feat: control-driven SAST — LUT + grounded LLM triage over tool findings (#213)

compliance-agent/Cargo.toml

@@ -8,6 +8,7 @@ workspace = true
 
 [dependencies]
 compliance-core = { workspace = true, features = ["mongodb", "telemetry", "axum"] }
+control-map = { workspace = true }
 compliance-graph = { path = "../compliance-graph" }
 compliance-dast = { path = "../compliance-dast" }
 # Shared dynamic-execution logic (soft-PLC provisioning + ICS probing), also

compliance-agent/src/controls/checker.rs

@@ -0,0 +1,114 @@
+//! The grounded control checker: judge each candidate region for a control, then
+//! keep only the verdicts that survive the grounding gate.
+//!
+//! Generic over [`ControlJudge`] so tests drive it with a deterministic stub —
+//! the whole recognize → ground path is then exercised without an LLM. With the
+//! real judge, determinism comes from temperature 0 plus the gate.
+
+use compliance_core::control_check::{ground, CandidateRegion, ControlCheckSpec};
+use compliance_core::models::Finding;
+
+use super::judge::ControlJudge;
+
+/// Runs a [`ControlJudge`] over candidate regions and grounds the results.
+pub struct GroundedControlChecker<J> {
+    judge: J,
+}
+
+impl<J: ControlJudge> GroundedControlChecker<J> {
+    pub fn new(judge: J) -> Self {
+        Self { judge }
+    }
+
+    /// Judge every candidate region for `spec` and return the grounded findings.
+    /// A verdict that doesn't quote real code in its region is dropped by
+    /// [`ground`], so nothing fabricated reaches the caller.
+    pub async fn check(
+        &self,
+        spec: &ControlCheckSpec,
+        regions: &[CandidateRegion],
+        repo_id: &str,
+    ) -> Vec<Finding> {
+        let mut findings = Vec::new();
+        for region in regions {
+            let verdict = self.judge.judge(spec, region).await;
+            if let Some(finding) = ground(spec, region, &verdict, repo_id) {
+                findings.push(finding);
+            }
+        }
+        findings
+    }
+}
+
+#[cfg(test)]
+mod tests {
+    use super::*;
+    use compliance_core::control_check::LlmVerdict;
+    use compliance_core::models::finding::Severity;
+
+    /// Deterministic stub: returns a fixed verdict for every region, so the
+    /// recognize → ground composition is tested without an LLM.
+    struct StubJudge {
+        verdict: LlmVerdict,
+    }
+
+    impl ControlJudge for StubJudge {
+        async fn judge(&self, _spec: &ControlCheckSpec, _region: &CandidateRegion) -> LlmVerdict {
+            self.verdict.clone()
+        }
+    }
+
+    fn spec() -> ControlCheckSpec {
+        ControlCheckSpec {
+            control_id: "cra-ai-8".into(),
+            title: "No default passwords".into(),
+            requirement: "No default credentials".into(),
+            default_cwe: Some("CWE-798".into()),
+            severity: Severity::High,
+        }
+    }
+
+    fn region(content: &str) -> CandidateRegion {
+        CandidateRegion {
+            file: "src/auth.py".into(),
+            start_line: 1,
+            content: content.into(),
+        }
+    }
+
+    #[tokio::test]
+    async fn keeps_grounded_and_drops_ungrounded() {
+        let checker = GroundedControlChecker::new(StubJudge {
+            verdict: LlmVerdict {
+                violates: true,
+                snippet: "PASSWORD = \"admin\"".into(),
+                cwe: None,
+                confidence: 0.9,
+            },
+        });
+        let regions = vec![
+            region("x = 1\nPASSWORD = \"admin\"\n"), // quotes real code → grounded
+            region("totally unrelated code\n"),      // snippet absent → dropped
+        ];
+        let findings = checker.check(&spec(), &regions, "repo").await;
+        assert_eq!(findings.len(), 1);
+        assert_eq!(findings[0].control_refs, vec!["cra-ai-8".to_string()]);
+        assert_eq!(findings[0].line_number, Some(2));
+    }
+
+    #[tokio::test]
+    async fn non_violation_yields_nothing() {
+        let checker = GroundedControlChecker::new(StubJudge {
+            verdict: LlmVerdict {
+                violates: false,
+                snippet: String::new(),
+                cwe: None,
+                confidence: 0.0,
+            },
+        });
+        let findings = checker
+            .check(&spec(), &[region("PASSWORD = \"admin\"\n")], "repo")
+            .await;
+        assert!(findings.is_empty());
+    }
+}

compliance-agent/src/controls/judge.rs

@@ -0,0 +1,167 @@
+//! The "recognize" stage: judge whether a code region violates a control.
+//!
+//! Behind the [`ControlJudge`] trait so the grounded checker can be driven by a
+//! deterministic stub in tests. The real [`LlmControlJudge`] runs the model at
+//! temperature 0 with a closed prompt — it must quote the offending code VERBATIM,
+//! and everything it returns is then re-checked by the grounding gate
+//! ([`compliance_core::control_check::ground`]). The judge is allowed to be
+//! smart; it is never trusted.
+
+use std::sync::Arc;
+
+use serde::Deserialize;
+
+use compliance_core::control_check::{CandidateRegion, ControlCheckSpec, LlmVerdict};
+
+use crate::llm::LlmClient;
+
+/// Prompt/logic version — part of the verdict cache key, bump on any change here.
+pub const PROMPT_VERSION: &str = "control-judge-v1";
+
+const SYSTEM_PROMPT: &str = "You are a precise security & compliance code auditor. \
+You are given ONE compliance control (a requirement) and ONE code region. Decide \
+ONLY whether the code region VIOLATES the control. Rules: (1) Judge only the code \
+shown — never assume code that is not present. (2) If and only if it violates, copy \
+the EXACT offending code VERBATIM into `snippet`, character-for-character from the \
+region — do not paraphrase, reformat, or reconstruct it. (3) If it does not clearly \
+violate, set violates=false and leave snippet empty. (4) Prefer false over guessing. \
+Respond with STRICT JSON only, no prose: \
+{\"violates\": bool, \"snippet\": \"<verbatim code or empty>\", \"cwe\": \"CWE-NNN or null\", \"confidence\": 0.0-1.0}";
+
+/// Judges one (control, region). Async-in-trait so a stub can drive tests.
+#[allow(async_fn_in_trait)]
+pub trait ControlJudge: Send + Sync {
+    async fn judge(&self, spec: &ControlCheckSpec, region: &CandidateRegion) -> LlmVerdict;
+}
+
+/// The real judge: the LLM at temperature 0 with the closed, verbatim-snippet prompt.
+pub struct LlmControlJudge {
+    llm: Arc<LlmClient>,
+}
+
+impl LlmControlJudge {
+    pub fn new(llm: Arc<LlmClient>) -> Self {
+        Self { llm }
+    }
+}
+
+impl ControlJudge for LlmControlJudge {
+    async fn judge(&self, spec: &ControlCheckSpec, region: &CandidateRegion) -> LlmVerdict {
+        let user = build_user_prompt(spec, region);
+        match self.llm.chat(SYSTEM_PROMPT, &user, Some(0.0)).await {
+            Ok(response) => parse_verdict(&response),
+            Err(e) => {
+                // Fail closed: a transient model error yields no finding, never a
+                // fabricated one.
+                tracing::warn!(control = %spec.control_id, error = %e, "control judge call failed");
+                no_violation()
+            }
+        }
+    }
+}
+
+fn build_user_prompt(spec: &ControlCheckSpec, region: &CandidateRegion) -> String {
+    format!(
+        "CONTROL {id} — {title}\nRequirement: {req}\n\nCODE ({file}, first line = {line}):\n```\n{code}\n```\n\nReturn the JSON verdict.",
+        id = spec.control_id,
+        title = spec.title,
+        req = spec.requirement,
+        file = region.file,
+        line = region.start_line,
+        code = region.content,
+    )
+}
+
+#[derive(Debug, Default, Deserialize)]
+struct RawVerdict {
+    #[serde(default)]
+    violates: bool,
+    #[serde(default)]
+    snippet: String,
+    #[serde(default)]
+    cwe: Option<String>,
+    #[serde(default)]
+    confidence: f64,
+}
+
+/// Parse the model's JSON verdict, tolerant of ```json fencing. Any parse failure
+/// degrades to a non-violation (never a fabricated finding).
+fn parse_verdict(response: &str) -> LlmVerdict {
+    let cleaned = response
+        .trim()
+        .trim_start_matches("```json")
+        .trim_start_matches("```")
+        .trim_end_matches("```")
+        .trim();
+    match serde_json::from_str::<RawVerdict>(cleaned) {
+        Ok(raw) => LlmVerdict {
+            violates: raw.violates,
+            snippet: raw.snippet,
+            cwe: raw.cwe.filter(|c| !c.trim().is_empty()),
+            confidence: raw.confidence,
+        },
+        Err(e) => {
+            tracing::debug!(error = %e, "failed to parse control verdict; treating as non-violation");
+            no_violation()
+        }
+    }
+}
+
+fn no_violation() -> LlmVerdict {
+    LlmVerdict {
+        violates: false,
+        snippet: String::new(),
+        cwe: None,
+        confidence: 0.0,
+    }
+}
+
+#[cfg(test)]
+mod tests {
+    use super::*;
+    use compliance_core::models::finding::Severity;
+
+    fn spec() -> ControlCheckSpec {
+        ControlCheckSpec {
+            control_id: "cra-ai-8".into(),
+            title: "No default passwords".into(),
+            requirement: "Products must not ship default credentials".into(),
+            default_cwe: Some("CWE-798".into()),
+            severity: Severity::High,
+        }
+    }
+
+    #[test]
+    fn parses_plain_and_fenced_json() {
+        let plain = r#"{"violates": true, "snippet": "PASSWORD = \"x\"", "cwe": "CWE-798", "confidence": 0.9}"#;
+        let v = parse_verdict(plain);
+        assert!(v.violates);
+        assert_eq!(v.snippet, "PASSWORD = \"x\"");
+        assert_eq!(v.cwe.as_deref(), Some("CWE-798"));
+
+        let fenced = "```json\n{\"violates\": false, \"snippet\": \"\", \"cwe\": null, \"confidence\": 0.1}\n```";
+        assert!(!parse_verdict(fenced).violates);
+    }
+
+    #[test]
+    fn garbage_and_empty_cwe_are_safe() {
+        assert!(!parse_verdict("not json at all").violates); // fail closed
+        let no_cwe =
+            parse_verdict(r#"{"violates": true, "snippet": "x", "cwe": "  ", "confidence": 0.5}"#);
+        assert!(no_cwe.cwe.is_none()); // blank CWE normalised away
+    }
+
+    #[test]
+    fn user_prompt_carries_control_and_code() {
+        let region = CandidateRegion {
+            file: "src/auth.py".into(),
+            start_line: 10,
+            content: "PASSWORD = \"admin\"".into(),
+        };
+        let p = build_user_prompt(&spec(), &region);
+        assert!(p.contains("cra-ai-8"));
+        assert!(p.contains("Products must not ship default credentials"));
+        assert!(p.contains("PASSWORD = \"admin\""));
+        assert!(p.contains("src/auth.py"));
+    }
+}

compliance-agent/src/controls/mod.rs

@@ -5,6 +5,14 @@
 //! [`OscalControlsProvider`], which pulls breakpilot-compliance's OSCAL catalog
 //! and snapshots it locally.
 
+mod checker;
+mod judge;
 mod oscal_provider;
+mod scan_triage;
+mod triage;
 
+pub use checker::GroundedControlChecker;
+pub use judge::{ControlJudge, LlmControlJudge, PROMPT_VERSION};
 pub use oscal_provider::OscalControlsProvider;
+pub use scan_triage::triage_repo_findings;
+pub use triage::{ControlTriage, TriageOutcome};

compliance-agent/src/controls/scan_triage.rs

@@ -0,0 +1,139 @@
+//! Scan-pipeline integration for control triage.
+//!
+//! After the deterministic tools have produced findings, this stamps each finding
+//! with the compliance control(s) it's evidence for and marks control-level false
+//! positives — using the ingested OSCAL catalog for control text, the
+//! `control-map` LUT for the finding→control link, and the grounded LLM judge to
+//! confirm. Skipped entirely unless breakpilot is configured.
+
+use std::collections::HashMap;
+use std::path::Path;
+use std::sync::Arc;
+
+use compliance_core::control_check::{CandidateRegion, ControlCheckSpec};
+use compliance_core::models::finding::{Finding, FindingStatus, Severity};
+use compliance_core::models::onboarding::ComplianceFramework;
+use compliance_core::AgentConfig;
+use control_map::ControlMap;
+
+use super::{ControlTriage, LlmControlJudge, OscalControlsProvider, TriageOutcome};
+use crate::llm::LlmClient;
+
+/// Lines of context to read on each side of a finding's line.
+const REGION_WINDOW: usize = 6;
+
+/// Triage every finding in `findings` against the CRA control map: stamp
+/// `control_refs` on confirmed findings and flag control false positives. Returns
+/// the number of findings tagged with at least one control.
+pub async fn triage_repo_findings(
+    config: &AgentConfig,
+    llm: Arc<LlmClient>,
+    repo_path: &Path,
+    findings: &mut [Finding],
+) -> usize {
+    let Some(base_url) = config.breakpilot.base_url.clone() else {
+        return 0; // control triage is opt-in via BREAKPILOT_BASE_URL
+    };
+    let provider = OscalControlsProvider::new(
+        reqwest::Client::new(),
+        base_url,
+        config.breakpilot.token.clone(),
+        &config.breakpilot.snapshot_dir,
+    );
+    let specs = build_specs(&provider).await;
+    if specs.is_empty() {
+        return 0;
+    }
+    let map = match ControlMap::cra() {
+        Ok(m) => m,
+        Err(e) => {
+            tracing::warn!(error = %e, "control map failed to load; skipping control triage");
+            return 0;
+        }
+    };
+    let triage = ControlTriage::new(LlmControlJudge::new(llm), map, specs);
+
+    let mut tagged = 0;
+    for finding in findings.iter_mut() {
+        let (Some(file), Some(line)) = (finding.file_path.clone(), finding.line_number) else {
+            continue;
+        };
+        let Some(region) = fetch_region(repo_path, &file, line) else {
+            continue;
+        };
+        match triage.triage(finding, &region).await {
+            TriageOutcome::Confirmed(controls) => {
+                finding.control_refs = controls;
+                tagged += 1;
+            }
+            TriageOutcome::FalsePositive => {
+                finding.status = FindingStatus::FalsePositive;
+                finding.triage_action = Some("control_false_positive".to_string());
+            }
+            TriageOutcome::Unmapped => {}
+        }
+    }
+    tagged
+}
+
+/// Build the control requirement specs (by id) from the ingested OSCAL catalog.
+async fn build_specs(provider: &OscalControlsProvider) -> HashMap<String, ControlCheckSpec> {
+    let mut specs = HashMap::new();
+    match provider.load(ComplianceFramework::Cra).await {
+        Ok(doc) => {
+            for control in doc.to_controls() {
+                specs.insert(
+                    control.id.clone(),
+                    ControlCheckSpec {
+                        control_id: control.id,
+                        title: control.title,
+                        requirement: control.text,
+                        default_cwe: None,
+                        severity: Severity::Medium,
+                    },
+                );
+            }
+        }
+        Err(e) => tracing::warn!(error = %e, "could not load control catalog for triage"),
+    }
+    specs
+}
+
+/// Read a window of lines around `line` (1-based) from `repo_path/file`.
+fn fetch_region(repo_path: &Path, file: &str, line: u32) -> Option<CandidateRegion> {
+    let content = std::fs::read_to_string(repo_path.join(file)).ok()?;
+    let lines: Vec<&str> = content.lines().collect();
+    if lines.is_empty() {
+        return None;
+    }
+    let center = (line.saturating_sub(1) as usize).min(lines.len() - 1);
+    let start = center.saturating_sub(REGION_WINDOW);
+    let end = (center + REGION_WINDOW + 1).min(lines.len());
+    Some(CandidateRegion {
+        file: file.to_string(),
+        start_line: (start as u32) + 1,
+        content: lines[start..end].join("\n"),
+    })
+}
+
+#[cfg(test)]
+mod tests {
+    use super::*;
+
+    #[test]
+    fn fetch_region_windows_around_the_line() {
+        let dir = std::env::temp_dir().join(format!("triage-region-{}", uuid::Uuid::new_v4()));
+        std::fs::create_dir_all(&dir).unwrap();
+        let file = "a.py";
+        std::fs::write(dir.join(file), "l1\nl2\nl3\nSECRET=1\nl5\nl6\n").unwrap();
+        let r = fetch_region(&dir, file, 4).unwrap();
+        assert!(r.content.contains("SECRET=1"));
+        assert_eq!(r.start_line, 1); // window clamps to file start
+        let _ = std::fs::remove_dir_all(&dir);
+    }
+
+    #[test]
+    fn fetch_region_missing_file_is_none() {
+        assert!(fetch_region(Path::new("/nonexistent"), "nope.py", 1).is_none());
+    }
+}

compliance-agent/src/controls/triage.rs

@@ -0,0 +1,184 @@
+//! Triage step: confirm/refute a deterministic tool finding against the controls
+//! it maps to (via the `control-map` LUT), grounding the judgment.
+//!
+//! This is where the LLM finally enters — as a **false-positive filter over tool
+//! output**, never as the detector (the ZeroFalse / IRIS pattern). A tool
+//! (semgrep, gitleaks, syft/osv) detects deterministically; `controls_for(tool,
+//! cwe)` attaches the finding to the control(s) it's evidence for; the grounded
+//! judge then confirms or refutes each, and only judgments anchored to real code
+//! survive.
+
+use std::collections::HashMap;
+
+use compliance_core::control_check::{ground, CandidateRegion, ControlCheckSpec};
+use compliance_core::models::Finding;
+use control_map::ControlMap;
+
+use super::judge::ControlJudge;
+
+/// What triage decided for one tool finding.
+#[derive(Debug, Clone, PartialEq, Eq)]
+pub enum TriageOutcome {
+    /// The finding maps to no control in the LUT — keep it, untagged.
+    Unmapped,
+    /// Maps to controls and the grounded judge confirmed at least one — keep the
+    /// finding and tag it with these control ids.
+    Confirmed(Vec<String>),
+    /// Maps to controls but the judge grounded none — treat as a false positive.
+    FalsePositive,
+}
+
+/// Triages tool findings against the control map, confirming with a grounded judge.
+pub struct ControlTriage<J> {
+    judge: J,
+    map: ControlMap,
+    /// Control requirement specs (by control id), built from the ingested catalog.
+    specs: HashMap<String, ControlCheckSpec>,
+}
+
+impl<J: ControlJudge> ControlTriage<J> {
+    pub fn new(judge: J, map: ControlMap, specs: HashMap<String, ControlCheckSpec>) -> Self {
+        Self { judge, map, specs }
+    }
+
+    /// Triage one tool finding. `region` is the code around the finding, used as
+    /// the grounding evidence for the judge.
+    pub async fn triage(&self, finding: &Finding, region: &CandidateRegion) -> TriageOutcome {
+        let Some(cwe) = finding.cwe.as_deref() else {
+            return TriageOutcome::Unmapped;
+        };
+        let mapped = self.map.controls_for(&finding.scanner, cwe);
+        if mapped.is_empty() {
+            return TriageOutcome::Unmapped;
+        }
+
+        let mut confirmed = Vec::new();
+        for entry in mapped {
+            let Some(spec) = self.specs.get(&entry.control) else {
+                continue;
+            };
+            let verdict = self.judge.judge(spec, region).await;
+            // The verdict only counts if it grounds to real code in the region.
+            if ground(spec, region, &verdict, &finding.repo_id).is_some() {
+                confirmed.push(entry.control.clone());
+            }
+        }
+
+        if confirmed.is_empty() {
+            TriageOutcome::FalsePositive
+        } else {
+            TriageOutcome::Confirmed(confirmed)
+        }
+    }
+}
+
+#[cfg(test)]
+mod tests {
+    use super::*;
+    use compliance_core::control_check::LlmVerdict;
+    use compliance_core::models::finding::Severity;
+    use compliance_core::models::scan::ScanType;
+
+    struct StubJudge {
+        verdict: LlmVerdict,
+    }
+    impl ControlJudge for StubJudge {
+        async fn judge(&self, _s: &ControlCheckSpec, _r: &CandidateRegion) -> LlmVerdict {
+            self.verdict.clone()
+        }
+    }
+
+    fn specs() -> HashMap<String, ControlCheckSpec> {
+        let mut m = HashMap::new();
+        m.insert(
+            "cra-ai-8".to_string(),
+            ControlCheckSpec {
+                control_id: "cra-ai-8".into(),
+                title: "No default passwords".into(),
+                requirement: "No default credentials".into(),
+                default_cwe: Some("CWE-798".into()),
+                severity: Severity::High,
+            },
+        );
+        m
+    }
+
+    fn semgrep_finding(cwe: &str) -> Finding {
+        let mut f = Finding::new(
+            "repo".into(),
+            "fp1".into(),
+            "semgrep".into(),
+            ScanType::Sast,
+            "hardcoded credential".into(),
+            "desc".into(),
+            Severity::High,
+        );
+        f.cwe = Some(cwe.into());
+        f
+    }
+
+    fn region() -> CandidateRegion {
+        CandidateRegion {
+            file: "src/auth.py".into(),
+            start_line: 1,
+            content: "PASSWORD = \"admin123\"\n".into(),
+        }
+    }
+
+    #[tokio::test]
+    async fn confirmed_finding_is_tagged_with_control() {
+        let triage = ControlTriage::new(
+            StubJudge {
+                verdict: LlmVerdict {
+                    violates: true,
+                    snippet: "PASSWORD = \"admin123\"".into(),
+                    cwe: None,
+                    confidence: 0.9,
+                },
+            },
+            ControlMap::cra().unwrap(),
+            specs(),
+        );
+        let out = triage.triage(&semgrep_finding("CWE-798"), &region()).await;
+        assert_eq!(out, TriageOutcome::Confirmed(vec!["cra-ai-8".to_string()]));
+    }
+
+    #[tokio::test]
+    async fn refuted_mapped_finding_is_false_positive() {
+        // Maps to cra-ai-8, but the judge doesn't confirm (no violation) → FP.
+        let triage = ControlTriage::new(
+            StubJudge {
+                verdict: LlmVerdict {
+                    violates: false,
+                    snippet: String::new(),
+                    cwe: None,
+                    confidence: 0.1,
+                },
+            },
+            ControlMap::cra().unwrap(),
+            specs(),
+        );
+        let out = triage.triage(&semgrep_finding("CWE-798"), &region()).await;
+        assert_eq!(out, TriageOutcome::FalsePositive);
+    }
+
+    #[tokio::test]
+    async fn unmapped_cwe_is_left_untagged() {
+        let triage = ControlTriage::new(
+            StubJudge {
+                verdict: LlmVerdict {
+                    violates: true,
+                    snippet: "PASSWORD = \"admin123\"".into(),
+                    cwe: None,
+                    confidence: 0.9,
+                },
+            },
+            ControlMap::cra().unwrap(),
+            specs(),
+        );
+        let out = triage
+            .triage(&semgrep_finding("CWE-99999"), &region())
+            .await;
+        assert_eq!(out, TriageOutcome::Unmapped);
+    }
+}

compliance-agent/src/pipeline/orchestrator.rs

@@ -215,6 +215,21 @@ impl PipelineOrchestrator {
         .await;
         tracing::info!("[{repo_id}] Triaged: {triaged} findings passed confidence threshold");
 
+        // Stage 5b: control triage — stamp findings with the compliance control(s)
+        // they're evidence for and flag control false positives (grounded LLM over
+        // deterministic tool output). No-op unless breakpilot is configured.
+        self.update_phase(scan_run_id, "control_triage").await;
+        let tagged = crate::controls::triage_repo_findings(
+            &self.config,
+            self.llm.clone(),
+            &repo_path,
+            &mut all_findings,
+        )
+        .await;
+        if tagged > 0 {
+            tracing::info!("[{repo_id}] Control triage tagged {tagged} findings with control refs");
+        }
+
         // Dedup against existing findings and insert new ones
         let mut new_count = 0u32;
         let mut new_findings: Vec<Finding> = Vec::new();

compliance-agent/src/pipeline/semgrep.rs

@@ -82,10 +82,7 @@ impl Scanner for SemgrepScanner {
                 finding.file_path = Some(r.path);
                 finding.line_number = Some(r.start.line);
                 finding.code_snippet = Some(r.extra.lines);
-                finding.cwe = r
-                    .extra
-                    .metadata
-                    .and_then(|m| m.get("cwe").and_then(|v| v.as_str()).map(|s| s.to_string()));
+                finding.cwe = r.extra.metadata.as_ref().and_then(extract_cwe);
                 finding
             })
             .collect();
@@ -124,10 +121,34 @@ struct SemgrepExtra {
     metadata: Option<serde_json::Value>,
 }
 
+/// semgrep emits `metadata.cwe` as a list of strings like
+/// `"CWE-798: Use of Hard-coded Credentials"` (occasionally a bare string). Take
+/// the first entry and normalise it to just the `CWE-NNN` id.
+fn extract_cwe(metadata: &serde_json::Value) -> Option<String> {
+    let raw = metadata.get("cwe")?;
+    let text = match raw {
+        serde_json::Value::Array(items) => items.first()?.as_str()?,
+        serde_json::Value::String(s) => s.as_str(),
+        _ => return None,
+    };
+    let id = text.split(':').next().unwrap_or(text).trim();
+    (!id.is_empty()).then(|| id.to_string())
+}
+
 #[cfg(test)]
 mod tests {
     use super::*;
 
+    #[test]
+    fn extract_cwe_handles_list_and_normalises() {
+        let md = serde_json::json!({"cwe": ["CWE-798: Use of Hard-coded Credentials"]});
+        assert_eq!(extract_cwe(&md).as_deref(), Some("CWE-798"));
+        let bare = serde_json::json!({"cwe": "CWE-89"});
+        assert_eq!(extract_cwe(&bare).as_deref(), Some("CWE-89"));
+        let none = serde_json::json!({"severity": "ERROR"});
+        assert_eq!(extract_cwe(&none), None);
+    }
+
     #[test]
     fn deserialize_semgrep_output() {
         let json = r#"{