feat(controls): B1 — custom semgrep detectors for 4 CRA controls (#218)

compliance-agent/rules/cra_semgrep.yaml

@@ -0,0 +1,117 @@
+# Custom semgrep rules for CRA controls that no off-the-shelf ruleset digs out.
+# Each rule id is `cra-ai-<n>-<slug>` and is keyed back to its control via the
+# `control-map` LUT (by rule-id suffix, so semgrep's path prefix on check_id does
+# not matter). Detection here is deterministic; the grounded LLM judge downstream
+# only confirms/refutes — it never detects. Keep patterns tight: a false positive
+# that the judge refutes marks the whole finding a false positive.
+rules:
+  # --- cra-ai-1: Secure-by-Default-Konfiguration -------------------------------
+  - id: cra-ai-1-flask-debug-enabled
+    languages: [python]
+    severity: WARNING
+    message: Flask app started with debug=True — ships an interactive debugger / code execution in production (secure-by-default violation).
+    metadata:
+      cwe: ["CWE-489: Active Debug Code"]
+      control: cra-ai-1
+    patterns:
+      - pattern: '$APP.run(..., debug=True, ...)'
+
+  - id: cra-ai-1-django-debug-true
+    languages: [python]
+    severity: WARNING
+    message: Django DEBUG = True — leaks stack traces / settings in production (secure-by-default violation).
+    metadata:
+      cwe: ["CWE-489: Active Debug Code"]
+      control: cra-ai-1
+    patterns:
+      - pattern: 'DEBUG = True'
+
+  - id: cra-ai-1-tls-verify-disabled
+    languages: [python]
+    severity: ERROR
+    message: TLS certificate verification disabled (verify=False) — defeats transport security by default.
+    metadata:
+      cwe: ["CWE-295: Improper Certificate Validation"]
+      control: cra-ai-1
+    patterns:
+      - pattern: 'requests.$M(..., verify=False, ...)'
+
+  - id: cra-ai-1-cors-wildcard
+    languages: [javascript, typescript]
+    severity: WARNING
+    message: CORS Access-Control-Allow-Origin set to "*" — opens the API to any origin by default.
+    metadata:
+      cwe: ["CWE-942: Permissive Cross-domain Policy with Untrusted Domains"]
+      control: cra-ai-1
+    patterns:
+      - pattern-either:
+          - pattern: '$RES.header("Access-Control-Allow-Origin", "*")'
+          - pattern: '$RES.setHeader("Access-Control-Allow-Origin", "*")'
+
+  # --- cra-ai-7: Starke Authentifizierung (weak password hashing) --------------
+  - id: cra-ai-7-weak-password-hash
+    languages: [python]
+    severity: ERROR
+    message: Password/secret hashed with a fast, broken digest (md5/sha1) — use a password KDF (bcrypt/scrypt/argon2).
+    metadata:
+      cwe: ["CWE-916: Use of Password Hash With Insufficient Computational Effort"]
+      control: cra-ai-7
+    patterns:
+      - pattern-either:
+          - pattern: 'hashlib.md5($PW)'
+          - pattern: 'hashlib.sha1($PW)'
+      - metavariable-regex:
+          metavariable: $PW
+          regex: '(?i).*(pass|pwd|secret|cred|token).*'
+
+  # --- cra-ai-10: Sitzungsmanagement (insecure session cookies) ----------------
+  - id: cra-ai-10-session-cookie-insecure
+    languages: [python]
+    severity: ERROR
+    message: Session cookie hardened flag explicitly disabled (Secure/HttpOnly = False) — session token exposed to theft.
+    metadata:
+      cwe: ["CWE-614: Sensitive Cookie in HTTPS Session Without 'Secure' Attribute"]
+      control: cra-ai-10
+    patterns:
+      - pattern-either:
+          - pattern: 'SESSION_COOKIE_SECURE = False'
+          - pattern: 'SESSION_COOKIE_HTTPONLY = False'
+
+  - id: cra-ai-10-express-cookie-insecure
+    languages: [javascript, typescript]
+    severity: ERROR
+    message: Express cookie set with secure/httpOnly = false — session token exposed to interception / XSS theft.
+    metadata:
+      cwe: ["CWE-614: Sensitive Cookie in HTTPS Session Without 'Secure' Attribute"]
+      control: cra-ai-10
+    patterns:
+      - pattern-either:
+          - pattern: '$RES.cookie($NAME, $VAL, {..., secure: false, ...})'
+          - pattern: '$RES.cookie($NAME, $VAL, {..., httpOnly: false, ...})'
+
+  # --- cra-ai-14: Speicher-Schutz / Data at Rest (weak cipher) -----------------
+  - id: cra-ai-14-python-weak-cipher
+    languages: [python]
+    severity: ERROR
+    message: Data-at-rest encrypted with a broken cipher/mode (ECB, DES, 3DES) — provides no real confidentiality.
+    metadata:
+      cwe: ["CWE-327: Use of a Broken or Risky Cryptographic Algorithm"]
+      control: cra-ai-14
+    patterns:
+      - pattern-either:
+          - pattern: 'AES.new($K, AES.MODE_ECB, ...)'
+          - pattern: 'DES.new(...)'
+          - pattern: 'DES3.new(...)'
+
+  - id: cra-ai-14-node-weak-cipher
+    languages: [javascript, typescript]
+    severity: ERROR
+    message: Data-at-rest encrypted with a broken cipher (DES / deprecated createCipher) — provides no real confidentiality.
+    metadata:
+      cwe: ["CWE-327: Use of a Broken or Risky Cryptographic Algorithm"]
+      control: cra-ai-14
+    patterns:
+      - pattern-either:
+          - pattern: 'crypto.createCipheriv("des-ecb", ...)'
+          - pattern: 'crypto.createCipheriv("des", ...)'
+          - pattern: 'crypto.createCipher(...)'

compliance-agent/src/controls/triage.rs

@@ -44,10 +44,14 @@ impl<J: ControlJudge> ControlTriage<J> {
     /// 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);
+        // Match by CWE (off-the-shelf findings) and/or rule id (our custom
+        // detectors, which carry no LUT-bound CWE). A finding with neither is
+        // simply unmapped.
+        let mapped = self.map.controls_for_finding(
+            &finding.scanner,
+            finding.cwe.as_deref(),
+            finding.rule_id.as_deref(),
+        );
         if mapped.is_empty() {
             return TriageOutcome::Unmapped;
         }
@@ -162,6 +166,52 @@ mod tests {
         assert_eq!(out, TriageOutcome::FalsePositive);
     }
 
+    #[tokio::test]
+    async fn custom_rule_finding_without_cwe_is_confirmed() {
+        // A custom detector finding carries a rule id but no LUT-bound CWE; it must
+        // still map (by rule id) and confirm.
+        let mut specs = specs();
+        specs.insert(
+            "cra-ai-1".to_string(),
+            ControlCheckSpec {
+                control_id: "cra-ai-1".into(),
+                title: "Secure-by-Default".into(),
+                requirement: "Ship secure defaults".into(),
+                default_cwe: None,
+                severity: Severity::Medium,
+            },
+        );
+        let triage = ControlTriage::new(
+            StubJudge {
+                verdict: LlmVerdict {
+                    violates: true,
+                    snippet: "app.run(debug=True)".into(),
+                    cwe: None,
+                    confidence: 0.9,
+                },
+            },
+            ControlMap::cra().unwrap(),
+            specs,
+        );
+        let mut f = Finding::new(
+            "repo".into(),
+            "fp".into(),
+            "semgrep".into(),
+            ScanType::Sast,
+            "flask debug".into(),
+            "desc".into(),
+            Severity::Medium,
+        );
+        f.rule_id = Some("tmp.x.cra-ai-1-flask-debug-enabled".into()); // no cwe
+        let region = CandidateRegion {
+            file: "app.py".into(),
+            start_line: 1,
+            content: "app.run(debug=True)\n".into(),
+        };
+        let out = triage.triage(&f, &region).await;
+        assert_eq!(out, TriageOutcome::Confirmed(vec!["cra-ai-1".to_string()]));
+    }
+
     #[tokio::test]
     async fn unmapped_cwe_is_left_untagged() {
         let triage = ControlTriage::new(

compliance-agent/src/pipeline/semgrep.rs

@@ -1,4 +1,4 @@
-use std::path::Path;
+use std::path::{Path, PathBuf};
 
 use compliance_core::models::{Finding, ScanType, Severity};
 use compliance_core::traits::{ScanOutput, Scanner};
@@ -6,6 +6,30 @@ use compliance_core::CoreError;
 
 use crate::pipeline::dedup;
 
+/// Custom CRA-control detectors bundled into the binary and staged to a temp file
+/// at scan time so semgrep can `--config` them alongside the auto ruleset. These
+/// cover controls no off-the-shelf rule digs out (secure defaults, weak password
+/// hashing, insecure session cookies, weak data-at-rest ciphers); each rule id is
+/// keyed back to its control by the `control-map` LUT.
+const CRA_RULES: &str = include_str!("../../rules/cra_semgrep.yaml");
+
+/// Write the bundled CRA rules to a stable temp path (atomic: unique tmp +
+/// rename). Returns `None` on failure — the scan then runs with auto rules only.
+async fn stage_cra_rules() -> Option<PathBuf> {
+    let dir = std::env::temp_dir();
+    let path = dir.join("compliance-cra-semgrep.yaml");
+    let tmp = dir.join(format!("compliance-cra-semgrep.{}.tmp", std::process::id()));
+    if let Err(e) = tokio::fs::write(&tmp, CRA_RULES).await {
+        tracing::warn!(error = %e, "failed to stage custom CRA semgrep rules; using auto rules only");
+        return None;
+    }
+    if let Err(e) = tokio::fs::rename(&tmp, &path).await {
+        tracing::warn!(error = %e, "failed to stage custom CRA semgrep rules; using auto rules only");
+        return None;
+    }
+    Some(path)
+}
+
 pub struct SemgrepScanner;
 
 impl Scanner for SemgrepScanner {
@@ -19,30 +43,26 @@ impl Scanner for SemgrepScanner {
 
     #[tracing::instrument(skip_all)]
     async fn scan(&self, repo_path: &Path, repo_id: &str) -> Result<ScanOutput, CoreError> {
-        let output = tokio::time::timeout(
-            std::time::Duration::from_secs(600),
-            tokio::process::Command::new("semgrep")
-                .args([
-                    "--config=auto",
-                    "--json",
-                    "--quiet",
-                    "--max-memory",
-                    "500",
-                    "--jobs",
-                    "1",
-                ])
-                .arg(repo_path)
-                .output(),
-        )
-        .await
-        .map_err(|_| CoreError::Scanner {
-            scanner: "semgrep".to_string(),
-            source: "timed out after 10 minutes".into(),
-        })?
-        .map_err(|e| CoreError::Scanner {
-            scanner: "semgrep".to_string(),
-            source: Box::new(e),
-        })?;
+        let cra_rules = stage_cra_rules().await;
+        let mut command = tokio::process::Command::new("semgrep");
+        command.arg("--config=auto");
+        if let Some(path) = &cra_rules {
+            command.arg(format!("--config={}", path.display()));
+        }
+        command
+            .args(["--json", "--quiet", "--max-memory", "500", "--jobs", "1"])
+            .arg(repo_path);
+
+        let output = tokio::time::timeout(std::time::Duration::from_secs(600), command.output())
+            .await
+            .map_err(|_| CoreError::Scanner {
+                scanner: "semgrep".to_string(),
+                source: "timed out after 10 minutes".into(),
+            })?
+            .map_err(|e| CoreError::Scanner {
+                scanner: "semgrep".to_string(),
+                source: Box::new(e),
+            })?;
 
         if !output.status.success() && output.stdout.is_empty() {
             let stderr = String::from_utf8_lossy(&output.stderr);