Compare commits
1
Commits
| Author | SHA1 | Date | |
|---|---|---|---|
|
|
2d20ad7a6e |
@@ -109,8 +109,6 @@ jobs:
|
||||
run: cargo clippy -p compliance-mcp -- -D warnings
|
||||
- name: Clippy (werkbank-exec)
|
||||
run: cargo clippy -p werkbank-exec -- -D warnings
|
||||
- name: Clippy (control-map)
|
||||
run: cargo clippy -p control-map -- -D warnings
|
||||
|
||||
# Security audit
|
||||
- name: Security Audit
|
||||
@@ -119,8 +117,8 @@ jobs:
|
||||
RUSTC_WRAPPER: ""
|
||||
|
||||
# Tests (reuses compilation artifacts from clippy)
|
||||
- name: Tests (core + agent + werkbank-exec + control-map)
|
||||
run: cargo test -p compliance-core -p compliance-agent -p werkbank-exec -p control-map --lib
|
||||
- name: Tests (core + agent + werkbank-exec)
|
||||
run: cargo test -p compliance-core -p compliance-agent -p werkbank-exec --lib
|
||||
- name: Tests (dashboard server)
|
||||
run: cargo test -p compliance-dashboard --features server --no-default-features
|
||||
- name: Tests (dashboard web)
|
||||
|
||||
Generated
-10
@@ -666,7 +666,6 @@ dependencies = [
|
||||
"compliance-core",
|
||||
"compliance-dast",
|
||||
"compliance-graph",
|
||||
"control-map",
|
||||
"dashmap",
|
||||
"dotenvy",
|
||||
"futures-core",
|
||||
@@ -969,15 +968,6 @@ dependencies = [
|
||||
"charset",
|
||||
]
|
||||
|
||||
[[package]]
|
||||
name = "control-map"
|
||||
version = "0.1.0"
|
||||
dependencies = [
|
||||
"serde",
|
||||
"serde_json",
|
||||
"thiserror 2.0.18",
|
||||
]
|
||||
|
||||
[[package]]
|
||||
name = "convert_case"
|
||||
version = "0.8.0"
|
||||
|
||||
@@ -8,7 +8,6 @@ members = [
|
||||
"compliance-mcp",
|
||||
"compliance-smoke",
|
||||
"werkbank-exec",
|
||||
"control-map",
|
||||
]
|
||||
resolver = "2"
|
||||
|
||||
@@ -18,7 +17,6 @@ expect_used = "deny"
|
||||
|
||||
[workspace.dependencies]
|
||||
compliance-core = { path = "compliance-core", default-features = false }
|
||||
control-map = { path = "control-map" }
|
||||
serde = { version = "1", features = ["derive"] }
|
||||
serde_json = "1"
|
||||
tokio = { version = "1", features = ["full"] }
|
||||
|
||||
@@ -8,7 +8,6 @@ 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
|
||||
|
||||
@@ -1,117 +0,0 @@
|
||||
# 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(...)'
|
||||
@@ -1,9 +1,9 @@
|
||||
//! OSCAL assessment endpoint.
|
||||
//!
|
||||
//! Returns a standard OSCAL assessment-results document for a target's findings,
|
||||
//! driven by each finding's stamped `control_refs` (from the scan's control-triage
|
||||
//! stage): mapped findings target their controls, unmapped findings are reported
|
||||
//! as-is. See `compliance_core::models::oscal_assessment`.
|
||||
//! Assesses a target's findings against the breakpilot-compliance control
|
||||
//! catalog and returns a standard OSCAL assessment-results document. Ties
|
||||
//! together the ingest provider ([`OscalControlsProvider`]) and the assessment
|
||||
//! emitter (`compliance_core::models::oscal_assessment`).
|
||||
|
||||
use axum::extract::Extension;
|
||||
use axum::http::StatusCode;
|
||||
@@ -12,24 +12,45 @@ use axum::Json;
|
||||
use mongodb::bson::doc;
|
||||
use serde::Deserialize;
|
||||
|
||||
use compliance_core::models::oscal_assessment::assess;
|
||||
use compliance_core::models::onboarding::ComplianceFramework;
|
||||
use compliance_core::models::oscal_assessment::{assess, ControlLinker};
|
||||
use compliance_core::models::Finding;
|
||||
use compliance_core::tenant_ctx::TenantCtx;
|
||||
|
||||
use super::dto::{collect_cursor_async, tenant_db, AgentExt};
|
||||
use crate::controls::OscalControlsProvider;
|
||||
|
||||
#[derive(Debug, Deserialize)]
|
||||
pub struct AssessRequest {
|
||||
/// The target / repo id whose findings are assessed.
|
||||
pub target_id: String,
|
||||
/// Frameworks to assess against; defaults to `[Cra]` when empty.
|
||||
#[serde(default)]
|
||||
pub frameworks: Vec<ComplianceFramework>,
|
||||
}
|
||||
|
||||
/// `POST /api/v1/oscal/assess` — OSCAL assessment-results for a target's findings.
|
||||
/// `POST /api/v1/oscal/assess` — pull the catalog(s), load the target's findings,
|
||||
/// and emit an OSCAL assessment-results document linking findings to controls.
|
||||
pub async fn assess_target(
|
||||
Extension(agent): AgentExt,
|
||||
tenant: TenantCtx,
|
||||
Json(req): Json<AssessRequest>,
|
||||
) -> Response {
|
||||
let cfg = &agent.config.breakpilot;
|
||||
let Some(base_url) = cfg.base_url.clone() else {
|
||||
return (
|
||||
StatusCode::SERVICE_UNAVAILABLE,
|
||||
"breakpilot base URL not configured (set BREAKPILOT_BASE_URL)",
|
||||
)
|
||||
.into_response();
|
||||
};
|
||||
|
||||
let frameworks = if req.frameworks.is_empty() {
|
||||
vec![ComplianceFramework::Cra]
|
||||
} else {
|
||||
req.frameworks.clone()
|
||||
};
|
||||
|
||||
let db = match tenant_db(&agent, &tenant).await {
|
||||
Ok(db) => db,
|
||||
Err(code) => return code.into_response(),
|
||||
@@ -44,5 +65,25 @@ pub async fn assess_target(
|
||||
}
|
||||
};
|
||||
|
||||
Json(assess(&findings, chrono::Utc::now())).into_response()
|
||||
let provider = OscalControlsProvider::new(
|
||||
agent.http.clone(),
|
||||
base_url,
|
||||
cfg.token.clone(),
|
||||
&cfg.snapshot_dir,
|
||||
);
|
||||
let mut controls = Vec::new();
|
||||
for framework in &frameworks {
|
||||
match provider.load(*framework).await {
|
||||
Ok(document) => controls.extend(document.to_controls()),
|
||||
Err(e) => tracing::warn!(?framework, error = %e, "OSCAL catalog load failed"),
|
||||
}
|
||||
}
|
||||
|
||||
let assessment = assess(
|
||||
&controls,
|
||||
&findings,
|
||||
&ControlLinker::cra_seed(),
|
||||
chrono::Utc::now(),
|
||||
);
|
||||
Json(assessment).into_response()
|
||||
}
|
||||
|
||||
@@ -100,8 +100,5 @@ fn load_breakpilot_config() -> BreakpilotConfig {
|
||||
base_url: env_var_opt("BREAKPILOT_BASE_URL"),
|
||||
token: env_secret_opt("BREAKPILOT_TOKEN"),
|
||||
snapshot_dir: env_var_opt("BREAKPILOT_SNAPSHOT_DIR").unwrap_or(d.snapshot_dir),
|
||||
semantic_mapping: env_var_opt("BREAKPILOT_SEMANTIC_MAPPING")
|
||||
.map(|v| v == "1" || v.eq_ignore_ascii_case("true"))
|
||||
.unwrap_or(d.semantic_mapping),
|
||||
}
|
||||
}
|
||||
|
||||
@@ -1,114 +0,0 @@
|
||||
//! 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(), ®ions, "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());
|
||||
}
|
||||
}
|
||||
@@ -1,245 +0,0 @@
|
||||
//! In-memory embedding index over the control corpus, for region → control
|
||||
//! retrieval.
|
||||
//!
|
||||
//! At master-control scale (~13.6k) findings can't be mapped by CWE (the master
|
||||
//! controls carry none), so we map by *similarity*: embed each control's
|
||||
//! requirement text once, then for a code region pull the top-K nearest controls
|
||||
//! to hand to the grounded judge. This is the retrieval half of the semantic path.
|
||||
|
||||
use std::path::Path;
|
||||
|
||||
use serde::{Deserialize, Serialize};
|
||||
use sha2::{Digest, Sha256};
|
||||
|
||||
use compliance_core::control_check::ControlCheckSpec;
|
||||
use compliance_core::error::CoreError;
|
||||
|
||||
use crate::llm::LlmClient;
|
||||
|
||||
/// A control spec paired with its requirement-text embedding.
|
||||
pub struct ControlIndex {
|
||||
entries: Vec<(ControlCheckSpec, Vec<f64>)>,
|
||||
}
|
||||
|
||||
/// On-disk form of the index: the corpus identity hash plus every spec+embedding.
|
||||
/// The hash lets a later scan reuse the embeddings only if the corpus is unchanged.
|
||||
#[derive(Serialize, Deserialize)]
|
||||
struct PersistedIndex {
|
||||
corpus_hash: String,
|
||||
entries: Vec<PersistedEntry>,
|
||||
}
|
||||
|
||||
#[derive(Serialize, Deserialize)]
|
||||
struct PersistedEntry {
|
||||
spec: ControlCheckSpec,
|
||||
embedding: Vec<f64>,
|
||||
}
|
||||
|
||||
/// Stable hash of the corpus identity (each control's id + requirement text, in
|
||||
/// order). Same catalog → same hash → the cached embeddings are reused instead of
|
||||
/// re-embedding the whole corpus.
|
||||
fn corpus_hash(specs: &[ControlCheckSpec]) -> String {
|
||||
let mut hasher = Sha256::new();
|
||||
for s in specs {
|
||||
hasher.update(s.control_id.as_bytes());
|
||||
hasher.update([0u8]);
|
||||
hasher.update(s.requirement.as_bytes());
|
||||
hasher.update([0u8]);
|
||||
}
|
||||
format!("{:x}", hasher.finalize())
|
||||
}
|
||||
|
||||
impl ControlIndex {
|
||||
/// Build directly from precomputed embeddings (used by tests + callers that
|
||||
/// already embedded the corpus).
|
||||
pub fn from_embeddings(entries: Vec<(ControlCheckSpec, Vec<f64>)>) -> Self {
|
||||
Self { entries }
|
||||
}
|
||||
|
||||
/// Load the index from `cache_path` if it still matches the current corpus,
|
||||
/// otherwise embed the corpus and persist it there. This turns the per-scan
|
||||
/// re-embed of the whole (~13.6k) master-control corpus into a one-time cost
|
||||
/// that survives across scans; the cache self-invalidates when the catalog
|
||||
/// changes (its [`corpus_hash`] no longer matches).
|
||||
pub async fn load_or_build(
|
||||
llm: &LlmClient,
|
||||
specs: Vec<ControlCheckSpec>,
|
||||
cache_path: &Path,
|
||||
) -> Result<Self, CoreError> {
|
||||
let hash = corpus_hash(&specs);
|
||||
if let Some(index) = Self::load_cache(cache_path, &hash).await {
|
||||
tracing::debug!(
|
||||
controls = index.len(),
|
||||
"reusing cached control embedding index"
|
||||
);
|
||||
return Ok(index);
|
||||
}
|
||||
let index = Self::build(llm, specs).await?;
|
||||
if let Err(e) = index.write_cache(cache_path, &hash).await {
|
||||
tracing::warn!(error = %e, "failed to persist control embedding index");
|
||||
}
|
||||
Ok(index)
|
||||
}
|
||||
|
||||
/// Read a persisted index, returning it only if its corpus hash matches.
|
||||
async fn load_cache(path: &Path, hash: &str) -> Option<Self> {
|
||||
let raw = tokio::fs::read(path).await.ok()?;
|
||||
let persisted: PersistedIndex = serde_json::from_slice(&raw).ok()?;
|
||||
if persisted.corpus_hash != hash {
|
||||
return None;
|
||||
}
|
||||
Some(Self {
|
||||
entries: persisted
|
||||
.entries
|
||||
.into_iter()
|
||||
.map(|e| (e.spec, e.embedding))
|
||||
.collect(),
|
||||
})
|
||||
}
|
||||
|
||||
/// Persist the index atomically (temp file + rename) keyed by corpus hash.
|
||||
async fn write_cache(&self, path: &Path, hash: &str) -> Result<(), CoreError> {
|
||||
if let Some(parent) = path.parent() {
|
||||
tokio::fs::create_dir_all(parent).await?;
|
||||
}
|
||||
let persisted = PersistedIndex {
|
||||
corpus_hash: hash.to_string(),
|
||||
entries: self
|
||||
.entries
|
||||
.iter()
|
||||
.map(|(spec, emb)| PersistedEntry {
|
||||
spec: spec.clone(),
|
||||
embedding: emb.clone(),
|
||||
})
|
||||
.collect(),
|
||||
};
|
||||
let raw = serde_json::to_vec(&persisted)?;
|
||||
let tmp = path.with_extension("json.tmp");
|
||||
tokio::fs::write(&tmp, &raw).await?;
|
||||
tokio::fs::rename(&tmp, path).await?;
|
||||
Ok(())
|
||||
}
|
||||
|
||||
/// Build by embedding each control's requirement text.
|
||||
pub async fn build(llm: &LlmClient, specs: Vec<ControlCheckSpec>) -> Result<Self, CoreError> {
|
||||
if specs.is_empty() {
|
||||
return Ok(Self {
|
||||
entries: Vec::new(),
|
||||
});
|
||||
}
|
||||
let texts: Vec<String> = specs.iter().map(|s| s.requirement.clone()).collect();
|
||||
let embeddings = llm
|
||||
.embed(texts)
|
||||
.await
|
||||
.map_err(|e| CoreError::Llm(e.to_string()))?;
|
||||
Ok(Self {
|
||||
entries: specs.into_iter().zip(embeddings).collect(),
|
||||
})
|
||||
}
|
||||
|
||||
pub fn len(&self) -> usize {
|
||||
self.entries.len()
|
||||
}
|
||||
|
||||
pub fn is_empty(&self) -> bool {
|
||||
self.entries.is_empty()
|
||||
}
|
||||
|
||||
/// The top-`k` control specs whose embedding is nearest (cosine) to `query`.
|
||||
pub fn nearest(&self, query: &[f64], k: usize) -> Vec<ControlCheckSpec> {
|
||||
let mut scored: Vec<(f64, &ControlCheckSpec)> = self
|
||||
.entries
|
||||
.iter()
|
||||
.map(|(spec, emb)| (cosine(query, emb), spec))
|
||||
.collect();
|
||||
scored.sort_by(|a, b| b.0.total_cmp(&a.0));
|
||||
scored.into_iter().take(k).map(|(_, s)| s.clone()).collect()
|
||||
}
|
||||
}
|
||||
|
||||
/// Cosine similarity; 0.0 for length-mismatched, empty, or zero vectors.
|
||||
fn cosine(a: &[f64], b: &[f64]) -> f64 {
|
||||
if a.len() != b.len() || a.is_empty() {
|
||||
return 0.0;
|
||||
}
|
||||
let dot: f64 = a.iter().zip(b).map(|(x, y)| x * y).sum();
|
||||
let na: f64 = a.iter().map(|x| x * x).sum();
|
||||
let nb: f64 = b.iter().map(|x| x * x).sum();
|
||||
if na == 0.0 || nb == 0.0 {
|
||||
return 0.0;
|
||||
}
|
||||
dot / (na.sqrt() * nb.sqrt())
|
||||
}
|
||||
|
||||
#[cfg(test)]
|
||||
mod tests {
|
||||
use super::*;
|
||||
use compliance_core::models::finding::Severity;
|
||||
|
||||
fn spec(id: &str) -> ControlCheckSpec {
|
||||
ControlCheckSpec {
|
||||
control_id: id.into(),
|
||||
title: id.into(),
|
||||
requirement: id.into(),
|
||||
default_cwe: None,
|
||||
severity: Severity::Medium,
|
||||
}
|
||||
}
|
||||
|
||||
#[test]
|
||||
fn nearest_ranks_by_cosine() {
|
||||
let index = ControlIndex::from_embeddings(vec![
|
||||
(spec("a"), vec![1.0, 0.0]),
|
||||
(spec("b"), vec![0.0, 1.0]),
|
||||
(spec("c"), vec![0.7, 0.7]),
|
||||
]);
|
||||
let hits = index.nearest(&[0.9, 0.1], 2);
|
||||
assert_eq!(hits.len(), 2);
|
||||
assert_eq!(hits[0].control_id, "a"); // closest to [0.9,0.1]
|
||||
}
|
||||
|
||||
#[test]
|
||||
fn cosine_edges_are_zero() {
|
||||
assert_eq!(cosine(&[1.0], &[1.0, 2.0]), 0.0); // length mismatch
|
||||
assert_eq!(cosine(&[0.0, 0.0], &[1.0, 1.0]), 0.0); // zero vector
|
||||
assert!((cosine(&[1.0, 0.0], &[1.0, 0.0]) - 1.0).abs() < 1e-9); // identical
|
||||
}
|
||||
|
||||
#[test]
|
||||
fn corpus_hash_is_stable_and_identity_sensitive() {
|
||||
let a = corpus_hash(&[spec("x"), spec("y")]);
|
||||
assert_eq!(a, corpus_hash(&[spec("x"), spec("y")])); // same corpus → same hash
|
||||
assert_ne!(a, corpus_hash(&[spec("y"), spec("x")])); // reorder → different
|
||||
assert_ne!(a, corpus_hash(&[spec("x")])); // fewer controls → different
|
||||
}
|
||||
|
||||
#[tokio::test]
|
||||
#[allow(clippy::unwrap_used)]
|
||||
async fn cache_round_trips_and_misses_on_corpus_change() {
|
||||
let dir = std::env::temp_dir().join(format!("cidx-{}", uuid::Uuid::new_v4()));
|
||||
let path = dir.join("control-index.json");
|
||||
let specs = [spec("a"), spec("b")];
|
||||
let hash = corpus_hash(&specs);
|
||||
let index = ControlIndex::from_embeddings(vec![
|
||||
(spec("a"), vec![1.0, 0.0]),
|
||||
(spec("b"), vec![0.0, 1.0]),
|
||||
]);
|
||||
index.write_cache(&path, &hash).await.unwrap();
|
||||
|
||||
// matching corpus hash → hit
|
||||
let loaded = ControlIndex::load_cache(&path, &hash).await.unwrap();
|
||||
assert_eq!(loaded.len(), 2);
|
||||
assert_eq!(loaded.nearest(&[0.9, 0.1], 1)[0].control_id, "a");
|
||||
// corpus changed → miss (forces a rebuild)
|
||||
assert!(ControlIndex::load_cache(&path, "differenthash")
|
||||
.await
|
||||
.is_none());
|
||||
// absent file → miss, not an error
|
||||
assert!(
|
||||
ControlIndex::load_cache(dir.join("nope.json").as_path(), &hash)
|
||||
.await
|
||||
.is_none()
|
||||
);
|
||||
let _ = std::fs::remove_dir_all(&dir);
|
||||
}
|
||||
}
|
||||
@@ -1,167 +0,0 @@
|
||||
//! 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(), ®ion);
|
||||
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"));
|
||||
}
|
||||
}
|
||||
@@ -5,18 +5,6 @@
|
||||
//! [`OscalControlsProvider`], which pulls breakpilot-compliance's OSCAL catalog
|
||||
//! and snapshots it locally.
|
||||
|
||||
mod checker;
|
||||
mod index;
|
||||
mod judge;
|
||||
mod oscal_provider;
|
||||
mod scan_triage;
|
||||
mod semantic;
|
||||
mod triage;
|
||||
|
||||
pub use checker::GroundedControlChecker;
|
||||
pub use index::ControlIndex;
|
||||
pub use judge::{ControlJudge, LlmControlJudge, PROMPT_VERSION};
|
||||
pub use oscal_provider::OscalControlsProvider;
|
||||
pub use scan_triage::{semantic_stamp_findings, triage_repo_findings};
|
||||
pub use semantic::SemanticControlChecker;
|
||||
pub use triage::{ControlTriage, TriageOutcome};
|
||||
|
||||
@@ -43,20 +43,20 @@ impl OscalControlsProvider {
|
||||
}
|
||||
}
|
||||
|
||||
fn catalog_url(&self, framework: &str) -> String {
|
||||
fn catalog_url(&self, framework: ComplianceFramework) -> String {
|
||||
format!(
|
||||
"{}/api/compliance/v1/oscal/catalog?framework={framework}",
|
||||
self.base_url.trim_end_matches('/')
|
||||
)
|
||||
}
|
||||
|
||||
fn snapshot_path(&self, framework: &str) -> PathBuf {
|
||||
fn snapshot_path(&self, framework: ComplianceFramework) -> PathBuf {
|
||||
self.snapshot_dir
|
||||
.join(format!("oscal-catalog-{framework}.json"))
|
||||
}
|
||||
|
||||
/// Fetch the raw catalog bytes for a framework token over HTTP.
|
||||
async fn fetch_raw(&self, framework: &str) -> Result<Vec<u8>, CoreError> {
|
||||
/// Fetch the raw catalog bytes for a framework over HTTP.
|
||||
async fn fetch_raw(&self, framework: ComplianceFramework) -> Result<Vec<u8>, CoreError> {
|
||||
let mut req = self.http.get(self.catalog_url(framework));
|
||||
if let Some(token) = &self.token {
|
||||
req = req.bearer_auth(token.expose_secret());
|
||||
@@ -78,7 +78,11 @@ impl OscalControlsProvider {
|
||||
}
|
||||
|
||||
/// Write a catalog snapshot atomically (temp file + rename).
|
||||
async fn write_snapshot(&self, framework: &str, raw: &[u8]) -> Result<(), CoreError> {
|
||||
async fn write_snapshot(
|
||||
&self,
|
||||
framework: ComplianceFramework,
|
||||
raw: &[u8],
|
||||
) -> Result<(), CoreError> {
|
||||
tokio::fs::create_dir_all(&self.snapshot_dir).await?;
|
||||
let path = self.snapshot_path(framework);
|
||||
let tmp = path.with_extension("json.tmp");
|
||||
@@ -88,7 +92,10 @@ impl OscalControlsProvider {
|
||||
}
|
||||
|
||||
/// Read a previously written snapshot, if one exists.
|
||||
async fn read_snapshot(&self, framework: &str) -> Result<Option<OscalDocument>, CoreError> {
|
||||
async fn read_snapshot(
|
||||
&self,
|
||||
framework: ComplianceFramework,
|
||||
) -> Result<Option<OscalDocument>, CoreError> {
|
||||
match tokio::fs::read(self.snapshot_path(framework)).await {
|
||||
Ok(raw) => Ok(Some(serde_json::from_slice(&raw)?)),
|
||||
Err(e) if e.kind() == std::io::ErrorKind::NotFound => Ok(None),
|
||||
@@ -96,21 +103,21 @@ impl OscalControlsProvider {
|
||||
}
|
||||
}
|
||||
|
||||
/// Load the catalog for a framework token: fetch fresh + snapshot the exact
|
||||
/// bytes; on network failure, fall back to the last snapshot so scans run.
|
||||
async fn load_token(&self, framework: &str) -> Result<OscalDocument, CoreError> {
|
||||
/// Load the catalog for a framework: fetch fresh + snapshot the exact bytes;
|
||||
/// on network failure, fall back to the last snapshot so scans still run.
|
||||
pub async fn load(&self, framework: ComplianceFramework) -> Result<OscalDocument, CoreError> {
|
||||
match self.fetch_raw(framework).await {
|
||||
Ok(raw) => {
|
||||
let doc: OscalDocument = serde_json::from_slice(&raw)?;
|
||||
if let Err(e) = self.write_snapshot(framework, &raw).await {
|
||||
tracing::warn!(framework, error = %e, "failed to write OSCAL snapshot");
|
||||
tracing::warn!(%framework, error = %e, "failed to write OSCAL snapshot");
|
||||
}
|
||||
Ok(doc)
|
||||
}
|
||||
Err(fetch_err) => match self.read_snapshot(framework).await? {
|
||||
Some(doc) => {
|
||||
tracing::warn!(
|
||||
framework, error = %fetch_err,
|
||||
%framework, error = %fetch_err,
|
||||
"OSCAL catalog fetch failed; falling back to snapshot"
|
||||
);
|
||||
Ok(doc)
|
||||
@@ -119,17 +126,6 @@ impl OscalControlsProvider {
|
||||
},
|
||||
}
|
||||
}
|
||||
|
||||
/// Load the OSCAL catalog for a compliance framework.
|
||||
pub async fn load(&self, framework: ComplianceFramework) -> Result<OscalDocument, CoreError> {
|
||||
self.load_token(&framework.to_string()).await
|
||||
}
|
||||
|
||||
/// Load the code-checkable master-controls catalog
|
||||
/// (`?framework=master-controls`).
|
||||
pub async fn load_master_controls(&self) -> Result<OscalDocument, CoreError> {
|
||||
self.load_token("master-controls").await
|
||||
}
|
||||
}
|
||||
|
||||
/// Order controls whose title/text mention the query context first (stable), then
|
||||
@@ -185,11 +181,11 @@ mod tests {
|
||||
fn builds_catalog_url_and_snapshot_path() {
|
||||
let p = provider(std::path::Path::new("/snap"));
|
||||
assert_eq!(
|
||||
p.catalog_url("cra"),
|
||||
p.catalog_url(ComplianceFramework::Cra),
|
||||
"http://unused/api/compliance/v1/oscal/catalog?framework=cra"
|
||||
);
|
||||
assert_eq!(
|
||||
p.snapshot_path("cra"),
|
||||
p.snapshot_path(ComplianceFramework::Cra),
|
||||
std::path::Path::new("/snap/oscal-catalog-cra.json")
|
||||
);
|
||||
}
|
||||
@@ -217,11 +213,19 @@ mod tests {
|
||||
async fn snapshot_round_trip_and_offline_fallback() {
|
||||
let dir = std::env::temp_dir().join(format!("oscal-test-{}", uuid::Uuid::new_v4()));
|
||||
let p = provider(&dir);
|
||||
assert!(p.read_snapshot("cra").await.unwrap().is_none());
|
||||
p.write_snapshot("cra", MINI_CATALOG.as_bytes())
|
||||
assert!(p
|
||||
.read_snapshot(ComplianceFramework::Cra)
|
||||
.await
|
||||
.unwrap()
|
||||
.is_none());
|
||||
p.write_snapshot(ComplianceFramework::Cra, MINI_CATALOG.as_bytes())
|
||||
.await
|
||||
.unwrap();
|
||||
let doc = p.read_snapshot("cra").await.unwrap().unwrap();
|
||||
let doc = p
|
||||
.read_snapshot(ComplianceFramework::Cra)
|
||||
.await
|
||||
.unwrap()
|
||||
.unwrap();
|
||||
assert_eq!(doc.to_controls().len(), 1);
|
||||
assert_eq!(doc.framework(), Some(ComplianceFramework::Cra));
|
||||
let _ = std::fs::remove_dir_all(&dir);
|
||||
|
||||
@@ -1,246 +0,0 @@
|
||||
//! 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::{
|
||||
ControlIndex, ControlTriage, LlmControlJudge, OscalControlsProvider, SemanticControlChecker,
|
||||
TriageOutcome,
|
||||
};
|
||||
use crate::llm::LlmClient;
|
||||
|
||||
/// Nearest master controls judged per code region in the semantic pass.
|
||||
const SEMANTIC_TOP_K: usize = 5;
|
||||
|
||||
/// Lines of context to read on each side of a finding's line.
|
||||
const REGION_WINDOW: usize = 6;
|
||||
|
||||
/// Triage every finding in `findings` against the CRA control map: stamp
|
||||
/// `control_refs` on confirmed findings and flag control false positives. Returns
|
||||
/// the number of findings tagged with at least one control.
|
||||
pub async fn triage_repo_findings(
|
||||
config: &AgentConfig,
|
||||
llm: Arc<LlmClient>,
|
||||
repo_path: &Path,
|
||||
findings: &mut [Finding],
|
||||
) -> usize {
|
||||
let Some(base_url) = config.breakpilot.base_url.clone() else {
|
||||
return 0; // control triage is opt-in via BREAKPILOT_BASE_URL
|
||||
};
|
||||
let provider = OscalControlsProvider::new(
|
||||
reqwest::Client::new(),
|
||||
base_url,
|
||||
config.breakpilot.token.clone(),
|
||||
&config.breakpilot.snapshot_dir,
|
||||
);
|
||||
let specs = build_specs(&provider).await;
|
||||
if specs.is_empty() {
|
||||
return 0;
|
||||
}
|
||||
let map = match ControlMap::cra() {
|
||||
Ok(m) => m,
|
||||
Err(e) => {
|
||||
tracing::warn!(error = %e, "control map failed to load; skipping control triage");
|
||||
return 0;
|
||||
}
|
||||
};
|
||||
let triage = ControlTriage::new(LlmControlJudge::new(llm), map, specs);
|
||||
|
||||
let mut tagged = 0;
|
||||
for finding in findings.iter_mut() {
|
||||
let (Some(file), Some(line)) = (finding.file_path.clone(), finding.line_number) else {
|
||||
continue;
|
||||
};
|
||||
let Some(region) = fetch_region(repo_path, &file, line) else {
|
||||
continue;
|
||||
};
|
||||
match triage.triage(finding, ®ion).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"),
|
||||
})
|
||||
}
|
||||
|
||||
/// Master-controls **semantic** pass: for each finding's code region, retrieve the
|
||||
/// top-K nearest master controls by embedding, have the grounded judge confirm,
|
||||
/// and stamp the confirmed control ids onto the finding — the scale path for the
|
||||
/// ~13.6k master-control corpus (which has no CWE to LUT on). Returns the number
|
||||
/// of findings that gained a master-control ref.
|
||||
///
|
||||
/// Gated: the orchestrator runs this only when `breakpilot.semantic_mapping` is
|
||||
/// set (default off, flipped on once the master-controls catalog is live). The
|
||||
/// control embedding index is built once and cached to `snapshot_dir` keyed by
|
||||
/// corpus hash ([`ControlIndex::load_or_build`]), so only the first scan after a
|
||||
/// catalog change pays the embedding cost.
|
||||
pub async fn semantic_stamp_findings(
|
||||
config: &AgentConfig,
|
||||
llm: Arc<LlmClient>,
|
||||
repo_path: &Path,
|
||||
findings: &mut [Finding],
|
||||
) -> usize {
|
||||
let Some(base_url) = config.breakpilot.base_url.clone() else {
|
||||
return 0;
|
||||
};
|
||||
let provider = OscalControlsProvider::new(
|
||||
reqwest::Client::new(),
|
||||
base_url,
|
||||
config.breakpilot.token.clone(),
|
||||
&config.breakpilot.snapshot_dir,
|
||||
);
|
||||
let doc = match provider.load_master_controls().await {
|
||||
Ok(d) => d,
|
||||
Err(e) => {
|
||||
tracing::warn!(error = %e, "master-controls catalog unavailable; skipping semantic pass");
|
||||
return 0;
|
||||
}
|
||||
};
|
||||
let specs: Vec<ControlCheckSpec> = doc
|
||||
.to_controls()
|
||||
.into_iter()
|
||||
.map(|c| ControlCheckSpec {
|
||||
control_id: c.id,
|
||||
title: c.title,
|
||||
requirement: c.text,
|
||||
default_cwe: None,
|
||||
severity: Severity::Medium,
|
||||
})
|
||||
.collect();
|
||||
let cache_path =
|
||||
Path::new(&config.breakpilot.snapshot_dir).join("control-index-master-controls.json");
|
||||
let index = match ControlIndex::load_or_build(&llm, specs, &cache_path).await {
|
||||
Ok(i) if !i.is_empty() => i,
|
||||
Ok(_) => return 0,
|
||||
Err(e) => {
|
||||
tracing::warn!(error = %e, "failed to embed master-controls corpus");
|
||||
return 0;
|
||||
}
|
||||
};
|
||||
let checker = SemanticControlChecker::new(LlmControlJudge::new(llm.clone()));
|
||||
|
||||
let mut tagged = 0;
|
||||
for finding in findings.iter_mut() {
|
||||
if finding.status == FindingStatus::FalsePositive {
|
||||
continue;
|
||||
}
|
||||
let (Some(file), Some(line)) = (finding.file_path.clone(), finding.line_number) else {
|
||||
continue;
|
||||
};
|
||||
let Some(region) = fetch_region(repo_path, &file, line) else {
|
||||
continue;
|
||||
};
|
||||
let region_emb = match llm.embed(vec![region.content.clone()]).await {
|
||||
Ok(mut embs) => match embs.pop() {
|
||||
Some(v) => v,
|
||||
None => continue,
|
||||
},
|
||||
Err(e) => {
|
||||
tracing::warn!(error = %e, "region embed failed; skipping finding");
|
||||
continue;
|
||||
}
|
||||
};
|
||||
let confirmed = checker
|
||||
.check(
|
||||
&index,
|
||||
®ion,
|
||||
®ion_emb,
|
||||
SEMANTIC_TOP_K,
|
||||
&finding.repo_id,
|
||||
)
|
||||
.await;
|
||||
let before = finding.control_refs.len();
|
||||
for f in confirmed {
|
||||
for cref in f.control_refs {
|
||||
if !finding.control_refs.contains(&cref) {
|
||||
finding.control_refs.push(cref);
|
||||
}
|
||||
}
|
||||
}
|
||||
if finding.control_refs.len() > before {
|
||||
tagged += 1;
|
||||
}
|
||||
}
|
||||
tagged
|
||||
}
|
||||
|
||||
#[cfg(test)]
|
||||
mod tests {
|
||||
use super::*;
|
||||
|
||||
#[test]
|
||||
fn fetch_region_windows_around_the_line() {
|
||||
let dir = std::env::temp_dir().join(format!("triage-region-{}", uuid::Uuid::new_v4()));
|
||||
std::fs::create_dir_all(&dir).unwrap();
|
||||
let file = "a.py";
|
||||
std::fs::write(dir.join(file), "l1\nl2\nl3\nSECRET=1\nl5\nl6\n").unwrap();
|
||||
let r = fetch_region(&dir, file, 4).unwrap();
|
||||
assert!(r.content.contains("SECRET=1"));
|
||||
assert_eq!(r.start_line, 1); // window clamps to file start
|
||||
let _ = std::fs::remove_dir_all(&dir);
|
||||
}
|
||||
|
||||
#[test]
|
||||
fn fetch_region_missing_file_is_none() {
|
||||
assert!(fetch_region(Path::new("/nonexistent"), "nope.py", 1).is_none());
|
||||
}
|
||||
}
|
||||
@@ -1,119 +0,0 @@
|
||||
//! Semantic control mapping: retrieve the top-K controls nearest a code region,
|
||||
//! then confirm each with the grounded judge.
|
||||
//!
|
||||
//! The `region → controls` direction (vs. the CWE-LUT's `finding → control`) is
|
||||
//! what scales to the full master-control corpus: the LLM only ever judges a
|
||||
//! handful of retrieved candidates, and every surviving verdict is still anchored
|
||||
//! to real code by the grounding gate.
|
||||
|
||||
use compliance_core::control_check::{ground, CandidateRegion};
|
||||
use compliance_core::models::Finding;
|
||||
|
||||
use super::index::ControlIndex;
|
||||
use super::judge::ControlJudge;
|
||||
|
||||
/// Retrieve → judge → ground, generic over the judge so tests use a stub.
|
||||
pub struct SemanticControlChecker<J> {
|
||||
judge: J,
|
||||
}
|
||||
|
||||
impl<J: ControlJudge> SemanticControlChecker<J> {
|
||||
pub fn new(judge: J) -> Self {
|
||||
Self { judge }
|
||||
}
|
||||
|
||||
/// Map a code region to the controls it violates. `region_embedding` is the
|
||||
/// region's embedding (the caller computes it via the LLM); the top-`k`
|
||||
/// nearest controls in `index` are judged and grounded.
|
||||
pub async fn check(
|
||||
&self,
|
||||
index: &ControlIndex,
|
||||
region: &CandidateRegion,
|
||||
region_embedding: &[f64],
|
||||
k: usize,
|
||||
repo_id: &str,
|
||||
) -> Vec<Finding> {
|
||||
let candidates = index.nearest(region_embedding, k);
|
||||
let mut findings = Vec::new();
|
||||
for spec in &candidates {
|
||||
let verdict = self.judge.judge(spec, region).await;
|
||||
if let Some(finding) = ground(spec, region, &verdict, repo_id) {
|
||||
findings.push(finding);
|
||||
}
|
||||
}
|
||||
findings
|
||||
}
|
||||
}
|
||||
|
||||
#[cfg(test)]
|
||||
mod tests {
|
||||
use super::*;
|
||||
use compliance_core::control_check::{ControlCheckSpec, LlmVerdict};
|
||||
use compliance_core::models::finding::Severity;
|
||||
|
||||
struct StubJudge {
|
||||
verdict: LlmVerdict,
|
||||
}
|
||||
impl ControlJudge for StubJudge {
|
||||
async fn judge(&self, _s: &ControlCheckSpec, _r: &CandidateRegion) -> LlmVerdict {
|
||||
self.verdict.clone()
|
||||
}
|
||||
}
|
||||
|
||||
fn spec(id: &str) -> ControlCheckSpec {
|
||||
ControlCheckSpec {
|
||||
control_id: id.into(),
|
||||
title: id.into(),
|
||||
requirement: id.into(),
|
||||
default_cwe: None,
|
||||
severity: Severity::Medium,
|
||||
}
|
||||
}
|
||||
|
||||
#[tokio::test]
|
||||
async fn retrieves_then_grounds_the_nearest_control() {
|
||||
let index = ControlIndex::from_embeddings(vec![
|
||||
(spec("mc-near"), vec![1.0, 0.0]),
|
||||
(spec("mc-far"), vec![0.0, 1.0]),
|
||||
]);
|
||||
let checker = SemanticControlChecker::new(StubJudge {
|
||||
verdict: LlmVerdict {
|
||||
violates: true,
|
||||
snippet: "PASSWORD = \"admin\"".into(),
|
||||
cwe: None,
|
||||
confidence: 0.9,
|
||||
},
|
||||
});
|
||||
let region = CandidateRegion {
|
||||
file: "src/auth.py".into(),
|
||||
start_line: 1,
|
||||
content: "PASSWORD = \"admin\"\n".into(),
|
||||
};
|
||||
// Query embedding nearest to mc-near; k=1 → only mc-near is judged.
|
||||
let findings = checker
|
||||
.check(&index, ®ion, &[0.95, 0.05], 1, "repo")
|
||||
.await;
|
||||
assert_eq!(findings.len(), 1);
|
||||
assert_eq!(findings[0].control_refs, vec!["mc-near".to_string()]);
|
||||
}
|
||||
|
||||
#[tokio::test]
|
||||
async fn ungrounded_verdict_is_dropped() {
|
||||
let index = ControlIndex::from_embeddings(vec![(spec("mc-near"), vec![1.0, 0.0])]);
|
||||
let checker = SemanticControlChecker::new(StubJudge {
|
||||
verdict: LlmVerdict {
|
||||
violates: true,
|
||||
snippet: "not in the region".into(),
|
||||
cwe: None,
|
||||
confidence: 0.9,
|
||||
},
|
||||
});
|
||||
let region = CandidateRegion {
|
||||
file: "f".into(),
|
||||
start_line: 1,
|
||||
content: "real code\n".into(),
|
||||
};
|
||||
let findings = checker.check(&index, ®ion, &[1.0, 0.0], 1, "repo").await;
|
||||
assert!(findings.is_empty());
|
||||
}
|
||||
}
|
||||
@@ -1,234 +0,0 @@
|
||||
//! Triage step: confirm/refute a deterministic tool finding against the controls
|
||||
//! it maps to (via the `control-map` LUT), grounding the judgment.
|
||||
//!
|
||||
//! This is where the LLM finally enters — as a **false-positive filter over tool
|
||||
//! output**, never as the detector (the ZeroFalse / IRIS pattern). A tool
|
||||
//! (semgrep, gitleaks, syft/osv) detects deterministically; `controls_for(tool,
|
||||
//! cwe)` attaches the finding to the control(s) it's evidence for; the grounded
|
||||
//! judge then confirms or refutes each, and only judgments anchored to real code
|
||||
//! survive.
|
||||
|
||||
use std::collections::HashMap;
|
||||
|
||||
use compliance_core::control_check::{ground, CandidateRegion, ControlCheckSpec};
|
||||
use compliance_core::models::Finding;
|
||||
use control_map::ControlMap;
|
||||
|
||||
use super::judge::ControlJudge;
|
||||
|
||||
/// What triage decided for one tool finding.
|
||||
#[derive(Debug, Clone, PartialEq, Eq)]
|
||||
pub enum TriageOutcome {
|
||||
/// The finding maps to no control in the LUT — keep it, untagged.
|
||||
Unmapped,
|
||||
/// Maps to controls and the grounded judge confirmed at least one — keep the
|
||||
/// finding and tag it with these control ids.
|
||||
Confirmed(Vec<String>),
|
||||
/// Maps to controls but the judge grounded none — treat as a false positive.
|
||||
FalsePositive,
|
||||
}
|
||||
|
||||
/// Triages tool findings against the control map, confirming with a grounded judge.
|
||||
pub struct ControlTriage<J> {
|
||||
judge: J,
|
||||
map: ControlMap,
|
||||
/// Control requirement specs (by control id), built from the ingested catalog.
|
||||
specs: HashMap<String, ControlCheckSpec>,
|
||||
}
|
||||
|
||||
impl<J: ControlJudge> ControlTriage<J> {
|
||||
pub fn new(judge: J, map: ControlMap, specs: HashMap<String, ControlCheckSpec>) -> Self {
|
||||
Self { judge, map, specs }
|
||||
}
|
||||
|
||||
/// Triage one tool finding. `region` is the code around the finding, used as
|
||||
/// the grounding evidence for the judge.
|
||||
pub async fn triage(&self, finding: &Finding, region: &CandidateRegion) -> TriageOutcome {
|
||||
// Match by CWE (off-the-shelf findings) and/or rule id (our custom
|
||||
// detectors, which carry no LUT-bound CWE). A finding with neither is
|
||||
// simply unmapped.
|
||||
let mapped = self.map.controls_for_finding(
|
||||
&finding.scanner,
|
||||
finding.cwe.as_deref(),
|
||||
finding.rule_id.as_deref(),
|
||||
);
|
||||
if mapped.is_empty() {
|
||||
return TriageOutcome::Unmapped;
|
||||
}
|
||||
|
||||
let mut confirmed = Vec::new();
|
||||
for entry in mapped {
|
||||
let Some(spec) = self.specs.get(&entry.control) else {
|
||||
continue;
|
||||
};
|
||||
let verdict = self.judge.judge(spec, region).await;
|
||||
// The verdict only counts if it grounds to real code in the region.
|
||||
if ground(spec, region, &verdict, &finding.repo_id).is_some() {
|
||||
confirmed.push(entry.control.clone());
|
||||
}
|
||||
}
|
||||
|
||||
if confirmed.is_empty() {
|
||||
TriageOutcome::FalsePositive
|
||||
} else {
|
||||
TriageOutcome::Confirmed(confirmed)
|
||||
}
|
||||
}
|
||||
}
|
||||
|
||||
#[cfg(test)]
|
||||
mod tests {
|
||||
use super::*;
|
||||
use compliance_core::control_check::LlmVerdict;
|
||||
use compliance_core::models::finding::Severity;
|
||||
use compliance_core::models::scan::ScanType;
|
||||
|
||||
struct StubJudge {
|
||||
verdict: LlmVerdict,
|
||||
}
|
||||
impl ControlJudge for StubJudge {
|
||||
async fn judge(&self, _s: &ControlCheckSpec, _r: &CandidateRegion) -> LlmVerdict {
|
||||
self.verdict.clone()
|
||||
}
|
||||
}
|
||||
|
||||
fn specs() -> HashMap<String, ControlCheckSpec> {
|
||||
let mut m = HashMap::new();
|
||||
m.insert(
|
||||
"cra-ai-8".to_string(),
|
||||
ControlCheckSpec {
|
||||
control_id: "cra-ai-8".into(),
|
||||
title: "No default passwords".into(),
|
||||
requirement: "No default credentials".into(),
|
||||
default_cwe: Some("CWE-798".into()),
|
||||
severity: Severity::High,
|
||||
},
|
||||
);
|
||||
m
|
||||
}
|
||||
|
||||
fn semgrep_finding(cwe: &str) -> Finding {
|
||||
let mut f = Finding::new(
|
||||
"repo".into(),
|
||||
"fp1".into(),
|
||||
"semgrep".into(),
|
||||
ScanType::Sast,
|
||||
"hardcoded credential".into(),
|
||||
"desc".into(),
|
||||
Severity::High,
|
||||
);
|
||||
f.cwe = Some(cwe.into());
|
||||
f
|
||||
}
|
||||
|
||||
fn region() -> CandidateRegion {
|
||||
CandidateRegion {
|
||||
file: "src/auth.py".into(),
|
||||
start_line: 1,
|
||||
content: "PASSWORD = \"admin123\"\n".into(),
|
||||
}
|
||||
}
|
||||
|
||||
#[tokio::test]
|
||||
async fn confirmed_finding_is_tagged_with_control() {
|
||||
let triage = ControlTriage::new(
|
||||
StubJudge {
|
||||
verdict: LlmVerdict {
|
||||
violates: true,
|
||||
snippet: "PASSWORD = \"admin123\"".into(),
|
||||
cwe: None,
|
||||
confidence: 0.9,
|
||||
},
|
||||
},
|
||||
ControlMap::cra().unwrap(),
|
||||
specs(),
|
||||
);
|
||||
let out = triage.triage(&semgrep_finding("CWE-798"), ®ion()).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"), ®ion()).await;
|
||||
assert_eq!(out, TriageOutcome::FalsePositive);
|
||||
}
|
||||
|
||||
#[tokio::test]
|
||||
async fn custom_rule_finding_without_cwe_is_confirmed() {
|
||||
// A custom detector finding carries a rule id but no LUT-bound CWE; it must
|
||||
// still map (by rule id) and confirm.
|
||||
let mut specs = specs();
|
||||
specs.insert(
|
||||
"cra-ai-1".to_string(),
|
||||
ControlCheckSpec {
|
||||
control_id: "cra-ai-1".into(),
|
||||
title: "Secure-by-Default".into(),
|
||||
requirement: "Ship secure defaults".into(),
|
||||
default_cwe: None,
|
||||
severity: Severity::Medium,
|
||||
},
|
||||
);
|
||||
let triage = ControlTriage::new(
|
||||
StubJudge {
|
||||
verdict: LlmVerdict {
|
||||
violates: true,
|
||||
snippet: "app.run(debug=True)".into(),
|
||||
cwe: None,
|
||||
confidence: 0.9,
|
||||
},
|
||||
},
|
||||
ControlMap::cra().unwrap(),
|
||||
specs,
|
||||
);
|
||||
let mut f = Finding::new(
|
||||
"repo".into(),
|
||||
"fp".into(),
|
||||
"semgrep".into(),
|
||||
ScanType::Sast,
|
||||
"flask debug".into(),
|
||||
"desc".into(),
|
||||
Severity::Medium,
|
||||
);
|
||||
f.rule_id = Some("tmp.x.cra-ai-1-flask-debug-enabled".into()); // no cwe
|
||||
let region = CandidateRegion {
|
||||
file: "app.py".into(),
|
||||
start_line: 1,
|
||||
content: "app.run(debug=True)\n".into(),
|
||||
};
|
||||
let out = triage.triage(&f, ®ion).await;
|
||||
assert_eq!(out, TriageOutcome::Confirmed(vec!["cra-ai-1".to_string()]));
|
||||
}
|
||||
|
||||
#[tokio::test]
|
||||
async fn unmapped_cwe_is_left_untagged() {
|
||||
let triage = ControlTriage::new(
|
||||
StubJudge {
|
||||
verdict: LlmVerdict {
|
||||
violates: true,
|
||||
snippet: "PASSWORD = \"admin123\"".into(),
|
||||
cwe: None,
|
||||
confidence: 0.9,
|
||||
},
|
||||
},
|
||||
ControlMap::cra().unwrap(),
|
||||
specs(),
|
||||
);
|
||||
let out = triage
|
||||
.triage(&semgrep_finding("CWE-99999"), ®ion())
|
||||
.await;
|
||||
assert_eq!(out, TriageOutcome::Unmapped);
|
||||
}
|
||||
}
|
||||
@@ -215,43 +215,6 @@ impl PipelineOrchestrator {
|
||||
.await;
|
||||
tracing::info!("[{repo_id}] Triaged: {triaged} findings passed confidence threshold");
|
||||
|
||||
// Stage 5b: control triage — stamp findings with the compliance control(s)
|
||||
// they're evidence for and flag control false positives (grounded LLM over
|
||||
// deterministic tool output). No-op unless breakpilot is configured.
|
||||
self.update_phase(scan_run_id, "control_triage").await;
|
||||
let tagged = crate::controls::triage_repo_findings(
|
||||
&self.config,
|
||||
self.llm.clone(),
|
||||
&repo_path,
|
||||
&mut all_findings,
|
||||
)
|
||||
.await;
|
||||
if tagged > 0 {
|
||||
tracing::info!("[{repo_id}] Control triage tagged {tagged} findings with control refs");
|
||||
}
|
||||
|
||||
// Stage 5c: semantic control mapping — scale path for the master-controls
|
||||
// corpus (no CWE to LUT on): embed each finding's region, retrieve the
|
||||
// nearest master controls, grounded-judge, and stamp confirmed refs. Gated
|
||||
// (default off) as the corpus embedding + per-finding judging is the heavy
|
||||
// path; enabled once verified live against a deployed master-controls catalog.
|
||||
if self.config.breakpilot.semantic_mapping {
|
||||
self.update_phase(scan_run_id, "semantic_control_mapping")
|
||||
.await;
|
||||
let sem = crate::controls::semantic_stamp_findings(
|
||||
&self.config,
|
||||
self.llm.clone(),
|
||||
&repo_path,
|
||||
&mut all_findings,
|
||||
)
|
||||
.await;
|
||||
if sem > 0 {
|
||||
tracing::info!(
|
||||
"[{repo_id}] Semantic mapping tagged {sem} findings with master-control refs"
|
||||
);
|
||||
}
|
||||
}
|
||||
|
||||
// Dedup against existing findings and insert new ones
|
||||
let mut new_count = 0u32;
|
||||
let mut new_findings: Vec<Finding> = Vec::new();
|
||||
|
||||
@@ -1,4 +1,4 @@
|
||||
use std::path::{Path, PathBuf};
|
||||
use std::path::Path;
|
||||
|
||||
use compliance_core::models::{Finding, ScanType, Severity};
|
||||
use compliance_core::traits::{ScanOutput, Scanner};
|
||||
@@ -6,30 +6,6 @@ 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 {
|
||||
@@ -43,26 +19,30 @@ impl Scanner for SemgrepScanner {
|
||||
|
||||
#[tracing::instrument(skip_all)]
|
||||
async fn scan(&self, repo_path: &Path, repo_id: &str) -> Result<ScanOutput, CoreError> {
|
||||
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),
|
||||
})?;
|
||||
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),
|
||||
})?;
|
||||
|
||||
if !output.status.success() && output.stdout.is_empty() {
|
||||
let stderr = String::from_utf8_lossy(&output.stderr);
|
||||
@@ -102,7 +82,10 @@ 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.as_ref().and_then(extract_cwe);
|
||||
finding.cwe = r
|
||||
.extra
|
||||
.metadata
|
||||
.and_then(|m| m.get("cwe").and_then(|v| v.as_str()).map(|s| s.to_string()));
|
||||
finding
|
||||
})
|
||||
.collect();
|
||||
@@ -141,34 +124,10 @@ 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#"{
|
||||
|
||||
@@ -75,11 +75,6 @@ pub struct BreakpilotConfig {
|
||||
pub token: Option<SecretString>,
|
||||
/// Directory for catalog snapshots.
|
||||
pub snapshot_dir: String,
|
||||
/// Enable the master-controls **semantic** mapping pass (embed regions,
|
||||
/// retrieve nearest controls, grounded-judge). Off by default: it is the
|
||||
/// scale path and stays gated until verified live against a deployed
|
||||
/// master-controls catalog.
|
||||
pub semantic_mapping: bool,
|
||||
}
|
||||
|
||||
impl Default for BreakpilotConfig {
|
||||
@@ -88,7 +83,6 @@ impl Default for BreakpilotConfig {
|
||||
base_url: None,
|
||||
token: None,
|
||||
snapshot_dir: "/data/compliance-scanner/oscal".to_string(),
|
||||
semantic_mapping: false,
|
||||
}
|
||||
}
|
||||
}
|
||||
|
||||
@@ -1,205 +0,0 @@
|
||||
//! Grounded control-driven checking.
|
||||
//!
|
||||
//! Turns a *text* control into findings via an LLM used as a **pattern-recognizer**
|
||||
//! whose output is grounded to real code — so a hallucinated finding cannot
|
||||
//! survive. Determinism is structural, not a prompt plea:
|
||||
//!
|
||||
//! 1. the LLM only ever judges *retrieved* regions — it can't invent findings in
|
||||
//! code it never saw;
|
||||
//! 2. a verdict becomes a finding only if its quoted snippet appears **verbatim**
|
||||
//! in the region, and the line is recomputed from that match — the model's own
|
||||
//! line number is never trusted ([`ground`]);
|
||||
//! 3. verdicts are cached by content hash ([`cache_key`]) so re-scans reproduce.
|
||||
//!
|
||||
//! The LLM supplies cross-language / cross-stack pattern recognition; this module
|
||||
//! supplies the determinism.
|
||||
|
||||
use serde::{Deserialize, Serialize};
|
||||
use sha2::{Digest, Sha256};
|
||||
|
||||
use crate::models::finding::{Finding, Severity};
|
||||
use crate::models::scan::ScanType;
|
||||
|
||||
/// A control rendered as a check the LLM judges code against.
|
||||
#[derive(Debug, Clone, Serialize, Deserialize)]
|
||||
pub struct ControlCheckSpec {
|
||||
/// Stable control id, e.g. `"cra-ai-8"`.
|
||||
pub control_id: String,
|
||||
/// Short control title (used in the finding title).
|
||||
pub title: String,
|
||||
/// The requirement text the LLM judges against (control objective/statement).
|
||||
pub requirement: String,
|
||||
/// CWE to fall back to when the model doesn't supply one.
|
||||
pub default_cwe: Option<String>,
|
||||
/// Severity for findings raised from this control.
|
||||
pub severity: Severity,
|
||||
}
|
||||
|
||||
/// A retrieved code region the LLM judges — never the whole repo.
|
||||
#[derive(Debug, Clone)]
|
||||
pub struct CandidateRegion {
|
||||
/// Repo-relative path.
|
||||
pub file: String,
|
||||
/// 1-based line number of the region's first line in `file`.
|
||||
pub start_line: u32,
|
||||
/// The region's source text.
|
||||
pub content: String,
|
||||
}
|
||||
|
||||
/// The LLM's structured verdict for one (control, region). `snippet` is the
|
||||
/// verbatim code the model claims proves the violation — it is the anchor the
|
||||
/// grounding gate checks.
|
||||
#[derive(Debug, Clone)]
|
||||
pub struct LlmVerdict {
|
||||
pub violates: bool,
|
||||
pub snippet: String,
|
||||
pub cwe: Option<String>,
|
||||
pub confidence: f64,
|
||||
}
|
||||
|
||||
/// The grounding gate. A verdict becomes a [`Finding`] only if it claims a
|
||||
/// violation AND its quoted `snippet` appears verbatim in `region.content`; the
|
||||
/// finding's line is computed from the match, so a fabricated or mis-located
|
||||
/// snippet is dropped. Pure — no LLM, no I/O.
|
||||
pub fn ground(
|
||||
spec: &ControlCheckSpec,
|
||||
region: &CandidateRegion,
|
||||
verdict: &LlmVerdict,
|
||||
repo_id: &str,
|
||||
) -> Option<Finding> {
|
||||
if !verdict.violates {
|
||||
return None;
|
||||
}
|
||||
let snippet = verdict.snippet.trim();
|
||||
if snippet.is_empty() {
|
||||
return None;
|
||||
}
|
||||
// Grounding: the quoted snippet must literally exist in the retrieved region.
|
||||
let pos = region.content.find(snippet)?;
|
||||
// Recompute the real line from the match — never trust the model's number.
|
||||
let newlines_before = region.content[..pos].matches('\n').count();
|
||||
let line = region.start_line + newlines_before as u32;
|
||||
|
||||
let mut finding = Finding::new(
|
||||
repo_id.to_string(),
|
||||
control_finding_fingerprint(&spec.control_id, ®ion.file, snippet),
|
||||
"control-check".to_string(),
|
||||
ScanType::CodeReview,
|
||||
format!("{}: {}", spec.control_id, spec.title),
|
||||
format!(
|
||||
"Control {} appears violated ({}) at {}:{line}",
|
||||
spec.control_id, spec.requirement, region.file
|
||||
),
|
||||
spec.severity.clone(),
|
||||
);
|
||||
finding.cwe = verdict.cwe.clone().or_else(|| spec.default_cwe.clone());
|
||||
finding.file_path = Some(region.file.clone());
|
||||
finding.line_number = Some(line);
|
||||
finding.code_snippet = Some(snippet.to_string());
|
||||
finding.confidence = Some(verdict.confidence);
|
||||
// Carry the control reference on the finding.
|
||||
finding.control_refs = vec![spec.control_id.clone()];
|
||||
Some(finding)
|
||||
}
|
||||
|
||||
/// Deterministic cache key for a (control, region, model, prompt-version) verdict
|
||||
/// so identical inputs reproduce the same verdict without another LLM call.
|
||||
pub fn cache_key(
|
||||
control_id: &str,
|
||||
region_content: &str,
|
||||
model: &str,
|
||||
prompt_version: &str,
|
||||
) -> String {
|
||||
hash_parts(&[control_id, region_content, model, prompt_version])
|
||||
}
|
||||
|
||||
fn control_finding_fingerprint(control_id: &str, file: &str, snippet: &str) -> String {
|
||||
hash_parts(&[control_id, file, snippet])
|
||||
}
|
||||
|
||||
fn hash_parts(parts: &[&str]) -> String {
|
||||
let mut hasher = Sha256::new();
|
||||
for part in parts {
|
||||
hasher.update(part.as_bytes());
|
||||
hasher.update([0u8]); // domain separator between parts
|
||||
}
|
||||
hex::encode(hasher.finalize())
|
||||
}
|
||||
|
||||
#[cfg(test)]
|
||||
mod tests {
|
||||
use super::*;
|
||||
|
||||
fn spec() -> ControlCheckSpec {
|
||||
ControlCheckSpec {
|
||||
control_id: "cra-ai-8".into(),
|
||||
title: "No default passwords".into(),
|
||||
requirement: "Products must not ship default credentials".into(),
|
||||
default_cwe: Some("CWE-798".into()),
|
||||
severity: Severity::High,
|
||||
}
|
||||
}
|
||||
|
||||
fn region() -> CandidateRegion {
|
||||
CandidateRegion {
|
||||
file: "src/auth.py".into(),
|
||||
start_line: 10,
|
||||
content: "def login():\n PASSWORD = \"admin123\"\n return PASSWORD\n".into(),
|
||||
}
|
||||
}
|
||||
|
||||
#[test]
|
||||
fn grounds_real_snippet_with_recomputed_line() {
|
||||
let v = LlmVerdict {
|
||||
violates: true,
|
||||
snippet: "PASSWORD = \"admin123\"".into(),
|
||||
cwe: None,
|
||||
confidence: 0.9,
|
||||
};
|
||||
let f = ground(&spec(), ®ion(), &v, "repo").expect("should ground");
|
||||
assert_eq!(f.line_number, Some(11)); // 2nd line of a region starting at 10
|
||||
assert_eq!(f.cwe.as_deref(), Some("CWE-798")); // fell back to the spec default
|
||||
assert_eq!(f.control_refs, vec!["cra-ai-8".to_string()]); // control ref carried
|
||||
assert_eq!(f.file_path.as_deref(), Some("src/auth.py"));
|
||||
assert_eq!(f.code_snippet.as_deref(), Some("PASSWORD = \"admin123\""));
|
||||
}
|
||||
|
||||
#[test]
|
||||
fn drops_fabricated_snippet_not_in_region() {
|
||||
let v = LlmVerdict {
|
||||
violates: true,
|
||||
snippet: "SECRET = \"totally-made-up\"".into(),
|
||||
cwe: None,
|
||||
confidence: 0.99,
|
||||
};
|
||||
assert!(ground(&spec(), ®ion(), &v, "repo").is_none());
|
||||
}
|
||||
|
||||
#[test]
|
||||
fn drops_non_violation_and_empty_snippet() {
|
||||
let no = LlmVerdict {
|
||||
violates: false,
|
||||
snippet: "PASSWORD = \"admin123\"".into(),
|
||||
cwe: None,
|
||||
confidence: 0.9,
|
||||
};
|
||||
assert!(ground(&spec(), ®ion(), &no, "repo").is_none());
|
||||
let empty = LlmVerdict {
|
||||
violates: true,
|
||||
snippet: " ".into(),
|
||||
cwe: None,
|
||||
confidence: 0.9,
|
||||
};
|
||||
assert!(ground(&spec(), ®ion(), &empty, "repo").is_none());
|
||||
}
|
||||
|
||||
#[test]
|
||||
fn cache_key_and_fingerprint_are_deterministic() {
|
||||
assert_eq!(cache_key("c", "x", "m", "v"), cache_key("c", "x", "m", "v"));
|
||||
assert_ne!(cache_key("c", "x", "m", "v"), cache_key("c", "y", "m", "v"));
|
||||
assert_eq!(
|
||||
control_finding_fingerprint("c", "f", "s"),
|
||||
control_finding_fingerprint("c", "f", "s")
|
||||
);
|
||||
}
|
||||
}
|
||||
@@ -1,5 +1,4 @@
|
||||
pub mod config;
|
||||
pub mod control_check;
|
||||
pub mod db;
|
||||
pub mod error;
|
||||
pub mod models;
|
||||
|
||||
@@ -76,10 +76,6 @@ pub struct Finding {
|
||||
pub triage_rationale: Option<String>,
|
||||
/// Developer feedback on finding quality
|
||||
pub developer_feedback: Option<String>,
|
||||
/// Compliance control ids this finding is evidence for (stamped by control
|
||||
/// triage against the `control-map` LUT). Empty when unmapped.
|
||||
#[serde(default)]
|
||||
pub control_refs: Vec<String>,
|
||||
#[serde(with = "super::serde_helpers::bson_datetime")]
|
||||
pub created_at: DateTime<Utc>,
|
||||
#[serde(with = "super::serde_helpers::bson_datetime")]
|
||||
@@ -122,7 +118,6 @@ impl Finding {
|
||||
triage_action: None,
|
||||
triage_rationale: None,
|
||||
developer_feedback: None,
|
||||
control_refs: Vec::new(),
|
||||
created_at: now,
|
||||
updated_at: now,
|
||||
}
|
||||
|
||||
@@ -15,7 +15,8 @@ use chrono::{DateTime, Utc};
|
||||
use serde::Serialize;
|
||||
use uuid::Uuid;
|
||||
|
||||
use crate::models::finding::{Finding, FindingStatus};
|
||||
use crate::models::finding::Finding;
|
||||
use crate::traits::Control;
|
||||
|
||||
const OSCAL_VERSION: &str = "1.1.2";
|
||||
/// Same namespace as the catalog exporter, so ids are stable and correlatable.
|
||||
@@ -82,23 +83,22 @@ impl ControlLinker {
|
||||
}
|
||||
}
|
||||
|
||||
/// Build a standard OSCAL assessment-results document from `findings`, using each
|
||||
/// finding's stamped `control_refs` for control linkage. EVERY non-false-positive
|
||||
/// finding is emitted as an observation — mapped findings additionally produce a
|
||||
/// per-control `not-satisfied` finding; **unmapped findings are reported as-is**
|
||||
/// (an observation carrying their CWE/tool/severity, with no control target) so
|
||||
/// nothing is lost. `at` is the assessment timestamp.
|
||||
pub fn assess(findings: &[Finding], at: DateTime<Utc>) -> AssessmentResultsDoc {
|
||||
/// Assess `findings` against `controls`: link findings to control-ids and build a
|
||||
/// standard OSCAL assessment-results document. `at` is the assessment timestamp.
|
||||
pub fn assess(
|
||||
controls: &[Control],
|
||||
findings: &[Finding],
|
||||
linker: &ControlLinker,
|
||||
at: DateTime<Utc>,
|
||||
) -> AssessmentResultsDoc {
|
||||
let ts = at.to_rfc3339();
|
||||
|
||||
let mut observations = Vec::new();
|
||||
let mut obs_by_control: HashMap<String, Vec<String>> = HashMap::new();
|
||||
let mut mapped = 0usize;
|
||||
let mut unmapped = 0usize;
|
||||
|
||||
for finding in findings {
|
||||
if finding.status == FindingStatus::FalsePositive {
|
||||
continue; // flagged tool false positive — excluded from the report
|
||||
let targets = linker.controls_for(finding);
|
||||
if targets.is_empty() {
|
||||
continue;
|
||||
}
|
||||
let obs_uuid = det_uuid(&format!("obs:{}", finding.fingerprint));
|
||||
let location = match (&finding.file_path, finding.line_number) {
|
||||
@@ -106,67 +106,58 @@ pub fn assess(findings: &[Finding], at: DateTime<Utc>) -> AssessmentResultsDoc {
|
||||
(Some(f), None) => Some(f.clone()),
|
||||
_ => None,
|
||||
};
|
||||
let is_mapped = !finding.control_refs.is_empty();
|
||||
if is_mapped {
|
||||
mapped += 1;
|
||||
} else {
|
||||
unmapped += 1;
|
||||
}
|
||||
let mut props = vec![
|
||||
ObsProp::new("tool", &finding.scanner),
|
||||
ObsProp::new("severity", &finding.severity.to_string()),
|
||||
ObsProp::new("mapping", if is_mapped { "mapped" } else { "unmapped" }),
|
||||
];
|
||||
if let Some(cwe) = &finding.cwe {
|
||||
props.push(ObsProp::new("cwe", cwe));
|
||||
}
|
||||
observations.push(Observation {
|
||||
uuid: obs_uuid.clone(),
|
||||
title: finding.title.clone(),
|
||||
description: finding.description.clone(),
|
||||
description: finding.title.clone(),
|
||||
methods: vec!["TEST".to_string()],
|
||||
collected: ts.clone(),
|
||||
props,
|
||||
relevant_evidence: vec![RelevantEvidence {
|
||||
href: location.map(|l| format!("file://{l}")),
|
||||
description: format!("[{}] {}", finding.scanner, finding.title),
|
||||
}],
|
||||
});
|
||||
for control_id in &finding.control_refs {
|
||||
for control_id in targets {
|
||||
obs_by_control
|
||||
.entry(control_id.clone())
|
||||
.entry(control_id)
|
||||
.or_default()
|
||||
.push(obs_uuid.clone());
|
||||
}
|
||||
}
|
||||
|
||||
let titles: HashMap<&str, &str> = controls
|
||||
.iter()
|
||||
.map(|c| (c.id.as_str(), c.title.as_str()))
|
||||
.collect();
|
||||
let mut hit_controls: Vec<&String> = obs_by_control.keys().collect();
|
||||
hit_controls.sort();
|
||||
let ar_findings: Vec<ArFinding> = hit_controls
|
||||
.iter()
|
||||
.map(|control_id| ArFinding {
|
||||
uuid: det_uuid(&format!("finding:{control_id}")),
|
||||
title: format!("Findings affect {control_id}"),
|
||||
target: FindingTarget {
|
||||
target_type: "statement-id".to_string(),
|
||||
target_id: format!("{control_id}_smt"),
|
||||
status: TargetStatus {
|
||||
state: "not-satisfied".to_string(),
|
||||
.into_iter()
|
||||
.map(|control_id| {
|
||||
let title = titles.get(control_id.as_str()).copied().unwrap_or("");
|
||||
ArFinding {
|
||||
uuid: det_uuid(&format!("finding:{control_id}")),
|
||||
title: format!("Findings affect {control_id}: {title}"),
|
||||
target: FindingTarget {
|
||||
target_type: "statement-id".to_string(),
|
||||
target_id: format!("{control_id}_smt"),
|
||||
status: TargetStatus {
|
||||
state: "not-satisfied".to_string(),
|
||||
},
|
||||
},
|
||||
},
|
||||
related_observations: obs_by_control[*control_id]
|
||||
.iter()
|
||||
.map(|u| RelatedObservation {
|
||||
observation_uuid: u.clone(),
|
||||
})
|
||||
.collect(),
|
||||
related_observations: obs_by_control[control_id]
|
||||
.iter()
|
||||
.map(|u| RelatedObservation {
|
||||
observation_uuid: u.clone(),
|
||||
})
|
||||
.collect(),
|
||||
}
|
||||
})
|
||||
.collect();
|
||||
|
||||
let include_controls: Vec<SelectControlById> = hit_controls
|
||||
let include_controls = controls
|
||||
.iter()
|
||||
.map(|c| SelectControlById {
|
||||
control_id: (*c).clone(),
|
||||
control_id: c.id.clone(),
|
||||
})
|
||||
.collect();
|
||||
|
||||
@@ -174,9 +165,9 @@ pub fn assess(findings: &[Finding], at: DateTime<Utc>) -> AssessmentResultsDoc {
|
||||
uuid: det_uuid("result:cra"),
|
||||
title: "Automated code-compliance assessment".to_string(),
|
||||
description: format!(
|
||||
"{} observation(s): {mapped} control-linked, {unmapped} unmapped (as-is); {} control(s) affected",
|
||||
"{} finding-linked observation(s) across {} reviewed control(s)",
|
||||
observations.len(),
|
||||
include_controls.len()
|
||||
controls.len()
|
||||
),
|
||||
start: ts.clone(),
|
||||
reviewed_controls: ReviewedControls {
|
||||
@@ -271,33 +262,13 @@ pub struct SelectControlById {
|
||||
#[derive(Debug, Clone, Serialize)]
|
||||
pub struct Observation {
|
||||
pub uuid: String,
|
||||
pub title: String,
|
||||
pub description: String,
|
||||
pub methods: Vec<String>,
|
||||
pub collected: String,
|
||||
#[serde(skip_serializing_if = "Vec::is_empty")]
|
||||
pub props: Vec<ObsProp>,
|
||||
#[serde(rename = "relevant-evidence", skip_serializing_if = "Vec::is_empty")]
|
||||
pub relevant_evidence: Vec<RelevantEvidence>,
|
||||
}
|
||||
|
||||
/// A name/value observation property (cwe, tool, severity, mapping status). Lets an
|
||||
/// unmapped finding be reported fully as-is.
|
||||
#[derive(Debug, Clone, Serialize)]
|
||||
pub struct ObsProp {
|
||||
pub name: String,
|
||||
pub value: String,
|
||||
}
|
||||
|
||||
impl ObsProp {
|
||||
fn new(name: &str, value: &str) -> Self {
|
||||
Self {
|
||||
name: name.to_string(),
|
||||
value: value.to_string(),
|
||||
}
|
||||
}
|
||||
}
|
||||
|
||||
#[derive(Debug, Clone, Serialize)]
|
||||
pub struct RelevantEvidence {
|
||||
#[serde(skip_serializing_if = "Option::is_none")]
|
||||
@@ -339,9 +310,20 @@ pub struct RelatedObservation {
|
||||
mod tests {
|
||||
use super::*;
|
||||
use crate::models::finding::Severity;
|
||||
use crate::models::onboarding::ComplianceFramework;
|
||||
use crate::models::scan::ScanType;
|
||||
|
||||
fn finding(fp: &str, cwe: Option<&str>, refs: &[&str]) -> Finding {
|
||||
fn control(id: &str, title: &str) -> Control {
|
||||
Control {
|
||||
id: id.into(),
|
||||
framework: ComplianceFramework::Cra,
|
||||
title: title.into(),
|
||||
text: String::new(),
|
||||
source: None,
|
||||
}
|
||||
}
|
||||
|
||||
fn finding(fp: &str, cwe: Option<&str>) -> Finding {
|
||||
let mut f = Finding::new(
|
||||
"repo".into(),
|
||||
fp.into(),
|
||||
@@ -354,7 +336,6 @@ mod tests {
|
||||
f.cwe = cwe.map(Into::into);
|
||||
f.file_path = Some("src/auth.rs".into());
|
||||
f.line_number = Some(42);
|
||||
f.control_refs = refs.iter().map(|s| s.to_string()).collect();
|
||||
f
|
||||
}
|
||||
|
||||
@@ -365,60 +346,57 @@ mod tests {
|
||||
}
|
||||
|
||||
#[test]
|
||||
fn mapped_finding_becomes_control_finding() {
|
||||
let doc = assess(&[finding("f1", Some("CWE-798"), &["cra-ai-8"])], at());
|
||||
fn links_cwe_finding_to_control_not_satisfied() {
|
||||
let controls = vec![
|
||||
control("cra-ai-8", "No default passwords"),
|
||||
control("cra-ai-13", "Crypto"),
|
||||
];
|
||||
let findings = vec![finding("f1", Some("CWE-798"))];
|
||||
let doc = assess(&controls, &findings, &ControlLinker::cra_seed(), at());
|
||||
let r = &doc.assessment_results.results[0];
|
||||
assert_eq!(r.observations.len(), 1);
|
||||
assert_eq!(r.findings.len(), 1);
|
||||
assert_eq!(r.findings[0].target.target_id, "cra-ai-8_smt");
|
||||
assert_eq!(r.findings[0].target.status.state, "not-satisfied");
|
||||
assert_eq!(r.findings[0].related_observations.len(), 1);
|
||||
assert_eq!(
|
||||
r.reviewed_controls.control_selections[0]
|
||||
.include_controls
|
||||
.len(),
|
||||
1
|
||||
2
|
||||
);
|
||||
}
|
||||
|
||||
#[test]
|
||||
fn unmapped_finding_is_reported_as_is() {
|
||||
let doc = assess(&[finding("f1", Some("CWE-319"), &[])], at());
|
||||
fn unlinked_finding_yields_no_control_finding() {
|
||||
let controls = vec![control("cra-ai-8", "x")];
|
||||
let findings = vec![finding("f1", Some("CWE-99999"))];
|
||||
let doc = assess(&controls, &findings, &ControlLinker::cra_seed(), at());
|
||||
let r = &doc.assessment_results.results[0];
|
||||
assert_eq!(r.observations.len(), 1); // still emitted...
|
||||
assert!(r.findings.is_empty()); // ...but no control finding
|
||||
assert!(r.reviewed_controls.control_selections[0]
|
||||
.include_controls
|
||||
.is_empty());
|
||||
let props: Vec<(&str, &str)> = r.observations[0]
|
||||
.props
|
||||
.iter()
|
||||
.map(|p| (p.name.as_str(), p.value.as_str()))
|
||||
.collect();
|
||||
assert!(props.contains(&("mapping", "unmapped")));
|
||||
assert!(props.contains(&("cwe", "CWE-319")));
|
||||
assert!(r.observations.is_empty());
|
||||
assert!(r.findings.is_empty());
|
||||
}
|
||||
|
||||
#[test]
|
||||
fn false_positive_is_excluded() {
|
||||
let mut f = finding("f1", Some("CWE-798"), &["cra-ai-8"]);
|
||||
f.status = FindingStatus::FalsePositive;
|
||||
let doc = assess(&[f], at());
|
||||
assert!(doc.assessment_results.results[0].observations.is_empty());
|
||||
}
|
||||
|
||||
#[test]
|
||||
fn deterministic_and_valid_oscal() {
|
||||
let mk = || {
|
||||
vec![
|
||||
finding("f1", Some("CWE-798"), &["cra-ai-8"]),
|
||||
finding("f2", Some("CWE-319"), &[]),
|
||||
]
|
||||
};
|
||||
let a = serde_json::to_string(&assess(&mk(), at())).unwrap();
|
||||
let b = serde_json::to_string(&assess(&mk(), at())).unwrap();
|
||||
fn output_is_deterministic_and_valid_oscal() {
|
||||
let controls = vec![control("cra-ai-8", "x")];
|
||||
let findings = vec![finding("f1", Some("798"))];
|
||||
let a = serde_json::to_string(&assess(
|
||||
&controls,
|
||||
&findings,
|
||||
&ControlLinker::cra_seed(),
|
||||
at(),
|
||||
))
|
||||
.unwrap();
|
||||
let b = serde_json::to_string(&assess(
|
||||
&controls,
|
||||
&findings,
|
||||
&ControlLinker::cra_seed(),
|
||||
at(),
|
||||
))
|
||||
.unwrap();
|
||||
assert_eq!(a, b);
|
||||
assert!(a.contains("\"oscal-version\":\"1.1.2\""));
|
||||
assert!(a.contains("\"not-satisfied\""));
|
||||
assert!(a.contains("\"mapping\""));
|
||||
}
|
||||
}
|
||||
|
||||
@@ -4,7 +4,7 @@ use rmcp::{
|
||||
|
||||
use crate::auth::current_tenant_id;
|
||||
use crate::database::{Database, DatabasePool};
|
||||
use crate::tools::{dast, findings, oscal, pentest, sbom};
|
||||
use crate::tools::{dast, findings, pentest, sbom};
|
||||
|
||||
pub struct ComplianceMcpServer {
|
||||
pool: DatabasePool,
|
||||
@@ -68,17 +68,6 @@ impl ComplianceMcpServer {
|
||||
findings::findings_summary(&db, params).await
|
||||
}
|
||||
|
||||
#[tool(
|
||||
description = "Emit an OSCAL 1.1 assessment-results document for a repo's findings (mapped findings target their compliance controls; unmapped findings are reported as-is)"
|
||||
)]
|
||||
async fn oscal_assessment(
|
||||
&self,
|
||||
Parameters(params): Parameters<oscal::OscalAssessmentParams>,
|
||||
) -> Result<CallToolResult, rmcp::ErrorData> {
|
||||
let db = self.tenant_db()?;
|
||||
oscal::oscal_assessment(&db, params).await
|
||||
}
|
||||
|
||||
// ── SBOM ──────────────────────────────────────────────
|
||||
|
||||
#[tool(
|
||||
|
||||
@@ -1,5 +1,4 @@
|
||||
pub mod dast;
|
||||
pub mod findings;
|
||||
pub mod oscal;
|
||||
pub mod pentest;
|
||||
pub mod sbom;
|
||||
|
||||
@@ -1,51 +0,0 @@
|
||||
//! OSCAL assessment MCP tool.
|
||||
//!
|
||||
//! Emits a standard OSCAL assessment-results document for a repo's findings —
|
||||
//! what breakpilot's scanner MCP client pulls. Mapped findings target their
|
||||
//! compliance controls (via the stamped `control_refs`); unmapped findings are
|
||||
//! reported as-is, so nothing is lost.
|
||||
|
||||
use mongodb::bson::doc;
|
||||
use rmcp::{model::*, ErrorData as McpError};
|
||||
use schemars::JsonSchema;
|
||||
use serde::Deserialize;
|
||||
|
||||
use compliance_core::models::oscal_assessment::assess;
|
||||
use compliance_core::models::Finding;
|
||||
|
||||
use crate::database::Database;
|
||||
|
||||
#[derive(Debug, Deserialize, JsonSchema)]
|
||||
pub struct OscalAssessmentParams {
|
||||
/// Repository / target id to assess.
|
||||
pub repo_id: String,
|
||||
}
|
||||
|
||||
pub async fn oscal_assessment(
|
||||
db: &Database,
|
||||
params: OscalAssessmentParams,
|
||||
) -> Result<CallToolResult, McpError> {
|
||||
let mut cursor = db
|
||||
.findings()
|
||||
.find(doc! { "repo_id": ¶ms.repo_id })
|
||||
.await
|
||||
.map_err(|e| McpError::internal_error(format!("DB error: {e}"), None))?;
|
||||
|
||||
let mut findings: Vec<Finding> = Vec::new();
|
||||
while cursor
|
||||
.advance()
|
||||
.await
|
||||
.map_err(|e| McpError::internal_error(format!("cursor error: {e}"), None))?
|
||||
{
|
||||
findings.push(
|
||||
cursor
|
||||
.deserialize_current()
|
||||
.map_err(|e| McpError::internal_error(format!("deserialize error: {e}"), None))?,
|
||||
);
|
||||
}
|
||||
|
||||
let document = assess(&findings, chrono::Utc::now());
|
||||
let json = serde_json::to_string_pretty(&document)
|
||||
.map_err(|e| McpError::internal_error(format!("json error: {e}"), None))?;
|
||||
Ok(CallToolResult::success(vec![Content::text(json)]))
|
||||
}
|
||||
@@ -1,12 +0,0 @@
|
||||
[package]
|
||||
name = "control-map"
|
||||
version = "0.1.0"
|
||||
edition = "2021"
|
||||
|
||||
[lints]
|
||||
workspace = true
|
||||
|
||||
[dependencies]
|
||||
serde = { workspace = true }
|
||||
serde_json = { workspace = true }
|
||||
thiserror = { workspace = true }
|
||||
@@ -1,440 +0,0 @@
|
||||
{
|
||||
"version": "1.0",
|
||||
"framework": "cra",
|
||||
"controls": [
|
||||
{
|
||||
"control": "cra-ai-1",
|
||||
"title": "Secure-by-Default-Konfiguration",
|
||||
"scans": [
|
||||
{
|
||||
"tool": "semgrep",
|
||||
"scan_type": "sast",
|
||||
"cwe": [],
|
||||
"rules": [
|
||||
"cra-ai-1-flask-debug-enabled",
|
||||
"cra-ai-1-django-debug-true",
|
||||
"cra-ai-1-tls-verify-disabled",
|
||||
"cra-ai-1-cors-wildcard"
|
||||
]
|
||||
}
|
||||
],
|
||||
"note": null,
|
||||
"status": "covered"
|
||||
},
|
||||
{
|
||||
"control": "cra-ai-2",
|
||||
"title": "Minimale Angriffsflaeche",
|
||||
"scans": [],
|
||||
"note": "code-checkable but no off-the-shelf tool digs it out — author a detector (custom semgrep rule / check)",
|
||||
"status": "needs_tooling"
|
||||
},
|
||||
{
|
||||
"control": "cra-ai-3",
|
||||
"title": "Sichere Systemarchitektur",
|
||||
"scans": [],
|
||||
"note": "code-checkable but no off-the-shelf tool digs it out — author a detector (custom semgrep rule / check)",
|
||||
"status": "needs_tooling"
|
||||
},
|
||||
{
|
||||
"control": "cra-ai-4",
|
||||
"title": "Least-Privilege-Prinzip",
|
||||
"scans": [],
|
||||
"note": "code-checkable but no off-the-shelf tool digs it out — author a detector (custom semgrep rule / check)",
|
||||
"status": "needs_tooling"
|
||||
},
|
||||
{
|
||||
"control": "cra-ai-5",
|
||||
"title": "Manipulationsschutz",
|
||||
"scans": [],
|
||||
"note": "code-checkable but no off-the-shelf tool digs it out — author a detector (custom semgrep rule / check)",
|
||||
"status": "needs_tooling"
|
||||
},
|
||||
{
|
||||
"control": "cra-ai-6",
|
||||
"title": "Integritaetspruefung",
|
||||
"scans": [],
|
||||
"note": "code-checkable but no off-the-shelf tool digs it out — author a detector (custom semgrep rule / check)",
|
||||
"status": "needs_tooling"
|
||||
},
|
||||
{
|
||||
"control": "cra-ai-7",
|
||||
"title": "Starke Authentifizierung",
|
||||
"scans": [
|
||||
{
|
||||
"tool": "semgrep",
|
||||
"scan_type": "sast",
|
||||
"cwe": [],
|
||||
"rules": [
|
||||
"cra-ai-7-weak-password-hash"
|
||||
]
|
||||
}
|
||||
],
|
||||
"note": null,
|
||||
"status": "covered"
|
||||
},
|
||||
{
|
||||
"control": "cra-ai-8",
|
||||
"title": "Keine Default-Passwoerter",
|
||||
"scans": [
|
||||
{
|
||||
"tool": "gitleaks",
|
||||
"scan_type": "secret_detection",
|
||||
"cwe": [],
|
||||
"rules": []
|
||||
},
|
||||
{
|
||||
"tool": "semgrep",
|
||||
"scan_type": "sast",
|
||||
"cwe": [
|
||||
"CWE-798",
|
||||
"CWE-259"
|
||||
],
|
||||
"rules": []
|
||||
}
|
||||
],
|
||||
"note": null,
|
||||
"status": "covered"
|
||||
},
|
||||
{
|
||||
"control": "cra-ai-9",
|
||||
"title": "Sicheres Credential-Management",
|
||||
"scans": [
|
||||
{
|
||||
"tool": "gitleaks",
|
||||
"scan_type": "secret_detection",
|
||||
"cwe": [],
|
||||
"rules": []
|
||||
},
|
||||
{
|
||||
"tool": "semgrep",
|
||||
"scan_type": "sast",
|
||||
"cwe": [
|
||||
"CWE-798",
|
||||
"CWE-522"
|
||||
],
|
||||
"rules": []
|
||||
}
|
||||
],
|
||||
"note": null,
|
||||
"status": "covered"
|
||||
},
|
||||
{
|
||||
"control": "cra-ai-10",
|
||||
"title": "Sitzungsmanagement",
|
||||
"scans": [
|
||||
{
|
||||
"tool": "semgrep",
|
||||
"scan_type": "sast",
|
||||
"cwe": [],
|
||||
"rules": [
|
||||
"cra-ai-10-session-cookie-insecure",
|
||||
"cra-ai-10-express-cookie-insecure"
|
||||
]
|
||||
}
|
||||
],
|
||||
"note": null,
|
||||
"status": "covered"
|
||||
},
|
||||
{
|
||||
"control": "cra-ai-11",
|
||||
"title": "Brute-Force-Schutz",
|
||||
"scans": [],
|
||||
"note": "code-checkable but no off-the-shelf tool digs it out — author a detector (custom semgrep rule / check)",
|
||||
"status": "needs_tooling"
|
||||
},
|
||||
{
|
||||
"control": "cra-ai-12",
|
||||
"title": "Rollenbasierte Autorisierung",
|
||||
"scans": [],
|
||||
"note": "code-checkable but no off-the-shelf tool digs it out — author a detector (custom semgrep rule / check)",
|
||||
"status": "needs_tooling"
|
||||
},
|
||||
{
|
||||
"control": "cra-ai-13",
|
||||
"title": "Verschluesselung sensibler Daten",
|
||||
"scans": [
|
||||
{
|
||||
"tool": "semgrep",
|
||||
"scan_type": "sast",
|
||||
"cwe": [
|
||||
"CWE-327",
|
||||
"CWE-326"
|
||||
],
|
||||
"rules": []
|
||||
}
|
||||
],
|
||||
"note": null,
|
||||
"status": "covered"
|
||||
},
|
||||
{
|
||||
"control": "cra-ai-14",
|
||||
"title": "Speicher-Schutz (Data at Rest)",
|
||||
"scans": [
|
||||
{
|
||||
"tool": "semgrep",
|
||||
"scan_type": "sast",
|
||||
"cwe": [],
|
||||
"rules": [
|
||||
"cra-ai-14-python-weak-cipher",
|
||||
"cra-ai-14-node-weak-cipher"
|
||||
]
|
||||
}
|
||||
],
|
||||
"note": null,
|
||||
"status": "covered"
|
||||
},
|
||||
{
|
||||
"control": "cra-ai-15",
|
||||
"title": "Transport-Schutz (Data in Transit)",
|
||||
"scans": [
|
||||
{
|
||||
"tool": "semgrep",
|
||||
"scan_type": "sast",
|
||||
"cwe": [
|
||||
"CWE-319",
|
||||
"CWE-311"
|
||||
],
|
||||
"rules": []
|
||||
}
|
||||
],
|
||||
"note": null,
|
||||
"status": "covered"
|
||||
},
|
||||
{
|
||||
"control": "cra-ai-16",
|
||||
"title": "Sicheres Schluesselmanagement",
|
||||
"scans": [
|
||||
{
|
||||
"tool": "gitleaks",
|
||||
"scan_type": "secret_detection",
|
||||
"cwe": [],
|
||||
"rules": []
|
||||
},
|
||||
{
|
||||
"tool": "semgrep",
|
||||
"scan_type": "sast",
|
||||
"cwe": [
|
||||
"CWE-798",
|
||||
"CWE-321"
|
||||
],
|
||||
"rules": []
|
||||
}
|
||||
],
|
||||
"note": null,
|
||||
"status": "covered"
|
||||
},
|
||||
{
|
||||
"control": "cra-ai-17",
|
||||
"title": "Datenminimierung",
|
||||
"scans": [],
|
||||
"note": "process / document control — outside static-scan scope",
|
||||
"status": "not_code_checkable"
|
||||
},
|
||||
{
|
||||
"control": "cra-ai-18",
|
||||
"title": "Strukturierter SSDLC",
|
||||
"scans": [],
|
||||
"note": "process / document control — outside static-scan scope",
|
||||
"status": "not_code_checkable"
|
||||
},
|
||||
{
|
||||
"control": "cra-ai-19",
|
||||
"title": "Systematische Code Reviews",
|
||||
"scans": [],
|
||||
"note": "process / document control — outside static-scan scope",
|
||||
"status": "not_code_checkable"
|
||||
},
|
||||
{
|
||||
"control": "cra-ai-20",
|
||||
"title": "Automatisierte Sicherheitstests",
|
||||
"scans": [
|
||||
{
|
||||
"tool": "semgrep",
|
||||
"scan_type": "sast",
|
||||
"cwe": [
|
||||
"CWE-89",
|
||||
"CWE-78",
|
||||
"CWE-79",
|
||||
"CWE-22"
|
||||
],
|
||||
"rules": []
|
||||
}
|
||||
],
|
||||
"note": null,
|
||||
"status": "covered"
|
||||
},
|
||||
{
|
||||
"control": "cra-ai-21",
|
||||
"title": "Supply-Chain-Security",
|
||||
"scans": [],
|
||||
"note": "process / document control — outside static-scan scope",
|
||||
"status": "not_code_checkable"
|
||||
},
|
||||
{
|
||||
"control": "cra-ai-22",
|
||||
"title": "Dependency-Monitoring",
|
||||
"scans": [
|
||||
{
|
||||
"tool": "osv",
|
||||
"scan_type": "cve",
|
||||
"cwe": [],
|
||||
"rules": []
|
||||
},
|
||||
{
|
||||
"tool": "syft",
|
||||
"scan_type": "sbom",
|
||||
"cwe": [],
|
||||
"rules": []
|
||||
}
|
||||
],
|
||||
"note": null,
|
||||
"status": "covered"
|
||||
},
|
||||
{
|
||||
"control": "cra-ai-23",
|
||||
"title": "Software Bill of Materials (SBOM)",
|
||||
"scans": [
|
||||
{
|
||||
"tool": "syft",
|
||||
"scan_type": "sbom",
|
||||
"cwe": [],
|
||||
"rules": []
|
||||
}
|
||||
],
|
||||
"note": null,
|
||||
"status": "covered"
|
||||
},
|
||||
{
|
||||
"control": "cra-ai-24",
|
||||
"title": "Security-Logging",
|
||||
"scans": [],
|
||||
"note": "code-checkable but no off-the-shelf tool digs it out — author a detector (custom semgrep rule / check)",
|
||||
"status": "needs_tooling"
|
||||
},
|
||||
{
|
||||
"control": "cra-ai-25",
|
||||
"title": "Ereignis-Monitoring",
|
||||
"scans": [],
|
||||
"note": "process / document control — outside static-scan scope",
|
||||
"status": "not_code_checkable"
|
||||
},
|
||||
{
|
||||
"control": "cra-ai-26",
|
||||
"title": "Anomalie-Erkennung",
|
||||
"scans": [],
|
||||
"note": "process / document control — outside static-scan scope",
|
||||
"status": "not_code_checkable"
|
||||
},
|
||||
{
|
||||
"control": "cra-ai-27",
|
||||
"title": "Log-Integritaet und -Aufbewahrung",
|
||||
"scans": [],
|
||||
"note": "code-checkable but no off-the-shelf tool digs it out — author a detector (custom semgrep rule / check)",
|
||||
"status": "needs_tooling"
|
||||
},
|
||||
{
|
||||
"control": "cra-ai-28",
|
||||
"title": "Sichere Update-Mechanismen",
|
||||
"scans": [],
|
||||
"note": "code-checkable but no off-the-shelf tool digs it out — author a detector (custom semgrep rule / check)",
|
||||
"status": "needs_tooling"
|
||||
},
|
||||
{
|
||||
"control": "cra-ai-29",
|
||||
"title": "Update-Authentizitaet",
|
||||
"scans": [],
|
||||
"note": "code-checkable but no off-the-shelf tool digs it out — author a detector (custom semgrep rule / check)",
|
||||
"status": "needs_tooling"
|
||||
},
|
||||
{
|
||||
"control": "cra-ai-30",
|
||||
"title": "Update-Integritaet",
|
||||
"scans": [],
|
||||
"note": "code-checkable but no off-the-shelf tool digs it out — author a detector (custom semgrep rule / check)",
|
||||
"status": "needs_tooling"
|
||||
},
|
||||
{
|
||||
"control": "cra-ai-31",
|
||||
"title": "Lifecycle-Support",
|
||||
"scans": [],
|
||||
"note": "process / document control — outside static-scan scope",
|
||||
"status": "not_code_checkable"
|
||||
},
|
||||
{
|
||||
"control": "cra-ai-32",
|
||||
"title": "Schwachstellen-Identifikation",
|
||||
"scans": [],
|
||||
"note": "process / document control — outside static-scan scope",
|
||||
"status": "not_code_checkable"
|
||||
},
|
||||
{
|
||||
"control": "cra-ai-33",
|
||||
"title": "SBOM-Pflege und Analyse",
|
||||
"scans": [
|
||||
{
|
||||
"tool": "syft",
|
||||
"scan_type": "sbom",
|
||||
"cwe": [],
|
||||
"rules": []
|
||||
},
|
||||
{
|
||||
"tool": "osv",
|
||||
"scan_type": "cve",
|
||||
"cwe": [],
|
||||
"rules": []
|
||||
}
|
||||
],
|
||||
"note": null,
|
||||
"status": "covered"
|
||||
},
|
||||
{
|
||||
"control": "cra-ai-34",
|
||||
"title": "Risikobasierte Priorisierung",
|
||||
"scans": [],
|
||||
"note": "process / document control — outside static-scan scope",
|
||||
"status": "not_code_checkable"
|
||||
},
|
||||
{
|
||||
"control": "cra-ai-35",
|
||||
"title": "Coordinated Vulnerability Disclosure",
|
||||
"scans": [],
|
||||
"note": "process / document control — outside static-scan scope",
|
||||
"status": "not_code_checkable"
|
||||
},
|
||||
{
|
||||
"control": "cra-ai-36",
|
||||
"title": "Incident-Response-Prozess",
|
||||
"scans": [],
|
||||
"note": "process / document control — outside static-scan scope",
|
||||
"status": "not_code_checkable"
|
||||
},
|
||||
{
|
||||
"control": "cra-ai-37",
|
||||
"title": "Fruehwarnung (24h)",
|
||||
"scans": [],
|
||||
"note": "process / document control — outside static-scan scope",
|
||||
"status": "not_code_checkable"
|
||||
},
|
||||
{
|
||||
"control": "cra-ai-38",
|
||||
"title": "Detaillierter Vorfallsbericht (72h)",
|
||||
"scans": [],
|
||||
"note": "process / document control — outside static-scan scope",
|
||||
"status": "not_code_checkable"
|
||||
},
|
||||
{
|
||||
"control": "cra-ai-39",
|
||||
"title": "Patch-Bereitstellung",
|
||||
"scans": [],
|
||||
"note": "process / document control — outside static-scan scope",
|
||||
"status": "not_code_checkable"
|
||||
},
|
||||
{
|
||||
"control": "cra-ai-40",
|
||||
"title": "Dokumentation und Nachbereitung",
|
||||
"scans": [],
|
||||
"note": "process / document control — outside static-scan scope",
|
||||
"status": "not_code_checkable"
|
||||
}
|
||||
]
|
||||
}
|
||||
@@ -1,229 +0,0 @@
|
||||
//! `control-map` — the deterministic control → scan lookup table (LUT).
|
||||
//!
|
||||
//! The "transcribing" layer: it maps each compliance control to the static-scan
|
||||
//! step(s) that check it, or marks it as needing custom tooling, or as not
|
||||
//! code-checkable at all. The map is **authored and human-reviewed** — no LLM
|
||||
//! decides coverage. The LLM only enters later, downstream, to triage/ground the
|
||||
//! *tool's* findings (that lives in the agent, not here).
|
||||
//!
|
||||
//! This crate is intentionally tiny and standalone: types + an embedded JSON LUT
|
||||
//! + query helpers.
|
||||
|
||||
use serde::{Deserialize, Serialize};
|
||||
|
||||
/// Coverage bucket for a control under static (SAST-family) scanning.
|
||||
#[derive(Debug, Clone, Copy, PartialEq, Eq, Serialize, Deserialize)]
|
||||
#[serde(rename_all = "snake_case")]
|
||||
pub enum Coverage {
|
||||
/// An existing tool's scan surfaces findings for this control.
|
||||
Covered,
|
||||
/// Code-checkable, but no existing tool digs it out — we must write tooling.
|
||||
NeedsTooling,
|
||||
/// Process / document control — out of static-scan scope.
|
||||
NotCodeCheckable,
|
||||
}
|
||||
|
||||
/// One tool binding: a scan step that (at least partially) checks a control.
|
||||
#[derive(Debug, Clone, Serialize, Deserialize)]
|
||||
pub struct ScanBinding {
|
||||
/// Tool name, e.g. `"semgrep"`, `"gitleaks"`, `"syft"`, `"osv"`.
|
||||
pub tool: String,
|
||||
/// Scan family, e.g. `"sast"`, `"secret_detection"`, `"sbom"`, `"cve"`.
|
||||
pub scan_type: String,
|
||||
/// CWEs whose findings map to this control (used to attach findings back).
|
||||
#[serde(default)]
|
||||
pub cwe: Vec<String>,
|
||||
/// Optional specific rule ids this control keys on.
|
||||
#[serde(default)]
|
||||
pub rules: Vec<String>,
|
||||
}
|
||||
|
||||
/// One control's entry in the LUT.
|
||||
#[derive(Debug, Clone, Serialize, Deserialize)]
|
||||
pub struct ControlEntry {
|
||||
/// Control id, e.g. `"cra-ai-8"`.
|
||||
pub control: String,
|
||||
/// Human-readable title (for the reviewable view).
|
||||
#[serde(default)]
|
||||
pub title: String,
|
||||
/// Coverage bucket.
|
||||
pub status: Coverage,
|
||||
/// Tool bindings (empty unless `status == Covered`).
|
||||
#[serde(default)]
|
||||
pub scans: Vec<ScanBinding>,
|
||||
/// Reviewer note — why it needs tooling / isn't code-checkable.
|
||||
#[serde(default)]
|
||||
pub note: Option<String>,
|
||||
}
|
||||
|
||||
/// The control → scan lookup table for one framework.
|
||||
#[derive(Debug, Clone, Serialize, Deserialize)]
|
||||
pub struct ControlMap {
|
||||
pub version: String,
|
||||
pub framework: String,
|
||||
pub controls: Vec<ControlEntry>,
|
||||
}
|
||||
|
||||
const CRA_MAP_JSON: &str = include_str!("../data/cra_control_map.json");
|
||||
|
||||
/// Whether an authored rule id `bound` matches a scanner's emitted rule id
|
||||
/// `actual`. semgrep prefixes local-rule check_ids with a path
|
||||
/// (`tmp.compliance-cra-semgrep.cra-ai-1-flask-debug-enabled`), so match the final
|
||||
/// id segment rather than requiring exact equality.
|
||||
fn rule_id_matches(bound: &str, actual: &str) -> bool {
|
||||
actual == bound || actual.ends_with(&format!(".{bound}"))
|
||||
}
|
||||
|
||||
impl ControlMap {
|
||||
/// Load the built-in CRA control map (the embedded, authored LUT).
|
||||
pub fn cra() -> Result<Self, MapError> {
|
||||
Ok(serde_json::from_str(CRA_MAP_JSON)?)
|
||||
}
|
||||
|
||||
/// The coverage entry for a control id, if present.
|
||||
pub fn coverage(&self, control_id: &str) -> Option<&ControlEntry> {
|
||||
self.controls.iter().find(|c| c.control == control_id)
|
||||
}
|
||||
|
||||
/// Controls whose bindings include the given `tool` + `cwe` — used to attach a
|
||||
/// raw tool finding back to the control(s) it's evidence for.
|
||||
pub fn controls_for(&self, tool: &str, cwe: &str) -> Vec<&ControlEntry> {
|
||||
self.controls_for_finding(tool, Some(cwe), None)
|
||||
}
|
||||
|
||||
/// Controls a tool finding is evidence for, matched by CWE and/or the specific
|
||||
/// rule id that fired. Off-the-shelf findings bind by CWE; our custom detectors
|
||||
/// bind by rule id (precise — a broad CWE would over-attribute and then the
|
||||
/// grounded judge could drop a genuine finding as a control false positive).
|
||||
pub fn controls_for_finding(
|
||||
&self,
|
||||
tool: &str,
|
||||
cwe: Option<&str>,
|
||||
rule_id: Option<&str>,
|
||||
) -> Vec<&ControlEntry> {
|
||||
self.controls
|
||||
.iter()
|
||||
.filter(|c| {
|
||||
c.scans.iter().any(|s| {
|
||||
s.tool == tool
|
||||
&& (cwe.is_some_and(|w| s.cwe.iter().any(|x| x == w))
|
||||
|| rule_id
|
||||
.is_some_and(|r| s.rules.iter().any(|b| rule_id_matches(b, r))))
|
||||
})
|
||||
})
|
||||
.collect()
|
||||
}
|
||||
|
||||
/// Count of controls in each coverage bucket.
|
||||
pub fn summary(&self) -> CoverageSummary {
|
||||
let mut s = CoverageSummary::default();
|
||||
for c in &self.controls {
|
||||
match c.status {
|
||||
Coverage::Covered => s.covered += 1,
|
||||
Coverage::NeedsTooling => s.needs_tooling += 1,
|
||||
Coverage::NotCodeCheckable => s.not_code_checkable += 1,
|
||||
}
|
||||
}
|
||||
s
|
||||
}
|
||||
}
|
||||
|
||||
/// Coverage bucket counts.
|
||||
#[derive(Debug, Default, Clone, Copy, PartialEq, Eq)]
|
||||
pub struct CoverageSummary {
|
||||
pub covered: usize,
|
||||
pub needs_tooling: usize,
|
||||
pub not_code_checkable: usize,
|
||||
}
|
||||
|
||||
impl CoverageSummary {
|
||||
pub fn total(&self) -> usize {
|
||||
self.covered + self.needs_tooling + self.not_code_checkable
|
||||
}
|
||||
}
|
||||
|
||||
/// Errors loading a control map.
|
||||
#[derive(Debug, thiserror::Error)]
|
||||
pub enum MapError {
|
||||
#[error("failed to parse control map: {0}")]
|
||||
Parse(#[from] serde_json::Error),
|
||||
}
|
||||
|
||||
#[cfg(test)]
|
||||
mod tests {
|
||||
use super::*;
|
||||
|
||||
#[test]
|
||||
fn cra_map_loads_all_40_controls() {
|
||||
let map = ControlMap::cra().expect("CRA map should parse");
|
||||
assert_eq!(map.framework, "cra");
|
||||
assert_eq!(map.controls.len(), 40);
|
||||
assert_eq!(map.summary().total(), 40);
|
||||
}
|
||||
|
||||
#[test]
|
||||
fn hardcoded_password_control_is_tool_covered() {
|
||||
let map = ControlMap::cra().unwrap();
|
||||
let c = map.coverage("cra-ai-8").expect("cra-ai-8 present");
|
||||
assert_eq!(c.status, Coverage::Covered);
|
||||
assert!(c.scans.iter().any(|s| s.tool == "semgrep"));
|
||||
assert!(c.scans.iter().any(|s| s.tool == "gitleaks"));
|
||||
}
|
||||
|
||||
#[test]
|
||||
fn finding_attaches_back_to_control_via_tool_and_cwe() {
|
||||
let map = ControlMap::cra().unwrap();
|
||||
let hits = map.controls_for("semgrep", "CWE-798");
|
||||
assert!(hits.iter().any(|c| c.control == "cra-ai-8"));
|
||||
}
|
||||
|
||||
#[test]
|
||||
fn every_bucket_is_represented() {
|
||||
let s = ControlMap::cra().unwrap().summary();
|
||||
assert!(s.covered > 0);
|
||||
assert!(s.needs_tooling > 0);
|
||||
assert!(s.not_code_checkable > 0);
|
||||
}
|
||||
|
||||
#[test]
|
||||
fn rule_id_matching_handles_semgrep_path_prefix() {
|
||||
let bound = "cra-ai-1-flask-debug-enabled";
|
||||
assert!(rule_id_matches(bound, bound)); // exact
|
||||
assert!(rule_id_matches(
|
||||
bound,
|
||||
"tmp.compliance-cra-semgrep.cra-ai-1-flask-debug-enabled"
|
||||
)); // semgrep path prefix
|
||||
assert!(!rule_id_matches(
|
||||
bound,
|
||||
"cra-ai-1-flask-debug-enabled-extra"
|
||||
)); // not a suffix segment
|
||||
assert!(!rule_id_matches(
|
||||
bound,
|
||||
"python.lang.security.exec-detected"
|
||||
)); // unrelated
|
||||
}
|
||||
|
||||
#[test]
|
||||
fn custom_rule_finding_attaches_to_control_by_rule_id() {
|
||||
let map = ControlMap::cra().unwrap();
|
||||
// cra-ai-1 is now tool-covered by custom rules.
|
||||
assert_eq!(map.coverage("cra-ai-1").unwrap().status, Coverage::Covered);
|
||||
// A prefixed check_id still maps back to cra-ai-1 by rule id.
|
||||
let hits =
|
||||
map.controls_for_finding("semgrep", None, Some("tmp.x.cra-ai-1-tls-verify-disabled"));
|
||||
assert!(hits.iter().any(|c| c.control == "cra-ai-1"));
|
||||
}
|
||||
|
||||
#[test]
|
||||
fn custom_rule_controls_do_not_bind_by_broad_cwe() {
|
||||
let map = ControlMap::cra().unwrap();
|
||||
// cra-ai-1 rules emit CWE-489 in metadata, but the LUT binds by rule id
|
||||
// only (cwe: []) — so a stray CWE-489 finding must NOT attach to it.
|
||||
assert!(map.controls_for("semgrep", "CWE-489").is_empty());
|
||||
// The CWE path for off-the-shelf findings is unchanged.
|
||||
assert!(map
|
||||
.controls_for("semgrep", "CWE-798")
|
||||
.iter()
|
||||
.any(|c| c.control == "cra-ai-8"));
|
||||
}
|
||||
}
|
||||
Reference in New Issue
Block a user