("Repository {repo_id} not found")))?;
// Create scan run
let scan_run = ScanRun::new(repo_id.to_string(), trigger);
let insert = self.db.scan_runs().insert_one(&scan_run).await?;
let scan_run_id = insert
.inserted_id
.as_object_id()
.map(|id| id.to_hex())
.unwrap_or_default();
let result = self.run_pipeline(&repo, &scan_run_id).await;
// Update scan run status
match &result {
Ok(count) => {
self.db
.scan_runs()
.update_one(
doc! { "_id": &insert.inserted_id },
doc! {
"$set": {
"status": "completed",
"current_phase": "completed",
"new_findings_count": *count as i64,
"completed_at": mongodb::bson::DateTime::now(),
}
},
)
.await?;
}
Err(e) => {
tracing::error!(repo_id, error = %e, "Scan pipeline failed");
self.db
.scan_runs()
.update_one(
doc! { "_id": &insert.inserted_id },
doc! {
"$set": {
"status": "failed",
"error_message": e.to_string(),
"completed_at": mongodb::bson::DateTime::now(),
}
},
)
.await?;
}
}
result.map(|_| ())
}
#[tracing::instrument(skip_all, fields(repo_id = repo.name.as_str()))] #[tracing::instrument(skip_all, fields(repo_id = repo.name.as_str()))]
async fn run_pipeline( async fn run_pipeline(&self, repo: &RepoView, scan_run_id: &str) -> Result<u32, AgentError> {
&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(); let repo_id = repo.id.as_ref().map(|id| id.to_hex()).unwrap_or_default();
// Stage 0: Change detection // Stage 0: Change detection
@@ -130,7 +67,6 @@ impl PipelineOrchestrator {
return Ok(0); return Ok(0);
} }
let current_sha = GitOps::get_head_sha(&repo_path)?;
let mut all_findings: Vec<Finding> = Vec::new(); let mut all_findings: Vec<Finding> = Vec::new();
// Stage 1: Semgrep SAST // Stage 1: Semgrep SAST
@@ -396,20 +332,9 @@ impl PipelineOrchestrator {
tracing::warn!("[{repo_id}] Issue creation failed: {e}"); tracing::warn!("[{repo_id}] Issue creation failed: {e}");
} }
// Stage 7: Update repository // The onboarded target's findings_count and the git artifact's
self.db // last_scanned_commit watermark are persisted by `finalize_target` after
.repositories() // `run_pipeline` returns.
.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) // Stage 8: DAST (async, optional — only if a DastTarget is configured)
tracing::info!("[{repo_id}] Stage 8: Checking for DAST targets"); tracing::info!("[{repo_id}] Stage 8: Checking for DAST targets");
@@ -524,9 +449,14 @@ impl PipelineOrchestrator {
// wizard-created targets, not just migrated ones. // wizard-created targets, not just migrated ones.
self.ensure_dast_target(target, &plan).await; self.ensure_dast_target(target, &plan).await;
// PLC control-logic analysis for PLC/SPS targets (a PlcProject artifact).
if plan.has(ScanType::PlcControlLogic) {
return self.run_plc_scan(target, &target_id, scan_run_id).await;
}
match target.code_artifact() { match target.code_artifact() {
Some(code) if code.kind == ArtifactKind::GitRepo => { Some(code) if code.kind == ArtifactKind::GitRepo => {
let repo = repo_view_from_target(target, code); let repo = RepoView::from_target(target, code);
let new_count = self.run_pipeline(&repo, scan_run_id).await?; let new_count = self.run_pipeline(&repo, scan_run_id).await?;
self.finalize_target(target, &repo, new_count).await?; self.finalize_target(target, &repo, new_count).await?;
Ok(new_count) Ok(new_count)
@@ -553,6 +483,52 @@ impl PipelineOrchestrator {
} }
} }
/// 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)?;
let path = target
.first_of(ArtifactKind::PlcProject)
.and_then(|a| ingest_set.get(&a.id))
.and_then(|ia| ia.working_path.clone());
let Some(path) = path else {
tracing::warn!(target_id, "PLC scan: no ingested PLC project path");
return Ok(0);
};
let findings = crate::pipeline::plc::analyze_tree(&path, target_id);
tracing::info!(
target_id,
found = findings.len(),
"PLC control-logic analysis 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)
}
/// Ingest the target's artifacts, classify (tramiton for firmware/RTOS/Yocto, /// Ingest the target's artifacts, classify (tramiton for firmware/RTOS/Yocto,
/// heuristics otherwise), and store the detected classification on the target. /// heuristics otherwise), and store the detected classification on the target.
/// Best-effort — never fails the scan. /// Best-effort — never fails the scan.
@@ -703,7 +679,7 @@ impl PipelineOrchestrator {
async fn finalize_target( async fn finalize_target(
&self, &self,
target: &OnboardedTarget, target: &OnboardedTarget,
repo: &TrackedRepository, repo: &RepoView,
new_count: u32, new_count: u32,
) -> Result<(), AgentError> { ) -> Result<(), AgentError> {
let oid = match target.id { let oid = match target.id {
@@ -751,37 +727,6 @@ impl PipelineOrchestrator {
} }
} }
/// Build a legacy `TrackedRepository` view from an onboarded target's code
/// artifact, so the unified pipeline can reuse the existing repo pipeline. The
/// inverse of the migration's `repo_to_target`. `_id` is preserved so findings
/// and DAST lookups resolve against the same key.
fn repo_view_from_target(target: &OnboardedTarget, code: &Artifact) -> TrackedRepository {
let mut repo = TrackedRepository::new(target.name.clone(), code.source_ref.clone());
repo.id = target.id;
if let Some(git) = &code.git {
repo.default_branch = git.default_branch.clone();
repo.last_scanned_commit = git.last_scanned_commit.clone();
repo.local_path = git.local_path.clone();
}
if let Some(auth) = &code.auth {
repo.auth_token = auth.secret.clone();
repo.auth_username = auth.username.clone();
}
if let Some(it) = &target.scan_config.issue_tracker {
repo.tracker_type = it.tracker_type.clone();
repo.tracker_owner = it.owner.clone();
repo.tracker_repo = it.repo.clone();
repo.tracker_token = it.token.clone();
}
repo.scan_schedule = target.scan_schedule.clone();
repo.webhook_enabled = target.webhook_enabled;
repo.webhook_secret = target.webhook_secret.clone();
repo.findings_count = target.findings_count;
repo.created_at = target.created_at;
repo.updated_at = target.updated_at;
repo
}
/// Extract the scheme + host from a git URL. /// Extract the scheme + host from a git URL.
/// e.g. "https://gitea.example.com/owner/repo.git" -> "https://gitea.example.com" /// e.g. "https://gitea.example.com/owner/repo.git" -> "https://gitea.example.com"
/// e.g. "ssh://git@gitea.example.com:22/owner/repo.git" -> "https://gitea.example.com" /// e.g. "ssh://git@gitea.example.com:22/owner/repo.git" -> "https://gitea.example.com"
@@ -840,7 +785,7 @@ mod tests {
target.artifacts.push(artifact); target.artifacts.push(artifact);
let code = target.code_artifact().expect("code artifact"); let code = target.code_artifact().expect("code artifact");
let repo = repo_view_from_target(&target, code); let repo = RepoView::from_target(&target, code);
assert_eq!(repo.id, target.id); // preserved assert_eq!(repo.id, target.id); // preserved
assert_eq!(repo.git_url, "https://git/acme.git"); assert_eq!(repo.git_url, "https://git/acme.git");
+226
View File
@@ -0,0 +1,226 @@
//! Abstract syntax tree for IEC 61131-3 Structured Text (ST).
//!
//! This is the security-relevant subset: POUs with their variable declarations
//! and statement bodies, enough to run semantic control-logic rules over. It is
//! deliberately not a full language model — declarations we don't reason about
//! (e.g. exotic type definitions) are parsed loosely and kept as raw text.
/// A Program Organization Unit: a PROGRAM, FUNCTION, or FUNCTION_BLOCK.
#[derive(Debug, Clone)]
pub struct Pou {
pub name: String,
pub kind: PouKind,
/// The declared variables, across all VAR_* sections.
pub vars: Vec<VarDecl>,
/// The statement body.
pub body: Vec<Stmt>,
/// 1-based line where the POU header appears (in the source that was parsed).
pub line: u32,
}
#[derive(Debug, Clone, Copy, PartialEq, Eq)]
pub enum PouKind {
Program,
Function,
FunctionBlock,
}
impl PouKind {
pub fn label(self) -> &'static str {
match self {
PouKind::Program => "PROGRAM",
PouKind::Function => "FUNCTION",
PouKind::FunctionBlock => "FUNCTION_BLOCK",
}
}
}
/// A single declared variable.
#[derive(Debug, Clone)]
pub struct VarDecl {
pub name: String,
pub section: VarSection,
/// The declared type as written (e.g. `BOOL`, `INT`, `ARRAY[0..9] OF INT`).
pub type_name: String,
/// Whether the type is an ARRAY, and its declared bounds `(lo, hi)` when
/// they are literal integers — used by the array-bounds rule.
pub array_bounds: Option<(i64, i64)>,
/// The initializer expression, if any (`:= <expr>`).
pub init: Option<Expr>,
pub line: u32,
}
#[derive(Debug, Clone, Copy, PartialEq, Eq)]
pub enum VarSection {
Var,
Input,
Output,
InOut,
Global,
Temp,
External,
}
/// A statement.
#[derive(Debug, Clone)]
pub enum Stmt {
Assign {
target: Expr,
value: Expr,
line: u32,
},
If {
/// (condition, body) for IF and each ELSIF, in order.
branches: Vec<(Expr, Vec<Stmt>)>,
else_body: Option<Vec<Stmt>>,
line: u32,
},
Case {
selector: Expr,
/// (label expressions, body) per CASE arm.
arms: Vec<(Vec<Expr>, Vec<Stmt>)>,
else_body: Option<Vec<Stmt>>,
line: u32,
},
For {
var: String,
from: Expr,
to: Expr,
by: Option<Expr>,
body: Vec<Stmt>,
line: u32,
},
While {
cond: Expr,
body: Vec<Stmt>,
line: u32,
},
Repeat {
body: Vec<Stmt>,
until: Expr,
line: u32,
},
/// A bare call statement, e.g. `TON1(IN := x, PT := T#5s);`.
Call {
callee: String,
args: Vec<CallArg>,
line: u32,
},
Return {
line: u32,
},
Exit {
line: u32,
},
/// `JMP label;` — an unstructured jump.
Jump {
label: String,
line: u32,
},
/// `label:` — a jump target.
Label {
name: String,
line: u32,
},
}
/// One argument in a call: positional (`name: None`) or named (`X := expr`).
#[derive(Debug, Clone)]
pub struct CallArg {
pub name: Option<String>,
pub value: Expr,
}
/// An expression.
#[derive(Debug, Clone)]
pub enum Expr {
Int(i64, u32),
Real(f64, u32),
Bool(bool, u32),
/// A string literal, with the unquoted contents.
Str(String, u32),
/// A duration / date / time literal, kept as raw text (`T#5s`, `DT#...`).
Time(String, u32),
Ident(String, u32),
/// `base[index]`.
Index {
base: Box<Expr>,
index: Box<Expr>,
line: u32,
},
/// `base.field`.
Member {
base: Box<Expr>,
field: String,
line: u32,
},
Unary {
op: UnOp,
expr: Box<Expr>,
line: u32,
},
Binary {
op: BinOp,
lhs: Box<Expr>,
rhs: Box<Expr>,
line: u32,
},
/// A function call used as an expression, e.g. `LIMIT(a, b, c)`.
Call {
callee: String,
args: Vec<CallArg>,
line: u32,
},
}
impl Expr {
/// The 1-based source line this expression starts on.
pub fn line(&self) -> u32 {
match self {
Expr::Int(_, l)
| Expr::Real(_, l)
| Expr::Bool(_, l)
| Expr::Str(_, l)
| Expr::Time(_, l)
| Expr::Ident(_, l)
| Expr::Index { line: l, .. }
| Expr::Member { line: l, .. }
| Expr::Unary { line: l, .. }
| Expr::Binary { line: l, .. }
| Expr::Call { line: l, .. } => *l,
}
}
/// If this expression is a plain identifier, its name.
pub fn as_ident(&self) -> Option<&str> {
match self {
Expr::Ident(name, _) => Some(name.as_str()),
_ => None,
}
}
}
#[derive(Debug, Clone, Copy, PartialEq, Eq)]
pub enum UnOp {
Not,
Neg,
}
#[derive(Debug, Clone, Copy, PartialEq, Eq)]
pub enum BinOp {
Add,
Sub,
Mul,
Div,
Mod,
Pow,
Eq,
Ne,
Lt,
Le,
Gt,
Ge,
And,
Or,
Xor,
}
+372
View File
@@ -0,0 +1,372 @@
//! Lexer for IEC 61131-3 Structured Text.
//!
//! Tokenizes ST source into a flat token stream with 1-based line numbers.
//! Keywords are case-insensitive. Handles `(* *)` and `//` comments, `'..'` and
//! `".."` strings (with `''`/`""` escapes), based integers (`16#FF`, `2#1010`),
//! and duration/date literals (`T#5s`, `DT#...`) kept as raw text.
/// A lexed token with its source line.
#[derive(Debug, Clone)]
pub struct Token {
pub kind: Tok,
pub line: u32,
}
#[derive(Debug, Clone, PartialEq)]
pub enum Tok {
Int(i64),
Real(f64),
Str(String),
Time(String),
Bool(bool),
Ident(String),
Kw(Keyword),
Assign, // :=
Plus, // +
Minus, // -
Star, // *
Slash, // /
Power, // **
LParen, // (
RParen, // )
LBrack, // [
RBrack, // ]
Dot, // .
DotDot, // ..
Comma, // ,
Semi, // ;
Colon, // :
Lt, // <
Le, // <=
Gt, // >
Ge, // >=
Eq, // =
Ne, // <>
Amp, // &
Eof,
}
#[derive(Debug, Clone, Copy, PartialEq, Eq)]
pub enum Keyword {
Program,
EndProgram,
Function,
EndFunction,
FunctionBlock,
EndFunctionBlock,
Var,
VarInput,
VarOutput,
VarInOut,
VarGlobal,
VarTemp,
VarExternal,
Constant,
EndVar,
Array,
Of,
If,
Then,
Elsif,
Else,
EndIf,
Case,
EndCase,
For,
To,
By,
Do,
EndFor,
While,
EndWhile,
Repeat,
Until,
EndRepeat,
Return,
Exit,
Jmp,
Not,
And,
Or,
Xor,
Mod,
Type,
EndType,
Struct,
EndStruct,
}
fn keyword_from(word: &str) -> Option<Keyword> {
use Keyword::*;
Some(match word.to_ascii_uppercase().as_str() {
"PROGRAM" => Program,
"END_PROGRAM" => EndProgram,
"FUNCTION" => Function,
"END_FUNCTION" => EndFunction,
"FUNCTION_BLOCK" => FunctionBlock,
"END_FUNCTION_BLOCK" => EndFunctionBlock,
"VAR" => Var,
"VAR_INPUT" => VarInput,
"VAR_OUTPUT" => VarOutput,
"VAR_IN_OUT" => VarInOut,
"VAR_GLOBAL" => VarGlobal,
"VAR_TEMP" => VarTemp,
"VAR_EXTERNAL" => VarExternal,
"CONSTANT" => Constant,
"END_VAR" => EndVar,
"ARRAY" => Array,
"OF" => Of,
"IF" => If,
"THEN" => Then,
"ELSIF" => Elsif,
"ELSE" => Else,
"END_IF" => EndIf,
"CASE" => Case,
"END_CASE" => EndCase,
"FOR" => For,
"TO" => To,
"BY" => By,
"DO" => Do,
"END_FOR" => EndFor,
"WHILE" => While,
"END_WHILE" => EndWhile,
"REPEAT" => Repeat,
"UNTIL" => Until,
"END_REPEAT" => EndRepeat,
"RETURN" => Return,
"EXIT" => Exit,
"JMP" => Jmp,
"NOT" => Not,
"AND" => And,
"OR" => Or,
"XOR" => Xor,
"MOD" => Mod,
"TYPE" => Type,
"END_TYPE" => EndType,
"STRUCT" => Struct,
"END_STRUCT" => EndStruct,
_ => return None,
})
}
/// Tokenize `src`. Unknown characters are skipped (best-effort — a scanner must
/// not die on odd input).
pub fn lex(src: &str) -> Vec<Token> {
let chars: Vec<char> = src.chars().collect();
let mut i = 0usize;
let mut line = 1u32;
let mut out = Vec::new();
let bump_line = |c: char, line: &mut u32| {
if c == '\n' {
*line += 1;
}
};
while i < chars.len() {
let c = chars[i];
// Whitespace.
if c.is_whitespace() {
bump_line(c, &mut line);
i += 1;
continue;
}
// Line comment: //
if c == '/' && i + 1 < chars.len() && chars[i + 1] == '/' {
while i < chars.len() && chars[i] != '\n' {
i += 1;
}
continue;
}
// Block comment: (* ... *)
if c == '(' && i + 1 < chars.len() && chars[i + 1] == '*' {
i += 2;
while i + 1 < chars.len() && !(chars[i] == '*' && chars[i + 1] == ')') {
bump_line(chars[i], &mut line);
i += 1;
}
i = (i + 2).min(chars.len());
continue;
}
let tok_line = line;
// String literal: '...' or "..."
if c == '\'' || c == '"' {
let quote = c;
i += 1;
let mut s = String::new();
while i < chars.len() {
let ch = chars[i];
if ch == quote {
// Doubled quote is an escaped quote.
if i + 1 < chars.len() && chars[i + 1] == quote {
s.push(quote);
i += 2;
continue;
}
i += 1;
break;
}
bump_line(ch, &mut line);
s.push(ch);
i += 1;
}
out.push(Token {
kind: Tok::Str(s),
line: tok_line,
});
continue;
}
// Identifier / keyword / time literal / boolean.
if c.is_ascii_alphabetic() || c == '_' {
let start = i;
while i < chars.len() && (chars[i].is_ascii_alphanumeric() || chars[i] == '_') {
i += 1;
}
let word: String = chars[start..i].iter().collect();
// Duration/date/time literal prefix: T#, TIME#, DT#, D#, TOD#, LT# ...
if i < chars.len() && chars[i] == '#' {
let up = word.to_ascii_uppercase();
if matches!(
up.as_str(),
"T" | "TIME" | "DT" | "D" | "TOD" | "LT" | "DATE"
) {
let lit_start = start;
i += 1; // consume '#'
while i < chars.len()
&& (chars[i].is_ascii_alphanumeric()
|| chars[i] == '.'
|| chars[i] == '_'
|| chars[i] == ':')
{
i += 1;
}
let lit: String = chars[lit_start..i].iter().collect();
out.push(Token {
kind: Tok::Time(lit),
line: tok_line,
});
continue;
}
}
let kind = match word.to_ascii_uppercase().as_str() {
"TRUE" => Tok::Bool(true),
"FALSE" => Tok::Bool(false),
_ => match keyword_from(&word) {
Some(kw) => Tok::Kw(kw),
None => Tok::Ident(word),
},
};
out.push(Token {
kind,
line: tok_line,
});
continue;
}
// Number: decimal, real, or based (16#..., 2#...).
if c.is_ascii_digit() {
let start = i;
while i < chars.len() && (chars[i].is_ascii_digit() || chars[i] == '_') {
i += 1;
}
// Based literal: <base>#<digits>
if i < chars.len() && chars[i] == '#' {
let base_str: String = chars[start..i].iter().filter(|c| **c != '_').collect();
i += 1;
let dstart = i;
while i < chars.len() && (chars[i].is_ascii_alphanumeric() || chars[i] == '_') {
i += 1;
}
let digits: String = chars[dstart..i].iter().filter(|c| **c != '_').collect();
let radix = base_str.parse::<u32>().unwrap_or(10);
let val = i64::from_str_radix(&digits, radix.clamp(2, 36)).unwrap_or(0);
out.push(Token {
kind: Tok::Int(val),
line: tok_line,
});
continue;
}
// Real: has a '.' (not '..') or exponent.
let is_real =
i < chars.len() && chars[i] == '.' && !(i + 1 < chars.len() && chars[i + 1] == '.');
if is_real {
i += 1;
while i < chars.len() && (chars[i].is_ascii_digit() || chars[i] == '_') {
i += 1;
}
let raw: String = chars[start..i].iter().filter(|c| **c != '_').collect();
out.push(Token {
kind: Tok::Real(raw.parse().unwrap_or(0.0)),
line: tok_line,
});
continue;
}
let raw: String = chars[start..i].iter().filter(|c| **c != '_').collect();
out.push(Token {
kind: Tok::Int(raw.parse().unwrap_or(0)),
line: tok_line,
});
continue;
}
// Operators / punctuation (longest match first).
let two: String = chars[i..(i + 2).min(chars.len())].iter().collect();
let kind = match two.as_str() {
":=" => Some(Tok::Assign),
"<=" => Some(Tok::Le),
">=" => Some(Tok::Ge),
"<>" => Some(Tok::Ne),
".." => Some(Tok::DotDot),
"**" => Some(Tok::Power),
_ => None,
};
if let Some(k) = kind {
out.push(Token {
kind: k,
line: tok_line,
});
i += 2;
continue;
}
let one = match c {
'+' => Some(Tok::Plus),
'-' => Some(Tok::Minus),
'*' => Some(Tok::Star),
'/' => Some(Tok::Slash),
'(' => Some(Tok::LParen),
')' => Some(Tok::RParen),
'[' => Some(Tok::LBrack),
']' => Some(Tok::RBrack),
'.' => Some(Tok::Dot),
',' => Some(Tok::Comma),
';' => Some(Tok::Semi),
':' => Some(Tok::Colon),
'<' => Some(Tok::Lt),
'>' => Some(Tok::Gt),
'=' => Some(Tok::Eq),
'&' => Some(Tok::Amp),
_ => None,
};
if let Some(k) = one {
out.push(Token {
kind: k,
line: tok_line,
});
}
i += 1;
}
out.push(Token {
kind: Tok::Eof,
line,
});
out
}
+200
View File
@@ -0,0 +1,200 @@
//! 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;
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"
);
}
}
+766
View File
@@ -0,0 +1,766 @@
//! Recursive-descent parser for the security-relevant subset of Structured Text.
//!
//! Tolerant by design: it parses the POUs, variable sections, and statement
//! bodies it understands, and skips (with statement/POU-level recovery) anything
//! it does not, so a single odd construct never sinks the whole file.
use super::ast::*;
use super::lexer::{Keyword as K, Tok, Token};
pub struct Parser {
toks: Vec<Token>,
pos: usize,
}
impl Parser {
pub fn new(toks: Vec<Token>) -> Self {
Self { toks, pos: 0 }
}
// ── token helpers ──────────────────────────────────────────────
fn peek(&self) -> &Tok {
&self.toks[self.pos.min(self.toks.len() - 1)].kind
}
fn line(&self) -> u32 {
self.toks[self.pos.min(self.toks.len() - 1)].line
}
fn at_end(&self) -> bool {
matches!(self.peek(), Tok::Eof)
}
fn advance(&mut self) -> Tok {
let t = self.toks[self.pos.min(self.toks.len() - 1)].kind.clone();
if self.pos < self.toks.len() - 1 {
self.pos += 1;
}
t
}
fn eat(&mut self, t: &Tok) -> bool {
if self.peek() == t {
self.advance();
true
} else {
false
}
}
fn eat_kw(&mut self, k: K) -> bool {
if matches!(self.peek(), Tok::Kw(x) if *x == k) {
self.advance();
true
} else {
false
}
}
fn at_kw(&self, k: K) -> bool {
matches!(self.peek(), Tok::Kw(x) if *x == k)
}
fn ident(&mut self) -> Option<String> {
if let Tok::Ident(s) = self.peek() {
let s = s.clone();
self.advance();
Some(s)
} else {
None
}
}
// ── top level ──────────────────────────────────────────────────
/// Parse every POU in the token stream.
pub fn parse_units(&mut self) -> Vec<Pou> {
let mut pous = Vec::new();
while !self.at_end() {
match self.peek() {
Tok::Kw(K::Program) => {
self.advance();
if let Some(p) = self.parse_pou(PouKind::Program, K::EndProgram) {
pous.push(p);
}
}
Tok::Kw(K::Function) => {
self.advance();
if let Some(p) = self.parse_pou(PouKind::Function, K::EndFunction) {
pous.push(p);
}
}
Tok::Kw(K::FunctionBlock) => {
self.advance();
if let Some(p) = self.parse_pou(PouKind::FunctionBlock, K::EndFunctionBlock) {
pous.push(p);
}
}
// Skip TYPE...END_TYPE and anything else at top level.
_ => {
self.advance();
}
}
}
pous
}
fn parse_pou(&mut self, kind: PouKind, end: K) -> Option<Pou> {
let line = self.line();
let name = self.ident().unwrap_or_else(|| "<anonymous>".to_string());
// Optional `: return_type` for functions.
if self.eat(&Tok::Colon) {
let _ = self.advance(); // return type token
}
let mut vars = Vec::new();
// Variable sections precede the body.
while let Some(section) = self.var_section_kw() {
self.advance();
let _ = self.eat_kw(K::Constant); // CONSTANT is informational for our rules
self.parse_var_decls(section, &mut vars);
}
// Body statements until END_<kind>.
let mut body = Vec::new();
while !self.at_end() && !self.at_kw(end) {
if let Some(s) = self.parse_stmt() {
body.push(s);
}
}
self.eat_kw(end);
Some(Pou {
name,
kind,
vars,
body,
line,
})
}
fn var_section_kw(&self) -> Option<VarSection> {
match self.peek() {
Tok::Kw(K::Var) => Some(VarSection::Var),
Tok::Kw(K::VarInput) => Some(VarSection::Input),
Tok::Kw(K::VarOutput) => Some(VarSection::Output),
Tok::Kw(K::VarInOut) => Some(VarSection::InOut),
Tok::Kw(K::VarGlobal) => Some(VarSection::Global),
Tok::Kw(K::VarTemp) => Some(VarSection::Temp),
Tok::Kw(K::VarExternal) => Some(VarSection::External),
_ => None,
}
}
fn parse_var_decls(&mut self, section: VarSection, out: &mut Vec<VarDecl>) {
while !self.at_end() && !self.at_kw(K::EndVar) {
let line = self.line();
// names: a, b, c
let mut names = Vec::new();
match self.ident() {
Some(n) => names.push(n),
None => {
// Not a declaration we understand — skip to next ; or END_VAR.
self.sync_decl();
continue;
}
}
while self.eat(&Tok::Comma) {
if let Some(n) = self.ident() {
names.push(n);
}
}
if !self.eat(&Tok::Colon) {
self.sync_decl();
continue;
}
let (type_name, array_bounds) = self.parse_type();
let init = if self.eat(&Tok::Assign) {
Some(self.parse_expr())
} else {
None
};
self.eat(&Tok::Semi);
for n in names {
out.push(VarDecl {
name: n,
section,
type_name: type_name.clone(),
array_bounds,
init: init.clone(),
line,
});
}
}
self.eat_kw(K::EndVar);
}
/// Parse a (possibly ARRAY) type, returning its rendered name and literal
/// bounds when present.
fn parse_type(&mut self) -> (String, Option<(i64, i64)>) {
if self.eat_kw(K::Array) {
let mut bounds = None;
if self.eat(&Tok::LBrack) {
let lo = self.int_lit();
self.eat(&Tok::DotDot);
let hi = self.int_lit();
if let (Some(lo), Some(hi)) = (lo, hi) {
bounds = Some((lo, hi));
}
// Skip any further dimensions / tokens to the closing bracket.
while !self.at_end() && !self.eat(&Tok::RBrack) {
self.advance();
}
}
self.eat_kw(K::Of);
let elem = self.type_ident();
(format!("ARRAY OF {elem}"), bounds)
} else {
(self.type_ident(), None)
}
}
fn type_ident(&mut self) -> String {
// Types can be qualified idents; keep it simple: one token, plus any
// string-length suffix like STRING[80].
let base = match self.advance() {
Tok::Ident(s) => s,
Tok::Kw(_) => "TYPE".to_string(),
other => format!("{other:?}"),
};
if self.eat(&Tok::LBrack) {
while !self.at_end() && !self.eat(&Tok::RBrack) {
self.advance();
}
}
base
}
fn int_lit(&mut self) -> Option<i64> {
match self.peek() {
Tok::Int(n) => {
let n = *n;
self.advance();
Some(n)
}
Tok::Minus => {
self.advance();
if let Tok::Int(n) = self.peek() {
let n = -*n;
self.advance();
Some(n)
} else {
None
}
}
_ => None,
}
}
fn sync_decl(&mut self) {
while !self.at_end() && !self.eat(&Tok::Semi) && !self.at_kw(K::EndVar) {
self.advance();
}
}
fn sync_stmt(&mut self) {
while !self.at_end() && !self.eat(&Tok::Semi) {
// Stop at block terminators so recovery doesn't swallow structure.
if matches!(
self.peek(),
Tok::Kw(
K::EndIf
| K::EndFor
| K::EndWhile
| K::EndCase
| K::EndRepeat
| K::EndProgram
| K::EndFunction
| K::EndFunctionBlock
| K::Else
| K::Elsif
)
) {
return;
}
self.advance();
}
}
// ── statements ─────────────────────────────────────────────────
fn parse_stmt(&mut self) -> Option<Stmt> {
let line = self.line();
match self.peek().clone() {
Tok::Semi => {
self.advance();
None
}
Tok::Kw(K::If) => self.parse_if(),
Tok::Kw(K::Case) => self.parse_case(),
Tok::Kw(K::For) => self.parse_for(),
Tok::Kw(K::While) => self.parse_while(),
Tok::Kw(K::Repeat) => self.parse_repeat(),
Tok::Kw(K::Return) => {
self.advance();
self.eat(&Tok::Semi);
Some(Stmt::Return { line })
}
Tok::Kw(K::Exit) => {
self.advance();
self.eat(&Tok::Semi);
Some(Stmt::Exit { line })
}
Tok::Kw(K::Jmp) => {
self.advance();
let label = self.ident().unwrap_or_default();
self.eat(&Tok::Semi);
Some(Stmt::Jump { label, line })
}
Tok::Ident(name) => {
// Could be `label:`, `call(...)`, or an assignment.
// Lookahead: ident ':' (not ':=') → label.
if matches!(
self.toks.get(self.pos + 1).map(|t| &t.kind),
Some(Tok::Colon)
) && !matches!(self.toks.get(self.pos + 2).map(|t| &t.kind), Some(Tok::Eq))
{
self.advance(); // ident
self.advance(); // ':'
return Some(Stmt::Label { name, line });
}
let lhs = self.parse_expr();
if self.eat(&Tok::Assign) {
let value = self.parse_expr();
self.eat(&Tok::Semi);
Some(Stmt::Assign {
target: lhs,
value,
line,
})
} else if let Expr::Call { callee, args, .. } = lhs {
self.eat(&Tok::Semi);
Some(Stmt::Call { callee, args, line })
} else {
// Bare expression / FB invocation without args recognized —
// skip to the terminator.
self.sync_stmt();
None
}
}
_ => {
self.sync_stmt();
None
}
}
}
fn parse_block_until(&mut self, terms: &[K]) -> Vec<Stmt> {
let mut body = Vec::new();
while !self.at_end() && !terms.iter().any(|k| self.at_kw(*k)) {
if let Some(s) = self.parse_stmt() {
body.push(s);
}
}
body
}
fn parse_if(&mut self) -> Option<Stmt> {
let line = self.line();
self.eat_kw(K::If);
let mut branches = Vec::new();
let cond = self.parse_expr();
self.eat_kw(K::Then);
let body = self.parse_block_until(&[K::Elsif, K::Else, K::EndIf]);
branches.push((cond, body));
while self.eat_kw(K::Elsif) {
let c = self.parse_expr();
self.eat_kw(K::Then);
let b = self.parse_block_until(&[K::Elsif, K::Else, K::EndIf]);
branches.push((c, b));
}
let else_body = if self.eat_kw(K::Else) {
Some(self.parse_block_until(&[K::EndIf]))
} else {
None
};
self.eat_kw(K::EndIf);
self.eat(&Tok::Semi);
Some(Stmt::If {
branches,
else_body,
line,
})
}
fn parse_case(&mut self) -> Option<Stmt> {
let line = self.line();
self.eat_kw(K::Case);
let selector = self.parse_expr();
self.eat_kw(K::Of);
let mut arms = Vec::new();
let mut else_body = None;
while !self.at_end() && !self.at_kw(K::EndCase) {
if self.eat_kw(K::Else) {
else_body = Some(self.parse_block_until(&[K::EndCase]));
break;
}
// labels: expr {, expr} :
let mut labels = vec![self.parse_expr()];
while self.eat(&Tok::Comma) {
labels.push(self.parse_expr());
}
self.eat(&Tok::Colon);
let body = self.parse_block_until(&[K::EndCase, K::Else]);
arms.push((labels, body));
}
self.eat_kw(K::EndCase);
self.eat(&Tok::Semi);
Some(Stmt::Case {
selector,
arms,
else_body,
line,
})
}
fn parse_for(&mut self) -> Option<Stmt> {
let line = self.line();
self.eat_kw(K::For);
let var = self.ident().unwrap_or_default();
self.eat(&Tok::Assign);
let from = self.parse_expr();
self.eat_kw(K::To);
let to = self.parse_expr();
let by = if self.eat_kw(K::By) {
Some(self.parse_expr())
} else {
None
};
self.eat_kw(K::Do);
let body = self.parse_block_until(&[K::EndFor]);
self.eat_kw(K::EndFor);
self.eat(&Tok::Semi);
Some(Stmt::For {
var,
from,
to,
by,
body,
line,
})
}
fn parse_while(&mut self) -> Option<Stmt> {
let line = self.line();
self.eat_kw(K::While);
let cond = self.parse_expr();
self.eat_kw(K::Do);
let body = self.parse_block_until(&[K::EndWhile]);
self.eat_kw(K::EndWhile);
self.eat(&Tok::Semi);
Some(Stmt::While { cond, body, line })
}
fn parse_repeat(&mut self) -> Option<Stmt> {
let line = self.line();
self.eat_kw(K::Repeat);
let body = self.parse_block_until(&[K::Until, K::EndRepeat]);
self.eat_kw(K::Until);
let until = self.parse_expr();
self.eat_kw(K::EndRepeat);
self.eat(&Tok::Semi);
Some(Stmt::Repeat { body, until, line })
}
// ── expressions (precedence climbing) ──────────────────────────
pub fn parse_expr(&mut self) -> Expr {
self.parse_or()
}
fn parse_or(&mut self) -> Expr {
let mut lhs = self.parse_and();
loop {
let op = match self.peek() {
Tok::Kw(K::Or) => BinOp::Or,
Tok::Kw(K::Xor) => BinOp::Xor,
_ => break,
};
let line = self.line();
self.advance();
let rhs = self.parse_and();
lhs = Expr::Binary {
op,
lhs: Box::new(lhs),
rhs: Box::new(rhs),
line,
};
}
lhs
}
fn parse_and(&mut self) -> Expr {
let mut lhs = self.parse_cmp();
while matches!(self.peek(), Tok::Kw(K::And) | Tok::Amp) {
let op = BinOp::And;
let line = self.line();
self.advance();
let rhs = self.parse_cmp();
lhs = Expr::Binary {
op,
lhs: Box::new(lhs),
rhs: Box::new(rhs),
line,
};
}
lhs
}
fn parse_cmp(&mut self) -> Expr {
let mut lhs = self.parse_add();
loop {
let op = match self.peek() {
Tok::Eq => BinOp::Eq,
Tok::Ne => BinOp::Ne,
Tok::Lt => BinOp::Lt,
Tok::Le => BinOp::Le,
Tok::Gt => BinOp::Gt,
Tok::Ge => BinOp::Ge,
_ => break,
};
let line = self.line();
self.advance();
let rhs = self.parse_add();
lhs = Expr::Binary {
op,
lhs: Box::new(lhs),
rhs: Box::new(rhs),
line,
};
}
lhs
}
fn parse_add(&mut self) -> Expr {
let mut lhs = self.parse_mul();
loop {
let op = match self.peek() {
Tok::Plus => BinOp::Add,
Tok::Minus => BinOp::Sub,
_ => break,
};
let line = self.line();
self.advance();
let rhs = self.parse_mul();
lhs = Expr::Binary {
op,
lhs: Box::new(lhs),
rhs: Box::new(rhs),
line,
};
}
lhs
}
fn parse_mul(&mut self) -> Expr {
let mut lhs = self.parse_unary();
loop {
let op = match self.peek() {
Tok::Star => BinOp::Mul,
Tok::Slash => BinOp::Div,
Tok::Kw(K::Mod) => BinOp::Mod,
Tok::Power => BinOp::Pow,
_ => break,
};
let line = self.line();
self.advance();
let rhs = self.parse_unary();
lhs = Expr::Binary {
op,
lhs: Box::new(lhs),
rhs: Box::new(rhs),
line,
};
}
lhs
}
fn parse_unary(&mut self) -> Expr {
let line = self.line();
match self.peek() {
Tok::Kw(K::Not) => {
self.advance();
Expr::Unary {
op: UnOp::Not,
expr: Box::new(self.parse_unary()),
line,
}
}
Tok::Minus => {
self.advance();
Expr::Unary {
op: UnOp::Neg,
expr: Box::new(self.parse_unary()),
line,
}
}
_ => self.parse_postfix(),
}
}
fn parse_postfix(&mut self) -> Expr {
let mut e = self.parse_primary();
loop {
let line = self.line();
match self.peek() {
Tok::LBrack => {
self.advance();
let index = self.parse_expr();
self.eat(&Tok::RBrack);
e = Expr::Index {
base: Box::new(e),
index: Box::new(index),
line,
};
}
Tok::Dot => {
self.advance();
let field = self.ident().unwrap_or_default();
e = Expr::Member {
base: Box::new(e),
field,
line,
};
}
_ => break,
}
}
e
}
fn parse_primary(&mut self) -> Expr {
let line = self.line();
match self.advance() {
Tok::Int(n) => Expr::Int(n, line),
Tok::Real(r) => Expr::Real(r, line),
Tok::Bool(b) => Expr::Bool(b, line),
Tok::Str(s) => Expr::Str(s, line),
Tok::Time(t) => Expr::Time(t, line),
Tok::LParen => {
let e = self.parse_expr();
self.eat(&Tok::RParen);
e
}
Tok::Ident(name) => {
if self.eat(&Tok::LParen) {
let args = self.parse_call_args();
Expr::Call {
callee: name,
args,
line,
}
} else {
Expr::Ident(name, line)
}
}
// Unrecognized start of expression — yield a placeholder identifier.
_ => Expr::Ident(String::new(), line),
}
}
fn parse_call_args(&mut self) -> Vec<CallArg> {
let mut args = Vec::new();
if self.eat(&Tok::RParen) {
return args;
}
loop {
// Named arg: ident := expr (peek two tokens).
if let Tok::Ident(name) = self.peek().clone() {
if matches!(
self.toks.get(self.pos + 1).map(|t| &t.kind),
Some(Tok::Assign)
) {
self.advance(); // ident
self.advance(); // :=
let value = self.parse_expr();
args.push(CallArg {
name: Some(name),
value,
});
if self.eat(&Tok::Comma) {
continue;
}
break;
}
}
let value = self.parse_expr();
args.push(CallArg { name: None, value });
if self.eat(&Tok::Comma) {
continue;
}
break;
}
self.eat(&Tok::RParen);
args
}
}
/// Parse ST source into its POUs.
pub fn parse(src: &str) -> Vec<Pou> {
let toks = super::lexer::lex(src);
Parser::new(toks).parse_units()
}
#[cfg(test)]
mod tests {
use super::*;
const SAMPLE: &str = r#"
PROGRAM Main
VAR
idx : INT;
pw : STRING := 'admin123';
buf : ARRAY[0..9] OF INT;
ok : BOOL := FALSE;
END_VAR
// a comment
IF idx > 0 THEN
buf[idx] := idx * 2;
ELSE
JMP done;
END_IF;
Comm(IP := '10.0.0.1', PORT := 502);
done:
ok := TRUE;
END_PROGRAM
"#;
#[test]
fn parses_program_vars_and_body() {
let pous = parse(SAMPLE);
assert_eq!(pous.len(), 1, "one POU");
let p = &pous[0];
assert_eq!(p.name, "Main");
assert_eq!(p.kind, PouKind::Program);
// vars: idx, pw, buf, ok
assert_eq!(p.vars.len(), 4);
let pw = p.vars.iter().find(|v| v.name == "pw").expect("pw");
assert!(matches!(&pw.init, Some(Expr::Str(s, _)) if s == "admin123"));
let buf = p.vars.iter().find(|v| v.name == "buf").expect("buf");
assert_eq!(buf.array_bounds, Some((0, 9)));
// body has an IF, a Call, a Label, and an Assign
assert!(p.body.iter().any(|s| matches!(s, Stmt::If { .. })));
assert!(p
.body
.iter()
.any(|s| matches!(s, Stmt::Call { callee, .. } if callee == "Comm")));
assert!(p
.body
.iter()
.any(|s| matches!(s, Stmt::Label { name, .. } if name == "done")));
}
#[test]
fn jmp_inside_if_is_captured() {
let pous = parse(SAMPLE);
let p = &pous[0];
// find the IF, check its else branch has a JMP
let has_jmp = p.body.iter().any(|s| match s {
Stmt::If { else_body, .. } => else_body
.as_ref()
.map(|b| b.iter().any(|s| matches!(s, Stmt::Jump { .. })))
.unwrap_or(false),
_ => false,
});
assert!(has_jmp, "JMP should be parsed inside the ELSE branch");
}
}
@@ -0,0 +1,149 @@
//! PLCopen XML → Structured Text POUs.
//!
//! A PLCopen project stores each POU as `<pou name=".." pouType="..">` with an
//! `<interface>` (typed variable sections) and a `<body>`. We handle the
//! Structured-Text body form (`<ST>…</ST>`); FBD/LD/SFC bodies are skipped.
//!
//! For each ST POU we reconstruct an equivalent ST source (a `VAR` block built
//! from the interface + the ST body) and run it through the ST parser, so both
//! raw `.st` files and PLCopen projects flow through one analysis path.
use super::ast::Pou;
use super::parser;
/// Parse every Structured-Text POU out of a PLCopen XML document.
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");
// ST body text (skip non-ST bodies).
let Some(st_node) = pou
.descendants()
.find(|n| n.has_tag_name("ST") && n.ancestors().any(|a| a.has_tag_name("body")))
else {
continue;
};
let body = collect_text(st_node);
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
}
/// Concatenate all descendant text of a node (ST bodies are often wrapped in
/// `<xhtml>` and may contain multiple text runs).
fn collect_text(node: roxmltree::Node) -> String {
node.descendants()
.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: roxmltree::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: roxmltree::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: roxmltree::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('\'', "''")))
}
}
+632
View File
@@ -0,0 +1,632 @@
//! Semantic control-logic security rules over the Structured Text AST.
//!
//! Each rule walks the parsed [`Pou`] and yields [`RuleHit`]s the scanner turns
//! into findings. Rules reason over structure (declarations, assignments, calls,
//! array accesses, division, jumps) rather than raw text, so they see through
//! formatting and comments.
use std::collections::{HashMap, HashSet};
use compliance_core::models::Severity;
use super::ast::*;
/// One rule match within a POU.
pub struct RuleHit {
pub line: u32,
pub severity: Severity,
pub rule_id: &'static str,
pub title: String,
pub description: String,
pub cwe: Option<&'static str>,
pub remediation: &'static str,
}
/// Run every rule over a POU.
pub fn analyze(pou: &Pou) -> Vec<RuleHit> {
let mut hits = Vec::new();
let ctx = Ctx::build(pou);
// Declaration-level rules.
for v in &pou.vars {
if let Some(init) = &v.init {
check_credential_binding(&v.name, init, &pou.name, &mut hits);
check_default_password(init, &v.name, &pou.name, &mut hits);
}
}
// Body walk.
walk(&pou.body, pou, &ctx, &GuardSet::default(), &mut hits);
hits
}
/// Per-POU context precomputed once.
struct Ctx {
/// Names declared in VAR_INPUT (untrusted / externally driven).
input_vars: HashSet<String>,
/// Array variable name → declared (lo, hi) bounds.
arrays: HashMap<String, (i64, i64)>,
}
impl Ctx {
fn build(pou: &Pou) -> Self {
let mut input_vars = HashSet::new();
let mut arrays = HashMap::new();
for v in &pou.vars {
if v.section == VarSection::Input {
input_vars.insert(v.name.to_ascii_lowercase());
}
if let Some(b) = v.array_bounds {
arrays.insert(v.name.to_ascii_lowercase(), b);
}
}
Self { input_vars, arrays }
}
}
/// Variables proven non-zero on the current control-flow path (from enclosing
/// `IF`/`WHILE` conditions), so guarded divisions aren't false-flagged.
#[derive(Default, Clone)]
struct GuardSet {
nonzero: HashSet<String>,
}
impl GuardSet {
fn with(&self, names: Vec<String>) -> Self {
let mut g = self.clone();
g.nonzero.extend(names);
g
}
fn is_nonzero(&self, name: &str) -> bool {
self.nonzero.contains(name)
}
}
/// Variable names a condition proves non-zero (`v <> 0`, `v > 0`, `v >= 1`,
/// `v < 0`, and conjunctions thereof).
fn guards_from_cond(cond: &Expr) -> Vec<String> {
let mut out = Vec::new();
collect_nonzero(cond, &mut out);
out
}
fn collect_nonzero(e: &Expr, out: &mut Vec<String>) {
let Expr::Binary { op, lhs, rhs, .. } = e else {
return;
};
let is_zero = |x: &Expr| {
matches!(x, Expr::Int(0, _)) || matches!(x, Expr::Real(r, _) if r.abs() < f64::EPSILON)
};
let int_of = |x: &Expr| match x {
Expr::Int(n, _) => Some(*n),
_ => None,
};
match op {
BinOp::And => {
collect_nonzero(lhs, out);
collect_nonzero(rhs, out);
}
BinOp::Ne => {
if let (Some(v), true) = (lhs.as_ident(), is_zero(rhs)) {
out.push(v.to_ascii_lowercase());
}
if let (true, Some(v)) = (is_zero(lhs), rhs.as_ident()) {
out.push(v.to_ascii_lowercase());
}
}
BinOp::Gt | BinOp::Lt => {
// v > 0 or v < 0
if let (Some(v), true) = (lhs.as_ident(), is_zero(rhs)) {
out.push(v.to_ascii_lowercase());
}
}
BinOp::Ge => {
// v >= n, n >= 1
if let (Some(v), Some(n)) = (lhs.as_ident(), int_of(rhs)) {
if n >= 1 {
out.push(v.to_ascii_lowercase());
}
}
}
_ => {}
}
}
// ── the walker ─────────────────────────────────────────────────────
fn walk(stmts: &[Stmt], pou: &Pou, ctx: &Ctx, guards: &GuardSet, hits: &mut Vec<RuleHit>) {
for s in stmts {
match s {
Stmt::Assign {
target,
value,
line,
} => {
check_safety_bypass(target, value, *line, &pou.name, hits);
// A string bound to a secret-looking target is a credential.
if let Some(name) = flatten_ident(target) {
check_credential_binding(&name, value, &pou.name, hits);
check_default_password(value, &name, &pou.name, hits);
}
walk_expr(target, pou, ctx, guards, hits);
walk_expr(value, pou, ctx, guards, hits);
}
Stmt::Call { callee, args, line } => {
check_insecure_comm(callee, args, *line, &pou.name, hits);
check_credentials_in_call(callee, args, *line, &pou.name, hits);
for a in args {
walk_expr(&a.value, pou, ctx, guards, hits);
}
}
Stmt::Jump { label, line } => hits.push(RuleHit {
line: *line,
severity: Severity::Medium,
rule_id: "plc-unstructured-jump",
title: "Unstructured jump (JMP) in control logic".to_string(),
description: format!(
"POU `{}` uses `JMP {label}`. Unstructured jumps make control flow hard to \
verify and can bypass safety interlocks or leave outputs in an undefined \
state on unexpected paths.",
pou.name
),
cwe: Some("CWE-691"),
remediation: "Replace JMP with structured constructs (IF/CASE/loops); reserve \
jumps for well-reviewed state machines only.",
}),
Stmt::If {
branches,
else_body,
..
} => {
for (cond, body) in branches {
walk_expr(cond, pou, ctx, guards, hits);
let child = guards.with(guards_from_cond(cond));
walk(body, pou, ctx, &child, hits);
}
if let Some(b) = else_body {
walk(b, pou, ctx, guards, hits);
}
}
Stmt::Case {
selector,
arms,
else_body,
..
} => {
walk_expr(selector, pou, ctx, guards, hits);
for (labels, body) in arms {
for l in labels {
walk_expr(l, pou, ctx, guards, hits);
}
walk(body, pou, ctx, guards, hits);
}
if let Some(b) = else_body {
walk(b, pou, ctx, guards, hits);
}
}
Stmt::For {
from, to, by, body, ..
} => {
walk_expr(from, pou, ctx, guards, hits);
walk_expr(to, pou, ctx, guards, hits);
if let Some(b) = by {
walk_expr(b, pou, ctx, guards, hits);
}
walk(body, pou, ctx, guards, hits);
}
Stmt::While { cond, body, .. } => {
walk_expr(cond, pou, ctx, guards, hits);
let child = guards.with(guards_from_cond(cond));
walk(body, pou, ctx, &child, hits);
}
Stmt::Repeat { body, until, .. } => {
walk(body, pou, ctx, guards, hits);
walk_expr(until, pou, ctx, guards, hits);
}
Stmt::Return { .. } | Stmt::Exit { .. } | Stmt::Label { .. } => {}
}
}
}
fn walk_expr(e: &Expr, pou: &Pou, ctx: &Ctx, guards: &GuardSet, hits: &mut Vec<RuleHit>) {
match e {
Expr::Index { base, index, line } => {
check_array_bounds(base, index, *line, ctx, &pou.name, hits);
walk_expr(base, pou, ctx, guards, hits);
walk_expr(index, pou, ctx, guards, hits);
}
Expr::Binary { op, lhs, rhs, line } => {
if matches!(op, BinOp::Div | BinOp::Mod) {
check_division(rhs, *line, &pou.name, guards, hits);
}
walk_expr(lhs, pou, ctx, guards, hits);
walk_expr(rhs, pou, ctx, guards, hits);
}
Expr::Unary { expr, .. } => walk_expr(expr, pou, ctx, guards, hits),
Expr::Member { base, .. } => walk_expr(base, pou, ctx, guards, hits),
Expr::Call { args, .. } => {
for a in args {
walk_expr(&a.value, pou, ctx, guards, hits);
}
}
_ => {}
}
}
// ── individual rules ───────────────────────────────────────────────
const SECRET_HINTS: &[&str] = &[
"password",
"passwd",
"pwd",
"secret",
"apikey",
"api_key",
"token",
"credential",
"privkey",
"private_key",
"passphrase",
];
const DEFAULT_PASSWORDS: &[&str] = &[
"admin",
"administrator",
"password",
"passwd",
"1234",
"12345",
"123456",
"0000",
"1111",
"root",
"default",
"admin123",
"changeme",
"letmein",
"guest",
"user",
"system",
"plc",
"codesys",
];
const COMM_FB_HINTS: &[&str] = &[
"modbus", "tcp", "udp", "socket", "mqtt", "opcua", "opc_ua", "ethernet", "ethip", "enip",
"dnp3", "ftp", "telnet", "http", "send", "connect", "sock", "comm", "profinet", "s7",
];
/// Insecure cleartext service ports.
const INSECURE_PORTS: &[i64] = &[21, 23, 80, 502, 20000, 44818, 102];
fn check_credential_binding(var_name: &str, value: &Expr, pou: &str, hits: &mut Vec<RuleHit>) {
let name = var_name.to_ascii_lowercase();
let looks_secret = SECRET_HINTS.iter().any(|h| name.contains(h));
if looks_secret {
if let Expr::Str(s, line) = value {
if !s.is_empty() {
hits.push(RuleHit {
line: *line,
severity: Severity::High,
rule_id: "plc-hardcoded-credential",
title: "Hardcoded credential in PLC program".to_string(),
description: format!(
"POU `{pou}` binds a hardcoded secret to `{var_name}`. Credentials \
embedded in control logic are extracted trivially from a project export \
or a firmware dump and cannot be rotated without a redeploy."
),
cwe: Some("CWE-798"),
remediation: "Store secrets outside the program (secure parameter store / \
operator-entered, retained-but-protected memory); never commit \
them to the POU.",
});
}
}
}
}
fn check_default_password(value: &Expr, var_name: &str, pou: &str, hits: &mut Vec<RuleHit>) {
if let Expr::Str(s, line) = value {
let lower = s.to_ascii_lowercase();
if DEFAULT_PASSWORDS.contains(&lower.as_str()) {
hits.push(RuleHit {
line: *line,
severity: Severity::Critical,
rule_id: "plc-default-password",
title: "Default/weak password in PLC program".to_string(),
description: format!(
"POU `{pou}` uses the well-known default/weak password `{s}` (bound to \
`{var_name}`). Default PLC credentials are the first thing an attacker tries."
),
cwe: Some("CWE-1393"),
remediation:
"Require a strong, unique, operator-set password; block commissioning \
until the default is changed.",
});
}
}
}
fn check_credentials_in_call(
callee: &str,
args: &[CallArg],
line: u32,
pou: &str,
hits: &mut Vec<RuleHit>,
) {
for a in args {
if let Some(name) = &a.name {
let n = name.to_ascii_lowercase();
if SECRET_HINTS.iter().any(|h| n.contains(h)) {
if let Expr::Str(s, l) = &a.value {
if !s.is_empty() {
hits.push(RuleHit {
line: *l,
severity: Severity::High,
rule_id: "plc-hardcoded-credential",
title: "Hardcoded credential passed to a function block".to_string(),
description: format!(
"POU `{pou}` passes a hardcoded secret as `{name}` to `{callee}`."
),
cwe: Some("CWE-798"),
remediation: "Supply credentials from protected configuration at \
runtime, not as a literal argument.",
});
}
}
}
}
}
let _ = line;
}
fn check_safety_bypass(target: &Expr, value: &Expr, line: u32, pou: &str, hits: &mut Vec<RuleHit>) {
let Some(name) = flatten_ident(target) else {
return;
};
let n = name.to_ascii_lowercase();
let safety = [
"safety",
"estop",
"e_stop",
"emergency",
"interlock",
"guard",
"permit",
]
.iter()
.any(|h| n.contains(h));
let watchdog = n.contains("watchdog") || n.contains("wdt");
// A safety enable / interlock / watchdog signal driven to FALSE or 0 in
// application logic is a bypass (e.g. `Safety_Enable := FALSE`, `Watchdog_Kick := 0`).
let disabling = matches!(value, Expr::Bool(false, _)) || matches!(value, Expr::Int(0, _));
if (safety || watchdog) && disabling {
hits.push(RuleHit {
line,
severity: Severity::Critical,
rule_id: "plc-safety-bypass",
title: "Safety interlock / watchdog disabled in logic".to_string(),
description: format!(
"POU `{pou}` disables a safety-related signal (`{name}`) in program logic. \
Bypassing interlocks or watchdogs in code defeats the plant's protective \
functions and is a direct hazard."
),
cwe: Some("CWE-1384"),
remediation: "Never disable safety functions from application logic; safety must be \
handled by a certified safety controller / hard-wired circuit.",
});
}
}
fn check_array_bounds(
base: &Expr,
index: &Expr,
line: u32,
ctx: &Ctx,
pou: &str,
hits: &mut Vec<RuleHit>,
) {
// Only reason about arrays we know the bounds of.
let Some(arr_name) = base.as_ident() else {
return;
};
if !ctx.arrays.contains_key(&arr_name.to_ascii_lowercase()) {
return;
}
// Index by an untrusted input variable → potential out-of-bounds access.
if let Some(idx_name) = index.as_ident() {
if ctx.input_vars.contains(&idx_name.to_ascii_lowercase()) {
hits.push(RuleHit {
line,
severity: Severity::High,
rule_id: "plc-array-unchecked-index",
title: "Array indexed by unvalidated input".to_string(),
description: format!(
"POU `{pou}` indexes array `{arr_name}` with the input variable `{idx_name}` \
without a validated bounds check. An out-of-range index corrupts adjacent \
memory or faults the PLC (loss of control)."
),
cwe: Some("CWE-129"),
remediation: "Clamp or validate the index against the array bounds (e.g. \
`LIMIT`/explicit `IF idx >= lo AND idx <= hi`) before the access.",
});
}
}
}
fn check_division(
divisor: &Expr,
line: u32,
pou: &str,
guards: &GuardSet,
hits: &mut Vec<RuleHit>,
) {
// A divisor proven non-zero by an enclosing guard is safe.
if let Expr::Ident(name, _) = divisor {
if guards.is_nonzero(&name.to_ascii_lowercase()) {
return;
}
}
// Flag division by a variable (could be zero); nonzero literals are fine.
let risky = matches!(
divisor,
Expr::Ident(_, _) | Expr::Member { .. } | Expr::Index { .. } | Expr::Int(0, _)
);
if risky {
hits.push(RuleHit {
line,
severity: Severity::Medium,
rule_id: "plc-division-by-zero",
title: "Division by a variable without a zero-guard".to_string(),
description: format!(
"POU `{pou}` divides by a variable that is not proven non-zero. A zero divisor \
raises a PLC exception and can halt the scan cycle (denial of control)."
),
cwe: Some("CWE-369"),
remediation: "Guard the divisor (`IF d <> 0 THEN …`) or use a safe-divide helper that \
returns a defined value for a zero denominator.",
});
}
}
fn check_insecure_comm(
callee: &str,
args: &[CallArg],
line: u32,
pou: &str,
hits: &mut Vec<RuleHit>,
) {
let c = callee.to_ascii_lowercase();
let is_comm = COMM_FB_HINTS.iter().any(|h| c.contains(h));
if !is_comm {
return;
}
// Auth/encryption explicitly disabled.
for a in args {
if let Some(name) = &a.name {
let n = name.to_ascii_lowercase();
let security_flag = ["auth", "secure", "encrypt", "tls", "ssl", "authentication"]
.iter()
.any(|h| n.contains(h));
if security_flag && matches!(a.value, Expr::Bool(false, _)) {
hits.push(RuleHit {
line,
severity: Severity::High,
rule_id: "plc-insecure-comm",
title: "Network communication with security disabled".to_string(),
description: format!(
"POU `{pou}` calls `{callee}` with `{name} := FALSE`, disabling \
authentication/encryption on an industrial network link."
),
cwe: Some("CWE-319"),
remediation: "Enable authentication + transport encryption; segment OT \
networks and restrict the endpoint to trusted peers.",
});
}
}
// Well-known cleartext port literal.
if let Expr::Int(p, _) = &a.value {
if INSECURE_PORTS.contains(p) {
hits.push(RuleHit {
line,
severity: Severity::Medium,
rule_id: "plc-insecure-protocol-port",
title: "Cleartext industrial protocol port".to_string(),
description: format!(
"POU `{pou}` opens `{callee}` on port {p}, a well-known cleartext OT \
protocol port with no built-in authentication or encryption."
),
cwe: Some("CWE-319"),
remediation: "Front the protocol with a secure gateway/VPN, or use the \
authenticated/encrypted variant; never expose it to untrusted \
networks.",
});
}
}
}
let _ = line;
}
/// The dotted/base identifier of an lvalue expression (`a`, `a.b` → `a.b`,
/// `a[i]` → `a`), for name-based rules.
fn flatten_ident(e: &Expr) -> Option<String> {
match e {
Expr::Ident(n, _) => Some(n.clone()),
Expr::Member { base, field, .. } => flatten_ident(base).map(|b| format!("{b}.{field}")),
Expr::Index { base, .. } => flatten_ident(base),
_ => None,
}
}
#[cfg(test)]
mod tests {
use super::*;
use crate::pipeline::plc::parser;
const VULN: &str = r#"
FUNCTION_BLOCK CommCtrl
VAR_INPUT
cmdIndex : INT;
END_VAR
VAR
Password : STRING := 'admin123';
buffer : ARRAY[0..15] OF INT;
Safety_Enable : BOOL := TRUE;
divisor : INT;
result : INT;
END_VAR
Safety_Enable := FALSE;
result := 100 / divisor;
buffer[cmdIndex] := 1;
Modbus_Connect(IP := '192.168.0.10', PORT := 502, AUTH := FALSE);
IF cmdIndex > 100 THEN
JMP fault;
END_IF;
fault:
result := 0;
END_FUNCTION_BLOCK
"#;
fn rule_ids(src: &str) -> Vec<&'static str> {
parser::parse(src)
.iter()
.flat_map(analyze)
.map(|h| h.rule_id)
.collect()
}
#[test]
fn vulnerable_program_triggers_every_rule() {
let ids = rule_ids(VULN);
for expected in [
"plc-hardcoded-credential",
"plc-default-password",
"plc-safety-bypass",
"plc-division-by-zero",
"plc-array-unchecked-index",
"plc-insecure-comm",
"plc-insecure-protocol-port",
"plc-unstructured-jump",
] {
assert!(
ids.contains(&expected),
"expected rule {expected}, got {ids:?}"
);
}
}
#[test]
fn clean_program_has_no_findings() {
let clean = r#"
PROGRAM Clean
VAR
a : INT := 5;
b : INT := 3;
total : INT;
END_VAR
IF b <> 0 THEN
total := a / b;
END_IF;
END_PROGRAM
"#;
assert!(rule_ids(clean).is_empty(), "clean program should be quiet");
}
}
+2 -1
View File
@@ -1,3 +1,4 @@
use crate::pipeline::repo_view::RepoView;
use compliance_core::models::*; use compliance_core::models::*;
use super::dedup::compute_fingerprint; use super::dedup::compute_fingerprint;
@@ -14,7 +15,7 @@ impl PipelineOrchestrator {
#[tracing::instrument(skip_all, fields(repo_id = %repo_id, pr_number))] #[tracing::instrument(skip_all, fields(repo_id = %repo_id, pr_number))]
pub async fn run_pr_review( pub async fn run_pr_review(
&self, &self,
repo: &TrackedRepository, repo: &RepoView,
repo_id: &str, repo_id: &str,
pr_number: u64, pr_number: u64,
base_sha: &str, base_sha: &str,
@@ -0,0 +1,74 @@
//! `RepoView` — an internal, non-persisted view of a code target for the scan
//! pipeline.
//!
//! It replaces the old persisted `TrackedRepository` model. The pipeline
//! (SAST → SBOM → CVE → triage → issues → DAST, and PR review) only ever needs a
//! flat bundle of git + issue-tracker + auth fields; those are projected from an
//! [`OnboardedTarget`] and its code [`Artifact`] by [`RepoView::from_target`].
//! Nothing here is written to Mongo — onboarded targets are the sole persisted
//! entity.
use compliance_core::models::{Artifact, OnboardedTarget, TrackerType};
/// A flat, pipeline-facing view of a code target. Built from an onboarded
/// target; never persisted.
#[derive(Debug, Clone)]
pub struct RepoView {
/// The onboarded target's id (used as `repo_id` across findings/sbom/etc.).
pub id: Option<mongodb::bson::oid::ObjectId>,
pub name: String,
pub git_url: String,
pub default_branch: String,
pub local_path: Option<String>,
pub scan_schedule: Option<String>,
pub webhook_enabled: bool,
pub webhook_secret: Option<String>,
pub tracker_type: Option<TrackerType>,
pub tracker_owner: Option<String>,
pub tracker_repo: Option<String>,
pub tracker_token: Option<String>,
pub auth_token: Option<String>,
pub auth_username: Option<String>,
pub last_scanned_commit: Option<String>,
pub findings_count: u32,
}
impl RepoView {
/// Project an onboarded target + its code artifact into a pipeline view.
pub fn from_target(target: &OnboardedTarget, code: &Artifact) -> Self {
let mut view = Self {
id: target.id,
name: target.name.clone(),
git_url: code.source_ref.clone(),
default_branch: "main".to_string(),
local_path: None,
scan_schedule: target.scan_schedule.clone(),
webhook_enabled: target.webhook_enabled,
webhook_secret: target.webhook_secret.clone(),
tracker_type: None,
tracker_owner: None,
tracker_repo: None,
tracker_token: None,
auth_token: None,
auth_username: None,
last_scanned_commit: None,
findings_count: target.findings_count,
};
if let Some(git) = &code.git {
view.default_branch = git.default_branch.clone();
view.last_scanned_commit = git.last_scanned_commit.clone();
view.local_path = git.local_path.clone();
}
if let Some(auth) = &code.auth {
view.auth_token = auth.secret.clone();
view.auth_username = auth.username.clone();
}
if let Some(it) = &target.scan_config.issue_tracker {
view.tracker_type = it.tracker_type.clone();
view.tracker_owner = it.owner.clone();
view.tracker_repo = it.repo.clone();
view.tracker_token = it.token.clone();
}
view
}
}
+1 -1
View File
@@ -348,7 +348,7 @@ async fn monitor_cves(agent: &ComplianceAgent, tenant_id: &str) {
std::collections::HashMap::new(); std::collections::HashMap::new();
for rid in &repo_ids { for rid in &repo_ids {
if let Ok(oid) = mongodb::bson::oid::ObjectId::parse_str(rid) { if let Ok(oid) = mongodb::bson::oid::ObjectId::parse_str(rid) {
if let Ok(Some(repo)) = db.repositories().find_one(doc! { "_id": oid }).await { if let Ok(Some(repo)) = db.onboarded_targets().find_one(doc! { "_id": oid }).await {
repo_names.insert(rid.clone(), repo.name.clone()); repo_names.insert(rid.clone(), repo.name.clone());
} }
} }
+1 -1
View File
@@ -31,7 +31,7 @@ pub async fn handle_gitea_webhook(
} }
}; };
let repo = match db let repo = match db
.repositories() .onboarded_targets()
.find_one(mongodb::bson::doc! { "_id": oid }) .find_one(mongodb::bson::doc! { "_id": oid })
.await .await
{ {
+1 -1
View File
@@ -31,7 +31,7 @@ pub async fn handle_github_webhook(
} }
}; };
let repo = match db let repo = match db
.repositories() .onboarded_targets()
.find_one(mongodb::bson::doc! { "_id": oid }) .find_one(mongodb::bson::doc! { "_id": oid })
.await .await
{ {
+1 -1
View File
@@ -27,7 +27,7 @@ pub async fn handle_gitlab_webhook(
} }
}; };
let repo = match db let repo = match db
.repositories() .onboarded_targets()
.find_one(mongodb::bson::doc! { "_id": oid }) .find_one(mongodb::bson::doc! { "_id": oid })
.await .await
{ {
-1
View File
@@ -70,7 +70,6 @@ impl TestServer {
pentest_imap_password: None, pentest_imap_password: None,
admin_api_token: None, admin_api_token: None,
tenant_registry_url: None, tenant_registry_url: None,
unified_pipeline: false,
}; };
let agent = ComplianceAgent::new(config, db_pool); let agent = ComplianceAgent::new(config, db_pool);
@@ -113,15 +113,16 @@ async fn delete_repo_cascades_to_dast_and_pentest_data() {
// Create a repo // Create a repo
let resp = server let resp = server
.post( .post(
"/api/v1/repositories", "/api/v1/targets",
&json!({ &json!({
"name": "cascade-test", "name": "cascade-test",
"git_url": "https://github.com/example/cascade-test.git", "target_type": "web_app",
"artifacts": [{ "kind": "git_repo", "source_ref": "https://github.com/example/cascade-test.git", "branch": "main" }],
}), }),
) )
.await; .await;
let body: serde_json::Value = resp.json().await.unwrap(); let body: serde_json::Value = resp.json().await.unwrap();
let repo_id = body["data"]["id"].as_str().unwrap().to_string(); let repo_id = body["data"]["_id"]["$oid"].as_str().unwrap().to_string();
// Insert DAST target linked to repo // Insert DAST target linked to repo
let target_id = insert_dast_target(&server, &repo_id, "cascade-target").await; let target_id = insert_dast_target(&server, &repo_id, "cascade-target").await;
@@ -140,9 +141,7 @@ async fn delete_repo_cascades_to_dast_and_pentest_data() {
assert_eq!(count_docs(&server, "dast_findings").await, 1); assert_eq!(count_docs(&server, "dast_findings").await, 1);
// Delete the repo // Delete the repo
let resp = server let resp = server.delete(&format!("/api/v1/targets/{repo_id}")).await;
.delete(&format!("/api/v1/repositories/{repo_id}"))
.await;
assert_eq!(resp.status(), 200); assert_eq!(resp.status(), 200);
// All downstream data should be gone // All downstream data should be gone
@@ -161,15 +160,16 @@ async fn delete_repo_cascades_sast_findings_and_sbom() {
// Create a repo // Create a repo
let resp = server let resp = server
.post( .post(
"/api/v1/repositories", "/api/v1/targets",
&json!({ &json!({
"name": "sast-cascade", "name": "sast-cascade",
"git_url": "https://github.com/example/sast-cascade.git", "target_type": "web_app",
"artifacts": [{ "kind": "git_repo", "source_ref": "https://github.com/example/sast-cascade.git", "branch": "main" }],
}), }),
) )
.await; .await;
let body: serde_json::Value = resp.json().await.unwrap(); let body: serde_json::Value = resp.json().await.unwrap();
let repo_id = body["data"]["id"].as_str().unwrap().to_string(); let repo_id = body["data"]["_id"]["$oid"].as_str().unwrap().to_string();
// Insert SAST finding and SBOM entry // Insert SAST finding and SBOM entry
let mongodb_uri = std::env::var("TEST_MONGODB_URI") let mongodb_uri = std::env::var("TEST_MONGODB_URI")
@@ -209,9 +209,7 @@ async fn delete_repo_cascades_sast_findings_and_sbom() {
assert_eq!(count_docs(&server, "sbom_entries").await, 1); assert_eq!(count_docs(&server, "sbom_entries").await, 1);
// Delete repo // Delete repo
server server.delete(&format!("/api/v1/targets/{repo_id}")).await;
.delete(&format!("/api/v1/repositories/{repo_id}"))
.await;
// Both should be gone // Both should be gone
assert_eq!(count_docs(&server, "findings").await, 0); assert_eq!(count_docs(&server, "findings").await, 0);
@@ -3,5 +3,4 @@ mod dast;
mod findings; mod findings;
mod health; mod health;
mod onboarding; mod onboarding;
mod repositories;
mod stats; mod stats;
@@ -1,110 +0,0 @@
use crate::common::TestServer;
use serde_json::json;
#[tokio::test]
async fn add_and_list_repository() {
let server = TestServer::start().await;
// Initially empty
let resp = server.get("/api/v1/repositories").await;
assert_eq!(resp.status(), 200);
let body: serde_json::Value = resp.json().await.unwrap();
assert_eq!(body["data"].as_array().unwrap().len(), 0);
// Add a repository
let resp = server
.post(
"/api/v1/repositories",
&json!({
"name": "test-repo",
"git_url": "https://github.com/example/test-repo.git",
}),
)
.await;
assert_eq!(resp.status(), 200);
let body: serde_json::Value = resp.json().await.unwrap();
let repo_id = body["data"]["id"].as_str().unwrap().to_string();
assert!(!repo_id.is_empty());
// List should now return 1
let resp = server.get("/api/v1/repositories").await;
let body: serde_json::Value = resp.json().await.unwrap();
let repos = body["data"].as_array().unwrap();
assert_eq!(repos.len(), 1);
assert_eq!(repos[0]["name"], "test-repo");
server.cleanup().await;
}
#[tokio::test]
async fn add_duplicate_repository_fails() {
let server = TestServer::start().await;
let payload = json!({
"name": "dup-repo",
"git_url": "https://github.com/example/dup-repo.git",
});
// First add succeeds
let resp = server.post("/api/v1/repositories", &payload).await;
assert_eq!(resp.status(), 200);
// Second add with same git_url should fail (unique index)
let resp = server.post("/api/v1/repositories", &payload).await;
assert_ne!(resp.status(), 200);
server.cleanup().await;
}
#[tokio::test]
async fn delete_repository() {
let server = TestServer::start().await;
// Add a repo
let resp = server
.post(
"/api/v1/repositories",
&json!({
"name": "to-delete",
"git_url": "https://github.com/example/to-delete.git",
}),
)
.await;
let body: serde_json::Value = resp.json().await.unwrap();
let repo_id = body["data"]["id"].as_str().unwrap();
// Delete it
let resp = server
.delete(&format!("/api/v1/repositories/{repo_id}"))
.await;
assert_eq!(resp.status(), 200);
// List should be empty again
let resp = server.get("/api/v1/repositories").await;
let body: serde_json::Value = resp.json().await.unwrap();
assert_eq!(body["data"].as_array().unwrap().len(), 0);
server.cleanup().await;
}
#[tokio::test]
async fn delete_nonexistent_repository_returns_404() {
let server = TestServer::start().await;
let resp = server
.delete("/api/v1/repositories/000000000000000000000000")
.await;
assert_eq!(resp.status(), 404);
server.cleanup().await;
}
#[tokio::test]
async fn delete_invalid_id_returns_400() {
let server = TestServer::start().await;
let resp = server.delete("/api/v1/repositories/not-a-valid-id").await;
assert_eq!(resp.status(), 400);
server.cleanup().await;
}
@@ -5,13 +5,14 @@ use serde_json::json;
async fn stats_overview_reflects_inserted_data() { async fn stats_overview_reflects_inserted_data() {
let server = TestServer::start().await; let server = TestServer::start().await;
// Add a repo // Add a target
server server
.post( .post(
"/api/v1/repositories", "/api/v1/targets",
&json!({ &json!({
"name": "stats-repo", "name": "stats-repo",
"git_url": "https://github.com/example/stats-repo.git", "target_type": "web_app",
"artifacts": [{ "kind": "git_repo", "source_ref": "https://github.com/example/stats-repo.git", "branch": "main" }],
}), }),
) )
.await; .await;
@@ -1,156 +0,0 @@
// Integration tests for the onboarding backfill migration.
//
// Requires MongoDB (set TEST_MONGODB_URI if not at the default).
// Not run in CI (which is `--lib` only) — run locally:
// cargo test -p compliance-agent --test e2e migration
use compliance_agent::database::{Database, DatabasePool};
use compliance_agent::migrate::onboarding;
use compliance_core::models::{
ArtifactKind, DastTarget, DastTargetType, TargetType, TrackedRepository,
};
use mongodb::bson::{doc, Document};
async fn fresh_db() -> (DatabasePool, String, Database) {
let uri = std::env::var("TEST_MONGODB_URI")
.unwrap_or_else(|_| "mongodb://root:example@localhost:27017/?authSource=admin".into());
// Prefix must fit the pool's 30-char cap (`<prefix>_<32 hex>` <= 63).
let prefix = format!("t_{}", &uuid::Uuid::new_v4().simple().to_string()[..16]);
let pool = DatabasePool::connect(&uri, &prefix)
.await
.expect("connect mongo");
let db = pool.for_tenant_id("t1").await.expect("tenant db");
(pool, prefix, db)
}
async fn cleanup(pool: &DatabasePool, prefix: &str) {
if let Ok(names) = pool.client().list_database_names().await {
for n in names {
if n.starts_with(prefix) {
pool.client().database(&n).drop().await.ok();
}
}
}
}
#[tokio::test]
async fn backfill_folds_relinks_is_idempotent_and_reversible() {
let (pool, prefix, db) = fresh_db().await;
// Seed a repo.
let repo = TrackedRepository::new("acme".into(), "https://git/acme.git".into());
let repo_id = db
.repositories()
.insert_one(repo)
.await
.expect("insert repo")
.inserted_id
.as_object_id()
.expect("repo oid");
// A DAST target linked to the repo (folds + promotes to WebApp + relinks).
let mut linked = DastTarget::new(
"acme-web".into(),
"https://acme.example.com".into(),
DastTargetType::WebApp,
);
linked.repo_id = Some(repo_id.to_hex());
let linked_id = db
.dast_targets()
.insert_one(linked)
.await
.expect("insert linked dast")
.inserted_id
.as_object_id()
.expect("linked oid");
// A repo-less DAST target (standalone).
let standalone = DastTarget::new(
"acme-api".into(),
"https://api.acme.com".into(),
DastTargetType::RestApi,
);
let standalone_id = db
.dast_targets()
.insert_one(standalone)
.await
.expect("insert standalone dast")
.inserted_id
.as_object_id()
.expect("standalone oid");
// A DAST scan run pointing at the linked target — should be relinked to the repo.
db.collection_named::<Document>("dast_scan_runs")
.insert_one(doc! { "target_id": linked_id.to_hex(), "status": "completed" })
.await
.expect("insert dast run");
// --- Backfill ---
assert!(!onboarding::already_applied(&db).await.unwrap());
let report = onboarding::backfill_onboarded_targets(&db, false)
.await
.expect("backfill");
assert_eq!(report.repos_migrated, 1);
assert_eq!(report.dast_targets_folded, 1);
assert_eq!(report.dast_targets_standalone, 1);
assert!(onboarding::already_applied(&db).await.unwrap());
// Repo target: preserved _id, has git + folded live-url, promoted to WebApp.
let repo_target = db
.onboarded_targets()
.find_one(doc! { "_id": repo_id })
.await
.unwrap()
.expect("repo target");
assert!(repo_target.has(ArtifactKind::GitRepo));
assert!(repo_target.has(ArtifactKind::LiveUrl));
assert_eq!(repo_target.target_type, TargetType::WebApp);
// Standalone target: preserved _id, live-url, backend service.
let standalone_target = db
.onboarded_targets()
.find_one(doc! { "_id": standalone_id })
.await
.unwrap()
.expect("standalone target");
assert!(standalone_target.has(ArtifactKind::LiveUrl));
assert_eq!(standalone_target.target_type, TargetType::BackendService);
// The DAST run was relinked from the old dast id to the repo (unified) id.
let run = db
.collection_named::<Document>("dast_scan_runs")
.find_one(doc! {})
.await
.unwrap()
.expect("run");
assert_eq!(run.get_str("target_id").unwrap(), repo_id.to_hex());
// --- Idempotent: re-run migrates nothing new ---
let again = onboarding::backfill_onboarded_targets(&db, false)
.await
.expect("backfill again");
assert_eq!(again.repos_migrated, 0);
assert_eq!(again.dast_targets_folded, 0);
assert_eq!(again.dast_targets_standalone, 0);
assert!(again.skipped_existing >= 2);
// --- Revert: onboarded targets gone, relink undone, marker cleared ---
onboarding::revert(&db).await.expect("revert");
assert_eq!(
db.onboarded_targets()
.count_documents(doc! {})
.await
.unwrap(),
0
);
let run_after = db
.collection_named::<Document>("dast_scan_runs")
.find_one(doc! {})
.await
.unwrap()
.expect("run");
assert_eq!(run_after.get_str("target_id").unwrap(), linked_id.to_hex());
assert!(!onboarding::already_applied(&db).await.unwrap());
cleanup(&pool, &prefix).await;
}
@@ -7,4 +7,3 @@
// Or nightly: (via CI with MongoDB service container) // Or nightly: (via CI with MongoDB service container)
mod api; mod api;
mod migration;
+13 -28
View File
@@ -11,7 +11,7 @@
#![allow(clippy::expect_used, clippy::unwrap_used)] #![allow(clippy::expect_used, clippy::unwrap_used)]
use compliance_agent::database::DatabasePool; use compliance_agent::database::DatabasePool;
use compliance_core::models::TrackedRepository; use compliance_core::models::{Artifact, OnboardedTarget, TargetType};
use compliance_core::{OrgRole, TenantContext, TenantStatus}; use compliance_core::{OrgRole, TenantContext, TenantStatus};
use mongodb::bson::doc; use mongodb::bson::doc;
@@ -28,27 +28,12 @@ fn ctx(tenant_id: &str, slug: &str) -> TenantContext {
} }
} }
fn fixture_repo(name: &str, git_url: &str) -> TrackedRepository { fn fixture_repo(name: &str, git_url: &str) -> OnboardedTarget {
TrackedRepository { let mut target = OnboardedTarget::new(name.to_string(), TargetType::WebApp);
id: None, target
name: name.to_string(), .artifacts
git_url: git_url.to_string(), .push(Artifact::git_repo(git_url.to_string(), "main".to_string()));
default_branch: "main".to_string(), target
local_path: None,
scan_schedule: None,
webhook_enabled: false,
webhook_secret: None,
tracker_type: None,
tracker_owner: None,
tracker_repo: None,
tracker_token: None,
auth_token: None,
auth_username: None,
last_scanned_commit: None,
findings_count: 0,
created_at: chrono::Utc::now(),
updated_at: chrono::Utc::now(),
}
} }
#[tokio::test] #[tokio::test]
@@ -71,12 +56,12 @@ async fn pool_isolates_tenants_at_driver_level() {
// Write distinct repos into each tenant's database. // Write distinct repos into each tenant's database.
acme_db acme_db
.repositories() .onboarded_targets()
.insert_one(fixture_repo("acme-app", "git@example.com:acme/app.git")) .insert_one(fixture_repo("acme-app", "git@example.com:acme/app.git"))
.await .await
.expect("insert acme"); .expect("insert acme");
globex_db globex_db
.repositories() .onboarded_targets()
.insert_one(fixture_repo( .insert_one(fixture_repo(
"globex-platform", "globex-platform",
"git@example.com:globex/platform.git", "git@example.com:globex/platform.git",
@@ -173,12 +158,12 @@ async fn admin_helpers_list_and_drop_tenant_dbs() {
let acme_db = pool.for_tenant(&acme).await.expect("acme db"); let acme_db = pool.for_tenant(&acme).await.expect("acme db");
let globex_db = pool.for_tenant(&globex).await.expect("globex db"); let globex_db = pool.for_tenant(&globex).await.expect("globex db");
acme_db acme_db
.repositories() .onboarded_targets()
.insert_one(fixture_repo("acme-app", "git@example.com:acme/app.git")) .insert_one(fixture_repo("acme-app", "git@example.com:acme/app.git"))
.await .await
.expect("insert acme"); .expect("insert acme");
globex_db globex_db
.repositories() .onboarded_targets()
.insert_one(fixture_repo("globex-app", "git@example.com:globex/app.git")) .insert_one(fixture_repo("globex-app", "git@example.com:globex/app.git"))
.await .await
.expect("insert globex"); .expect("insert globex");
@@ -284,9 +269,9 @@ fn short_id() -> String {
} }
/// Drain a `repositories` find cursor on the given tenant database. /// Drain a `repositories` find cursor on the given tenant database.
async fn collect(db: &compliance_agent::database::Database) -> Vec<TrackedRepository> { async fn collect(db: &compliance_agent::database::Database) -> Vec<OnboardedTarget> {
let mut cursor = db let mut cursor = db
.repositories() .onboarded_targets()
.find(doc! {}) .find(doc! {})
.await .await
.expect("find repositories"); .expect("find repositories");
-5
View File
@@ -49,11 +49,6 @@ pub struct AgentConfig {
/// of tenants to iterate. When `None` or unreachable, scheduler /// of tenants to iterate. When `None` or unreachable, scheduler
/// falls back to `SCHEDULER_TENANT_IDS` env (M7.2-C). /// falls back to `SCHEDULER_TENANT_IDS` env (M7.2-C).
pub tenant_registry_url: Option<String>, pub tenant_registry_url: Option<String>,
/// When true, `run_scan` dispatches to the unified `run_target` pipeline
/// (reads `onboarded_targets`) instead of the legacy repository pipeline.
/// Env `UNIFIED_PIPELINE`. Defaults on; set `UNIFIED_PIPELINE=0` to use the
/// legacy repository pipeline.
pub unified_pipeline: bool,
} }
#[derive(Clone, Debug, Serialize, Deserialize)] #[derive(Clone, Debug, Serialize, Deserialize)]
+1 -1
View File
@@ -44,6 +44,6 @@ pub use pentest::{
PentestStatus, PentestStrategy, SeverityDistribution, TestUserRecord, TesterInfo, PentestStatus, PentestStrategy, SeverityDistribution, TestUserRecord, TesterInfo,
ToolCallRecord, ToolCallRecord,
}; };
pub use repository::{ScanTrigger, TrackedRepository}; pub use repository::ScanTrigger;
pub use sbom::{SbomEntry, VulnRef}; pub use sbom::{SbomEntry, VulnRef};
pub use scan::{ScanPhase, ScanRun, ScanRunStatus, ScanType}; pub use scan::{ScanPhase, ScanRun, ScanRunStatus, ScanType};
+2 -93
View File
@@ -1,8 +1,6 @@
use chrono::{DateTime, Utc}; use serde::{Deserialize, Serialize};
use serde::{Deserialize, Deserializer, Serialize};
use super::issue::TrackerType;
/// What initiated a scan.
#[derive(Debug, Clone, Serialize, Deserialize, PartialEq, Eq)] #[derive(Debug, Clone, Serialize, Deserialize, PartialEq, Eq)]
#[serde(rename_all = "snake_case")] #[serde(rename_all = "snake_case")]
pub enum ScanTrigger { pub enum ScanTrigger {
@@ -10,92 +8,3 @@ pub enum ScanTrigger {
Webhook, Webhook,
Manual, 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,
}
}
}
-2
View File
@@ -10,8 +10,6 @@ pub enum Route {
#[layout(AppShell)] #[layout(AppShell)]
#[route("/")] #[route("/")]
OverviewPage {}, OverviewPage {},
#[route("/repositories")]
RepositoriesPage {},
#[route("/targets")] #[route("/targets")]
TargetsPage {}, TargetsPage {},
#[route("/onboard")] #[route("/onboard")]
@@ -4,8 +4,9 @@ use dioxus_free_icons::Icon;
use crate::app::Route; use crate::app::Route;
use crate::infrastructure::dast::fetch_dast_targets; 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::pentest::{create_pentest_session_wizard, lookup_repo_by_url};
use crate::infrastructure::repositories::{fetch_repositories, fetch_ssh_public_key}; use crate::infrastructure::repositories::fetch_ssh_public_key;
const DISCLAIMER_TEXT: &str = "I confirm that I have authorization to perform security testing \ 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 \ against the specified target. I understand that penetration testing may cause disruption to the \
@@ -39,7 +40,7 @@ pub fn PentestWizard(show: Signal<bool>) -> Element {
let mut show_target_dropdown = use_signal(|| false); let mut show_target_dropdown = use_signal(|| false);
let mut show_repo_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_targets = use_resource(|| async { fetch_dast_targets().await.ok() });
let existing_repos = use_resource(|| async { fetch_repositories(1).await.ok() }); let existing_repos = use_resource(|| async { fetch_targets().await.ok() });
// SSH key state for private repos // SSH key state for private repos
let mut ssh_public_key = use_signal(String::new); let mut ssh_public_key = use_signal(String::new);
@@ -211,7 +212,25 @@ pub fn PentestWizard(show: Signal<bool>) -> Element {
Some(Some(data)) => data Some(Some(data)) => data
.data .data
.iter() .iter()
.map(|r| (r.git_url.clone(), r.name.clone())) .filter_map(|t| {
let name = t
.get("name")
.and_then(|v| v.as_str())
.unwrap_or_default()
.to_string();
let git_url = t
.get("artifacts")
.and_then(|a| a.as_array())
.and_then(|arr| {
arr.iter().find(|a| {
a.get("kind").and_then(|k| k.as_str()) == Some("git_repo")
})
})
.and_then(|a| a.get("source_ref"))
.and_then(|s| s.as_str())?
.to_string();
Some((git_url, name))
})
.collect(), .collect(),
_ => Vec::new(), _ => Vec::new(),
} }
@@ -19,10 +19,6 @@ impl Database {
Ok(Self { inner: db }) Ok(Self { inner: db })
} }
pub fn repositories(&self) -> Collection<TrackedRepository> {
self.inner.collection("repositories")
}
pub fn findings(&self) -> Collection<Finding> { pub fn findings(&self) -> Collection<Finding> {
self.inner.collection("findings") self.inner.collection("findings")
} }
@@ -1,145 +1,10 @@
//! The agent's SSH deploy public key — shown so a read-only deploy key can be
//! added to private git targets. (The legacy repositories CRUD moved to the
//! unified onboarding/targets API.)
use dioxus::prelude::*; use dioxus::prelude::*;
use serde::{Deserialize, Serialize};
use compliance_core::models::TrackedRepository;
#[derive(Debug, Clone, Serialize, Deserialize, Default)]
pub struct RepositoryListResponse {
pub data: Vec<TrackedRepository>,
pub total: Option<u64>,
pub page: Option<u64>,
}
#[server]
pub async fn fetch_repositories(page: u64) -> Result<RepositoryListResponse, ServerFnError> {
let path = format!("/api/v1/repositories?page={page}&limit=20");
let resp = super::agent_client::agent_get(&path)
.await?
.send()
.await
.map_err(|e| ServerFnError::new(e.to_string()))?;
let body: RepositoryListResponse = resp
.json()
.await
.map_err(|e| ServerFnError::new(e.to_string()))?;
Ok(body)
}
#[server]
pub async fn add_repository(
name: String,
git_url: String,
default_branch: String,
auth_token: Option<String>,
auth_username: Option<String>,
tracker_type: Option<String>,
tracker_owner: Option<String>,
tracker_repo: Option<String>,
tracker_token: Option<String>,
) -> Result<(), ServerFnError> {
let mut body = serde_json::json!({
"name": name,
"git_url": git_url,
"default_branch": default_branch,
});
if let Some(token) = auth_token.filter(|t| !t.is_empty()) {
body["auth_token"] = serde_json::Value::String(token);
}
if let Some(username) = auth_username.filter(|u| !u.is_empty()) {
body["auth_username"] = serde_json::Value::String(username);
}
if let Some(tt) = tracker_type.filter(|t| !t.is_empty()) {
body["tracker_type"] = serde_json::Value::String(tt);
}
if let Some(to) = tracker_owner.filter(|t| !t.is_empty()) {
body["tracker_owner"] = serde_json::Value::String(to);
}
if let Some(tr) = tracker_repo.filter(|t| !t.is_empty()) {
body["tracker_repo"] = serde_json::Value::String(tr);
}
if let Some(tk) = tracker_token.filter(|t| !t.is_empty()) {
body["tracker_token"] = serde_json::Value::String(tk);
}
let resp = super::agent_client::agent_request(reqwest::Method::POST, "/api/v1/repositories")
.await?
.json(&body)
.send()
.await
.map_err(|e| ServerFnError::new(e.to_string()))?;
if !resp.status().is_success() {
let body = resp.text().await.unwrap_or_default();
return Err(ServerFnError::new(format!(
"Failed to add repository: {body}"
)));
}
Ok(())
}
#[server]
pub async fn update_repository(
repo_id: String,
name: Option<String>,
default_branch: Option<String>,
auth_token: Option<String>,
auth_username: Option<String>,
tracker_type: Option<String>,
tracker_owner: Option<String>,
tracker_repo: Option<String>,
tracker_token: Option<String>,
scan_schedule: Option<String>,
) -> Result<(), ServerFnError> {
let mut body = serde_json::Map::new();
if let Some(v) = name.filter(|s| !s.is_empty()) {
body.insert("name".into(), serde_json::Value::String(v));
}
if let Some(v) = default_branch.filter(|s| !s.is_empty()) {
body.insert("default_branch".into(), serde_json::Value::String(v));
}
if let Some(v) = auth_token {
body.insert("auth_token".into(), serde_json::Value::String(v));
}
if let Some(v) = auth_username {
body.insert("auth_username".into(), serde_json::Value::String(v));
}
if let Some(v) = tracker_type {
body.insert("tracker_type".into(), serde_json::Value::String(v));
}
if let Some(v) = tracker_owner {
body.insert("tracker_owner".into(), serde_json::Value::String(v));
}
if let Some(v) = tracker_repo {
body.insert("tracker_repo".into(), serde_json::Value::String(v));
}
if let Some(v) = tracker_token {
body.insert("tracker_token".into(), serde_json::Value::String(v));
}
if let Some(v) = scan_schedule {
body.insert("scan_schedule".into(), serde_json::Value::String(v));
}
let resp = super::agent_client::agent_request(
reqwest::Method::PATCH,
&format!("/api/v1/repositories/{repo_id}"),
)
.await?
.json(&body)
.send()
.await
.map_err(|e| ServerFnError::new(e.to_string()))?;
if !resp.status().is_success() {
let text = resp.text().await.unwrap_or_default();
return Err(ServerFnError::new(format!(
"Failed to update repository: {text}"
)));
}
Ok(())
}
/// Fetch the agent's SSH deploy public key.
#[server] #[server]
pub async fn fetch_ssh_public_key() -> Result<String, ServerFnError> { pub async fn fetch_ssh_public_key() -> Result<String, ServerFnError> {
let resp = super::agent_client::agent_get("/api/v1/settings/ssh-public-key") let resp = super::agent_client::agent_get("/api/v1/settings/ssh-public-key")
@@ -163,86 +28,3 @@ pub async fn fetch_ssh_public_key() -> Result<String, ServerFnError> {
.unwrap_or("") .unwrap_or("")
.to_string()) .to_string())
} }
#[server]
pub async fn delete_repository(repo_id: String) -> Result<(), ServerFnError> {
let resp = super::agent_client::agent_request(
reqwest::Method::DELETE,
&format!("/api/v1/repositories/{repo_id}"),
)
.await?
.send()
.await
.map_err(|e| ServerFnError::new(e.to_string()))?;
if !resp.status().is_success() {
let body = resp.text().await.unwrap_or_default();
return Err(ServerFnError::new(format!(
"Failed to delete repository: {body}"
)));
}
Ok(())
}
#[server]
pub async fn trigger_repo_scan(repo_id: String) -> Result<(), ServerFnError> {
super::agent_client::agent_request(
reqwest::Method::POST,
&format!("/api/v1/repositories/{repo_id}/scan"),
)
.await?
.send()
.await
.map_err(|e| ServerFnError::new(e.to_string()))?;
Ok(())
}
#[derive(Debug, Clone, Serialize, Deserialize, Default)]
pub struct WebhookConfigResponse {
pub webhook_secret: Option<String>,
pub tracker_type: String,
}
#[server]
pub async fn fetch_webhook_config(repo_id: String) -> Result<WebhookConfigResponse, ServerFnError> {
let resp =
super::agent_client::agent_get(&format!("/api/v1/repositories/{repo_id}/webhook-config"))
.await?
.send()
.await
.map_err(|e| ServerFnError::new(e.to_string()))?;
let body: WebhookConfigResponse = resp
.json()
.await
.map_err(|e| ServerFnError::new(e.to_string()))?;
Ok(body)
}
/// Check if a repository has any running scans
#[server]
pub async fn check_repo_scanning(repo_id: String) -> Result<bool, ServerFnError> {
let resp = super::agent_client::agent_get("/api/v1/scan-runs?page=1&limit=1")
.await?
.send()
.await
.map_err(|e| ServerFnError::new(e.to_string()))?;
let body: serde_json::Value = resp
.json()
.await
.map_err(|e| ServerFnError::new(e.to_string()))?;
// Check if the most recent scan for this repo is still running
if let Some(scans) = body.get("data").and_then(|d| d.as_array()) {
for scan in scans {
let scan_repo = scan.get("repo_id").and_then(|v| v.as_str()).unwrap_or("");
let status = scan.get("status").and_then(|v| v.as_str()).unwrap_or("");
if scan_repo == repo_id && status == "running" {
return Ok(true);
}
}
}
Ok(false)
}
+28 -6
View File
@@ -2,11 +2,11 @@ use dioxus::prelude::*;
use crate::app::Route; use crate::app::Route;
use crate::components::page_header::PageHeader; use crate::components::page_header::PageHeader;
use crate::infrastructure::repositories::fetch_repositories; use crate::infrastructure::onboarding::fetch_targets;
#[component] #[component]
pub fn ChatIndexPage() -> Element { pub fn ChatIndexPage() -> Element {
let repos = use_resource(|| async { fetch_repositories(1).await.ok() }); let repos = use_resource(|| async { fetch_targets().await.ok() });
rsx! { rsx! {
PageHeader { PageHeader {
@@ -28,10 +28,32 @@ pub fn ChatIndexPage() -> Element {
div { class: "graph-index-grid", div { class: "graph-index-grid",
for repo in repo_list { for repo in repo_list {
{ {
let repo_id = repo.id.map(|id| id.to_hex()).unwrap_or_default(); let repo_id = repo.get("_id").and_then(|o| o.get("$oid")).and_then(|s| s.as_str()).unwrap_or_default().to_string();
let name = repo.name.clone(); let name = repo.get("name").and_then(|n| n.as_str()).unwrap_or_default().to_string();
let url = repo.git_url.clone(); let url = repo
let branch = repo.default_branch.clone(); .get("artifacts")
.and_then(|a| a.as_array())
.and_then(|arr| {
arr.iter().find(|a| {
a.get("kind").and_then(|k| k.as_str()) == Some("git_repo")
})
})
.and_then(|a| a.get("source_ref"))
.and_then(|s| s.as_str())
.unwrap_or_default()
.to_string();
let branch = repo
.get("artifacts")
.and_then(|a| a.as_array())
.and_then(|arr| {
arr.iter().find_map(|a| {
a.get("git")
.and_then(|g| g.get("default_branch"))
.and_then(|b| b.as_str())
})
})
.unwrap_or("main")
.to_string();
rsx! { rsx! {
Link { Link {
to: Route::ChatPage { repo_id }, to: Route::ChatPage { repo_id },
+29 -25
View File
@@ -2,11 +2,11 @@ use dioxus::prelude::*;
use crate::app::Route; use crate::app::Route;
use crate::components::page_header::PageHeader; use crate::components::page_header::PageHeader;
use crate::infrastructure::repositories::fetch_repositories; use crate::infrastructure::onboarding::fetch_targets;
#[component] #[component]
pub fn GraphIndexPage() -> Element { pub fn GraphIndexPage() -> Element {
let repos = use_resource(|| async { fetch_repositories(1).await.ok() }); let repos = use_resource(|| async { fetch_targets().await.ok() });
rsx! { rsx! {
PageHeader { PageHeader {
@@ -28,27 +28,34 @@ pub fn GraphIndexPage() -> Element {
div { class: "graph-index-grid", div { class: "graph-index-grid",
for repo in repo_list { for repo in repo_list {
{ {
let repo_id = repo.id.map(|id| id.to_hex()).unwrap_or_default(); let repo_id = repo.get("_id").and_then(|o| o.get("$oid")).and_then(|s| s.as_str()).unwrap_or_default().to_string();
let name = repo.name.clone(); let name = repo.get("name").and_then(|n| n.as_str()).unwrap_or_default().to_string();
let url = repo.git_url.clone(); let url = repo
let branch = repo.default_branch.clone(); .get("artifacts")
let findings = repo.findings_count; .and_then(|a| a.as_array())
.and_then(|arr| {
arr.iter().find(|a| {
a.get("kind").and_then(|k| k.as_str()) == Some("git_repo")
})
})
.and_then(|a| a.get("source_ref"))
.and_then(|s| s.as_str())
.unwrap_or_default()
.to_string();
let branch = repo
.get("artifacts")
.and_then(|a| a.as_array())
.and_then(|arr| {
arr.iter().find_map(|a| {
a.get("git")
.and_then(|g| g.get("default_branch"))
.and_then(|b| b.as_str())
})
})
.unwrap_or("main")
.to_string();
let findings = repo.get("findings_count").and_then(|n| n.as_u64()).unwrap_or(0);
let findings_label = if findings != 1 { format!("{findings} findings") } else { "1 finding".to_string() }; let findings_label = if findings != 1 { format!("{findings} findings") } else { "1 finding".to_string() };
let updated = {
let now = chrono::Utc::now();
let diff = now.signed_duration_since(repo.updated_at);
if diff.num_minutes() < 1 {
"just now".to_string()
} else if diff.num_hours() < 1 {
format!("{}m ago", diff.num_minutes())
} else if diff.num_days() < 1 {
format!("{}h ago", diff.num_hours())
} else if diff.num_days() < 30 {
format!("{}d ago", diff.num_days())
} else {
repo.updated_at.format("%Y-%m-%d").to_string()
}
};
rsx! { rsx! {
Link { Link {
to: Route::GraphExplorerPage { repo_id }, to: Route::GraphExplorerPage { repo_id },
@@ -67,9 +74,6 @@ pub fn GraphIndexPage() -> Element {
span { class: "graph-repo-card-tag graph-repo-card-tag-findings", span { class: "graph-repo-card-tag graph-repo-card-tag-findings",
"{findings_label}" "{findings_label}"
} }
span { class: "graph-repo-card-tag",
"Updated {updated}"
}
} }
} }
} }
-2
View File
@@ -16,7 +16,6 @@ pub mod onboarding;
pub mod overview; pub mod overview;
pub mod pentest_dashboard; pub mod pentest_dashboard;
pub mod pentest_session; pub mod pentest_session;
pub mod repositories;
pub mod sbom; pub mod sbom;
pub mod targets; pub mod targets;
@@ -38,6 +37,5 @@ pub use onboarding::OnboardingPage;
pub use overview::OverviewPage; pub use overview::OverviewPage;
pub use pentest_dashboard::PentestDashboardPage; pub use pentest_dashboard::PentestDashboardPage;
pub use pentest_session::PentestSessionPage; pub use pentest_session::PentestSessionPage;
pub use repositories::RepositoriesPage;
pub use sbom::SbomPage; pub use sbom::SbomPage;
pub use targets::TargetsPage; pub use targets::TargetsPage;
+4 -4
View File
@@ -6,7 +6,7 @@ use crate::app::Route;
use crate::components::page_header::PageHeader; use crate::components::page_header::PageHeader;
use crate::components::stat_card::StatCard; use crate::components::stat_card::StatCard;
use crate::infrastructure::mcp::fetch_mcp_servers; use crate::infrastructure::mcp::fetch_mcp_servers;
use crate::infrastructure::repositories::fetch_repositories; use crate::infrastructure::onboarding::fetch_targets;
#[cfg(feature = "server")] #[cfg(feature = "server")]
use crate::infrastructure::stats::fetch_overview_stats; use crate::infrastructure::stats::fetch_overview_stats;
@@ -26,7 +26,7 @@ pub fn OverviewPage() -> Element {
} }
}); });
let repos = use_resource(|| async { fetch_repositories(1).await.ok() }); let repos = use_resource(|| async { fetch_targets().await.ok() });
let mcp_servers = use_resource(|| async { fetch_mcp_servers().await.ok() }); let mcp_servers = use_resource(|| async { fetch_mcp_servers().await.ok() });
rsx! { rsx! {
@@ -94,8 +94,8 @@ pub fn OverviewPage() -> Element {
style: "display: grid; grid-template-columns: repeat(3, 1fr); gap: 1rem; padding: 1rem;", style: "display: grid; grid-template-columns: repeat(3, 1fr); gap: 1rem; padding: 1rem;",
for repo in repo_list { for repo in repo_list {
{ {
let repo_id = repo.id.map(|id| id.to_hex()).unwrap_or_default(); let repo_id = repo.get("_id").and_then(|o| o.get("$oid")).and_then(|s| s.as_str()).unwrap_or_default().to_string();
let name = repo.name.clone(); let name = repo.get("name").and_then(|n| n.as_str()).unwrap_or_default().to_string();
rsx! { rsx! {
Link { Link {
to: Route::ChatPage { repo_id }, to: Route::ChatPage { repo_id },
@@ -1,428 +0,0 @@
use dioxus::prelude::*;
use dioxus_free_icons::icons::bs_icons::*;
#[allow(unused_imports)]
use dioxus_free_icons::icons::bs_icons::{BsGear, BsPencil};
use dioxus_free_icons::Icon;
use crate::components::page_header::PageHeader;
use crate::components::pagination::Pagination;
use crate::components::toast::{ToastType, Toasts};
use crate::pages::graph_explorer::GraphExplorerInline;
async fn async_sleep_5s() {
#[cfg(feature = "web")]
{
gloo_timers::future::TimeoutFuture::new(5_000).await;
}
#[cfg(not(feature = "web"))]
{
tokio::time::sleep(std::time::Duration::from_secs(5)).await;
}
}
#[component]
pub fn RepositoriesPage() -> Element {
let mut page = use_signal(|| 1u64);
let mut toasts = use_context::<Toasts>();
let mut confirm_delete = use_signal(|| Option::<(String, String)>::None); // (id, name)
let mut edit_repo_id = use_signal(|| Option::<String>::None);
let mut edit_name = use_signal(String::new);
let mut edit_branch = use_signal(String::new);
let mut edit_tracker_type = use_signal(String::new);
let mut edit_tracker_owner = use_signal(String::new);
let mut edit_tracker_repo = use_signal(String::new);
let mut edit_tracker_token = use_signal(String::new);
let mut edit_saving = use_signal(|| false);
let mut edit_webhook_secret = use_signal(|| Option::<String>::None);
let mut edit_webhook_tracker = use_signal(String::new);
let mut scanning_ids = use_signal(Vec::<String>::new);
let mut graph_repo_id = use_signal(|| Option::<String>::None);
let mut repos = use_resource(move || {
let p = page();
async move {
crate::infrastructure::repositories::fetch_repositories(p)
.await
.ok()
}
});
rsx! {
PageHeader {
title: "Repositories",
description: "Legacy git repositories. Onboard new targets from Targets / Onboard.",
}
// ── Delete confirmation dialog ──
if let Some((del_id, del_name)) = confirm_delete() {
div { class: "modal-overlay",
div { class: "modal-dialog",
h3 { "Delete Repository" }
p {
"Are you sure you want to delete "
strong { "{del_name}" }
"?"
}
p { class: "modal-warning",
"This will permanently remove all associated findings, SBOM entries, scan runs, graph data, embeddings, and CVE alerts."
}
div { class: "modal-actions",
button {
class: "btn btn-secondary",
onclick: move |_| confirm_delete.set(None),
"Cancel"
}
button {
class: "btn btn-danger",
onclick: move |_| {
let id = del_id.clone();
let name = del_name.clone();
confirm_delete.set(None);
spawn(async move {
match crate::infrastructure::repositories::delete_repository(id).await {
Ok(_) => {
toasts.push(ToastType::Success, format!("{name} deleted"));
repos.restart();
}
Err(e) => toasts.push(ToastType::Error, e.to_string()),
}
});
},
"Delete"
}
}
}
}
}
// ── Edit repository dialog ──
if let Some(eid) = edit_repo_id() {
div { class: "modal-overlay",
div { class: "modal-dialog",
h3 { "Edit Repository" }
div { class: "form-group",
label { "Name" }
input {
r#type: "text",
value: "{edit_name}",
oninput: move |e| edit_name.set(e.value()),
}
}
div { class: "form-group",
label { "Default Branch" }
input {
r#type: "text",
value: "{edit_branch}",
oninput: move |e| edit_branch.set(e.value()),
}
}
h4 { style: "margin-top: 16px; margin-bottom: 8px; font-size: 14px; color: var(--text-secondary);", "Issue Tracker" }
div { class: "form-group",
label { "Tracker Type" }
select {
value: "{edit_tracker_type}",
onchange: move |e| edit_tracker_type.set(e.value()),
option { value: "", "None" }
option { value: "github", "GitHub" }
option { value: "gitlab", "GitLab" }
option { value: "gitea", "Gitea" }
option { value: "jira", "Jira" }
}
}
div { class: "form-group",
label { "Owner / Namespace" }
input {
r#type: "text",
placeholder: "org-name",
value: "{edit_tracker_owner}",
oninput: move |e| edit_tracker_owner.set(e.value()),
}
}
div { class: "form-group",
label { "Repository / Project" }
input {
r#type: "text",
placeholder: "repo-name",
value: "{edit_tracker_repo}",
oninput: move |e| edit_tracker_repo.set(e.value()),
}
}
div { class: "form-group",
label { "Tracker Token (leave empty to keep existing)" }
input {
r#type: "password",
placeholder: "Enter new token to change",
value: "{edit_tracker_token}",
oninput: move |e| edit_tracker_token.set(e.value()),
}
}
// Webhook configuration section
if let Some(secret) = edit_webhook_secret() {
h4 {
style: "margin-top: 16px; margin-bottom: 8px; font-size: 14px; color: var(--text-secondary);",
"Webhook Configuration"
}
p {
style: "font-size: 12px; color: var(--text-secondary); margin-bottom: 8px;",
"Add this webhook in your repository settings to enable push-triggered scans and PR reviews."
}
div { class: "form-group",
label { "Webhook URL" }
{
#[cfg(feature = "web")]
let origin = web_sys::window()
.and_then(|w: web_sys::Window| w.location().origin().ok())
.unwrap_or_default();
#[cfg(not(feature = "web"))]
let origin = String::new();
let webhook_url = format!("{origin}/webhook/{}/{eid}", edit_webhook_tracker());
rsx! {
div { class: "copyable",
input {
r#type: "text",
readonly: true,
style: "font-family: monospace; font-size: 12px; flex: 1;",
value: "{webhook_url}",
}
crate::components::copy_button::CopyButton { value: webhook_url.clone() }
}
}
}
}
div { class: "form-group",
label { "Webhook Secret" }
div { class: "copyable",
input {
r#type: "text",
readonly: true,
style: "font-family: monospace; font-size: 12px; flex: 1;",
value: "{secret}",
}
crate::components::copy_button::CopyButton { value: secret.clone() }
}
}
}
div { class: "modal-actions",
button {
class: "btn btn-secondary",
onclick: move |_| edit_repo_id.set(None),
"Cancel"
}
button {
class: "btn btn-primary",
disabled: edit_saving(),
onclick: move |_| {
let id = eid.clone();
let nm = { let v = edit_name(); if v.is_empty() { None } else { Some(v) } };
let br = { let v = edit_branch(); if v.is_empty() { None } else { Some(v) } };
let tt = { let v = edit_tracker_type(); if v.is_empty() { None } else { Some(v) } };
let t_owner = { let v = edit_tracker_owner(); if v.is_empty() { None } else { Some(v) } };
let t_repo = { let v = edit_tracker_repo(); if v.is_empty() { None } else { Some(v) } };
let t_tok = { let v = edit_tracker_token(); if v.is_empty() { None } else { Some(v) } };
edit_saving.set(true);
spawn(async move {
match crate::infrastructure::repositories::update_repository(
id, nm, br, None, None, tt, t_owner, t_repo, t_tok, None,
).await {
Ok(_) => {
toasts.push(ToastType::Success, "Repository updated");
repos.restart();
}
Err(e) => toasts.push(ToastType::Error, e.to_string()),
}
edit_saving.set(false);
edit_repo_id.set(None);
});
},
if edit_saving() { "Saving..." } else { "Save" }
}
}
}
}
}
match &*repos.read() {
Some(Some(resp)) => {
let total_pages = resp.total.unwrap_or(0).div_ceil(20).max(1);
rsx! {
div { class: "card",
div { class: "table-wrapper",
table {
thead {
tr {
th { "Name" }
th { "Git URL" }
th { "Branch" }
th { "Findings" }
th { "Last Scanned" }
th { "Actions" }
}
}
tbody {
for repo in &resp.data {
{
let repo_id = repo.id.as_ref().map(|id| id.to_hex()).unwrap_or_default();
let repo_id_scan = repo_id.clone();
let repo_id_del = repo_id.clone();
let repo_id_edit = repo_id.clone();
let repo_name_del = repo.name.clone();
let edit_repo_data = repo.clone();
let is_scanning = scanning_ids().contains(&repo_id);
rsx! {
tr {
td { "{repo.name}" }
td {
style: "font-size: 12px; font-family: monospace;",
"{repo.git_url}"
}
td { "{repo.default_branch}" }
td { "{repo.findings_count}" }
td {
{
let now = chrono::Utc::now();
let diff = now.signed_duration_since(repo.updated_at);
let label = if diff.num_minutes() < 1 {
"just now".to_string()
} else if diff.num_hours() < 1 {
format!("{}m ago", diff.num_minutes())
} else if diff.num_days() < 1 {
format!("{}h ago", diff.num_hours())
} else if diff.num_days() < 30 {
format!("{}d ago", diff.num_days())
} else {
repo.updated_at.format("%Y-%m-%d").to_string()
};
rsx! { span { style: "font-size: 12px;", "{label}" } }
}
}
td { style: "display: flex; gap: 4px;",
button {
class: if graph_repo_id().as_deref() == Some(repo_id.as_str()) { "btn btn-ghost btn-active" } else { "btn btn-ghost" },
title: "View graph",
onclick: {
let rid = repo_id.clone();
move |_| {
if graph_repo_id().as_deref() == Some(rid.as_str()) {
graph_repo_id.set(None);
} else {
graph_repo_id.set(Some(rid.clone()));
}
}
},
Icon { icon: BsDiagram3, width: 16, height: 16 }
}
button {
class: "btn btn-ghost",
title: "Edit repository",
onclick: move |_| {
edit_name.set(edit_repo_data.name.clone());
edit_branch.set(edit_repo_data.default_branch.clone());
edit_tracker_type.set(
edit_repo_data.tracker_type.as_ref().map(|t| t.to_string()).unwrap_or_default()
);
edit_tracker_owner.set(edit_repo_data.tracker_owner.clone().unwrap_or_default());
edit_tracker_repo.set(edit_repo_data.tracker_repo.clone().unwrap_or_default());
edit_tracker_token.set(String::new());
edit_webhook_secret.set(None);
edit_webhook_tracker.set(String::new());
edit_repo_id.set(Some(repo_id_edit.clone()));
// Fetch webhook config in background
let rid = repo_id_edit.clone();
spawn(async move {
if let Ok(cfg) = crate::infrastructure::repositories::fetch_webhook_config(rid).await {
edit_webhook_secret.set(cfg.webhook_secret);
edit_webhook_tracker.set(cfg.tracker_type);
}
});
},
Icon { icon: BsPencil, width: 16, height: 16 }
}
button {
class: if is_scanning { "btn btn-ghost btn-scanning" } else { "btn btn-ghost" },
title: "Trigger scan",
disabled: is_scanning,
onclick: move |_| {
let id = repo_id_scan.clone();
// Add to scanning set
let mut ids = scanning_ids();
ids.push(id.clone());
scanning_ids.set(ids);
spawn(async move {
match crate::infrastructure::repositories::trigger_repo_scan(id.clone()).await {
Ok(_) => {
toasts.push(ToastType::Success, "Scan triggered");
// Poll until scan completes
loop {
async_sleep_5s().await;
match crate::infrastructure::repositories::check_repo_scanning(id.clone()).await {
Ok(false) => break,
Ok(true) => continue,
Err(_) => break,
}
}
toasts.push(ToastType::Success, "Scan complete");
repos.restart();
}
Err(e) => toasts.push(ToastType::Error, e.to_string()),
}
// Remove from scanning set
let mut ids = scanning_ids();
ids.retain(|i| i != &id);
scanning_ids.set(ids);
});
},
if is_scanning {
span { class: "spinner" }
} else {
Icon { icon: BsPlayCircle, width: 16, height: 16 }
}
}
button {
class: "btn btn-ghost btn-ghost-danger",
title: "Delete repository",
onclick: move |_| {
confirm_delete.set(Some((repo_id_del.clone(), repo_name_del.clone())));
},
Icon { icon: BsTrash, width: 16, height: 16 }
}
}
}
}
}
}
}
}
}
Pagination {
current_page: page(),
total_pages: total_pages,
on_page_change: move |p| page.set(p),
}
}
// Inline graph explorer
if let Some(rid) = graph_repo_id() {
div { class: "card", style: "margin-top: 16px;",
div { class: "card-header", style: "display: flex; justify-content: space-between; align-items: center;",
span { "Code Graph" }
button {
class: "btn btn-sm btn-ghost",
title: "Close graph",
onclick: move |_| { graph_repo_id.set(None); },
Icon { icon: BsX, width: 18, height: 18 }
}
}
GraphExplorerInline { repo_id: rid }
}
}
}
},
Some(None) => rsx! {
div { class: "card", p { "Failed to load repositories." } }
},
None => rsx! {
div { class: "loading", "Loading repositories..." }
},
}
}
}
+36
View File
@@ -0,0 +1,36 @@
<?xml version="1.0" encoding="utf-8"?>
<!-- Demo PLCopen project — conveyor sorter. Deliberately vulnerable. -->
<project xmlns="http://www.plcopen.org/xml/tc6_0201">
<types>
<pous>
<pou name="ConveyorCtrl" pouType="program">
<interface>
<localVars>
<variable name="AdminPwd">
<type><string/></type>
<initialValue><simpleValue value="password"/></initialValue>
</variable>
<variable name="Belt">
<type>
<array>
<dimension lower="0" upper="3"/>
<baseType><INT/></baseType>
</array>
</type>
</variable>
</localVars>
<inputVars>
<variable name="Slot"><type><INT/></type></variable>
</inputVars>
</interface>
<body>
<ST>
<xhtml xmlns="http://www.w3.org/1999/xhtml">Belt[Slot] := 1;
Ftp_Send(HOST := '192.168.1.5', PORT := 21, ENCRYPT := FALSE);
</xhtml>
</ST>
</body>
</pou>
</pous>
</types>
</project>
+57
View File
@@ -0,0 +1,57 @@
(*
* Demo PLC program pump-station control (IEC 61131-3 Structured Text).
*
* Deliberately vulnerable, for the compliance-scanner PLC control-logic demo.
* Each issue below is flagged by pipeline::plc::rules.
*)
FUNCTION_BLOCK PumpStationCtrl
VAR_INPUT
OperatorCmd : INT; (* HMI command index untrusted *)
FlowSetpoint : REAL;
END_VAR
VAR_OUTPUT
PumpSpeed : REAL;
Fault : BOOL;
END_VAR
VAR
HmiPassword : STRING := 'admin123'; (* hardcoded + default credential *)
ApiKey : STRING := 'sk_live_9c1f2a'; (* hardcoded secret *)
PumpProfiles : ARRAY[0..7] OF REAL;
Safety_Enable : BOOL := TRUE;
Watchdog_Kick : INT := 1;
MeasuredFlow : REAL;
ScaleFactor : REAL;
i : INT;
END_VAR
(* Operator can index the profile table with an unvalidated command. *)
PumpSpeed := PumpProfiles[OperatorCmd];
(* Divisor is a live process value that can read zero on a stopped line. *)
ScaleFactor := FlowSetpoint / MeasuredFlow;
(* Safety interlock disabled straight from application logic. *)
IF OperatorCmd = 99 THEN
Safety_Enable := FALSE;
Watchdog_Kick := 0;
END_IF;
(* Unauthenticated Modbus/TCP link on the cleartext OT port. *)
Modbus_TCP_Connect(IP := '10.10.5.20', PORT := 502, AUTH := FALSE, PASSWORD := 'plc');
(* Unstructured jump around the fault handler. *)
IF MeasuredFlow > 1000.0 THEN
JMP trip;
END_IF;
(* A correctly guarded division must NOT be flagged. *)
IF ScaleFactor <> 0.0 THEN
PumpSpeed := PumpSpeed / ScaleFactor;
END_IF;
RETURN;
trip:
Fault := TRUE;
PumpSpeed := 0.0;
END_FUNCTION_BLOCK
+92
View File
@@ -0,0 +1,92 @@
(*
* Pedestrian-crossing traffic-light controller.
*
* Structure adapted from the classic OpenPLC "traffic light" example
* (github.com/thiagoralves/OpenPLC_v3 examples) a timed state machine
* driving vehicle + pedestrian lamps, extended with a SCADA/Modbus link
* and a maintenance override so it reads like a real deployed program.
*
* The control logic itself is sound; the security-relevant defects are the
* kind that slip into field code under deadline: a hardcoded SCADA password,
* a cleartext Modbus/TCP master, and a maintenance mode that drops the
* pedestrian safety permit. Everything else should stay quiet.
*)
PROGRAM TrafficLight
VAR
State : INT := 0; (* 0 GreenVeh, 1 Amber, 2 RedVeh/WalkPed, 3 FlashPed *)
Tmr : TON;
StateElapsed : TIME;
CycleMs : DINT := 0;
(* Lamp outputs *)
VehGreen : BOOL := FALSE;
VehAmber : BOOL := FALSE;
VehRed : BOOL := FALSE;
PedWalk : BOOL := FALSE;
PedStop : BOOL := TRUE;
(* Pedestrian safety permit must be TRUE before the WALK phase asserts *)
PedPermit : BOOL := TRUE;
PedButton : BOOL := FALSE;
(* SCADA / remote monitoring *)
ScadaUser : STRING := 'operator';
ScadaPassword : STRING := 'Tr@ffic2019'; (* hardcoded SCADA credential *)
ModbusReady : BOOL := FALSE;
(* Maintenance override *)
MaintMode : BOOL := FALSE;
LampCount : INT := 5;
DutyPct : INT;
END_VAR
(* ---- SCADA uplink: publish state to the control room over Modbus/TCP ---- *)
IF NOT ModbusReady THEN
Modbus_TCP_Master(IP := '10.20.0.5', PORT := 502, AUTH := FALSE, USER := ScadaUser, PASS := ScadaPassword);
ModbusReady := TRUE;
END_IF;
(* ---- Duty-cycle for the flashing pedestrian lamp (guarded division) ---- *)
IF LampCount <> 0 THEN
DutyPct := (CycleMs * 100) / LampCount;
END_IF;
(* ---- Maintenance override: flash amber, hand control to the technician ---- *)
IF MaintMode THEN
VehGreen := FALSE;
VehRed := FALSE;
VehAmber := NOT VehAmber;
PedPermit := FALSE; (* drops the pedestrian safety permit in code *)
PedWalk := FALSE;
PedStop := TRUE;
ELSE
(* ---- Normal timed state machine ---- *)
Tmr(IN := TRUE, PT := T#5s);
StateElapsed := Tmr.ET;
CASE State OF
0: (* vehicles go, pedestrians stop *)
VehGreen := TRUE; VehAmber := FALSE; VehRed := FALSE;
PedWalk := FALSE; PedStop := TRUE;
IF PedButton AND Tmr.Q THEN
State := 1; Tmr(IN := FALSE);
END_IF;
1: (* amber transition *)
VehGreen := FALSE; VehAmber := TRUE;
IF Tmr.Q THEN State := 2; Tmr(IN := FALSE); END_IF;
2: (* vehicles stop, pedestrians walk only if permitted *)
VehAmber := FALSE; VehRed := TRUE;
IF PedPermit THEN
PedWalk := TRUE; PedStop := FALSE;
END_IF;
IF Tmr.Q THEN State := 3; Tmr(IN := FALSE); END_IF;
3: (* flashing don't-walk before returning to green *)
PedWalk := NOT PedWalk;
IF Tmr.Q THEN
State := 0; PedButton := FALSE; Tmr(IN := FALSE);
END_IF;
ELSE
State := 0;
END_CASE;
END_IF;
END_PROGRAM