Fix formatting and clippy warnings across workspace
All checks were successful
CI / Format (push) Successful in 3s
CI / Clippy (push) Successful in 2m15s
CI / Security Audit (push) Successful in 1m34s
CI / Tests (push) Successful in 3m4s

- Run cargo fmt on all crates
- Fix regex patterns using unsupported lookahead in patterns.rs
- Replace unwrap() calls with compile_regex() helper
- Fix never type fallback in GitHub tracker
- Fix redundant field name in findings page
- Allow enum_variant_names for Dioxus Route enum
- Fix &mut Vec -> &mut [T] clippy lint in sbom.rs
- Mark unused-but-intended APIs with #[allow(dead_code)]

Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
This commit is contained in:
Sharang Parnerkar
2026-03-02 17:41:03 +01:00
parent 62196e5d74
commit 03ee69834d
37 changed files with 519 additions and 220 deletions

View File

@@ -3,13 +3,22 @@ use compliance_core::CoreError;
pub struct CveScanner {
http: reqwest::Client,
#[allow(dead_code)]
searxng_url: Option<String>,
nvd_api_key: Option<String>,
}
impl CveScanner {
pub fn new(http: reqwest::Client, searxng_url: Option<String>, nvd_api_key: Option<String>) -> Self {
Self { http, searxng_url, nvd_api_key }
pub fn new(
http: reqwest::Client,
searxng_url: Option<String>,
nvd_api_key: Option<String>,
) -> Self {
Self {
http,
searxng_url,
nvd_api_key,
}
}
pub async fn scan_dependencies(
@@ -87,9 +96,10 @@ impl CveScanner {
return Ok(Vec::new());
}
let result: OsvBatchResponse = resp.json().await.map_err(|e| {
CoreError::Http(format!("Failed to parse OSV.dev response: {e}"))
})?;
let result: OsvBatchResponse = resp
.json()
.await
.map_err(|e| CoreError::Http(format!("Failed to parse OSV.dev response: {e}")))?;
let vulns = result
.results
@@ -101,8 +111,9 @@ impl CveScanner {
.map(|v| OsvVuln {
id: v.id,
summary: v.summary,
severity: v.database_specific
.and_then(|d| d.get("severity").and_then(|s| s.as_str()).map(String::from)),
severity: v.database_specific.and_then(|d| {
d.get("severity").and_then(|s| s.as_str()).map(String::from)
}),
})
.collect()
})
@@ -123,17 +134,19 @@ impl CveScanner {
req = req.header("apiKey", key.as_str());
}
let resp = req.send().await.map_err(|e| {
CoreError::Http(format!("NVD request failed: {e}"))
})?;
let resp = req
.send()
.await
.map_err(|e| CoreError::Http(format!("NVD request failed: {e}")))?;
if !resp.status().is_success() {
return Ok(None);
}
let body: serde_json::Value = resp.json().await.map_err(|e| {
CoreError::Http(format!("Failed to parse NVD response: {e}"))
})?;
let body: serde_json::Value = resp
.json()
.await
.map_err(|e| CoreError::Http(format!("Failed to parse NVD response: {e}")))?;
// Extract CVSS v3.1 base score
let score = body["vulnerabilities"]
@@ -146,15 +159,22 @@ impl CveScanner {
Ok(score)
}
#[allow(dead_code)]
pub async fn search_context(&self, cve_id: &str) -> Result<Vec<String>, CoreError> {
let Some(searxng_url) = &self.searxng_url else {
return Ok(Vec::new());
};
let url = format!("{}/search?q={cve_id}&format=json&engines=duckduckgo", searxng_url.trim_end_matches('/'));
let resp = self.http.get(&url).send().await.map_err(|e| {
CoreError::Http(format!("SearXNG request failed: {e}"))
})?;
let url = format!(
"{}/search?q={cve_id}&format=json&engines=duckduckgo",
searxng_url.trim_end_matches('/')
);
let resp = self
.http
.get(&url)
.send()
.await
.map_err(|e| CoreError::Http(format!("SearXNG request failed: {e}")))?;
if !resp.status().is_success() {
return Ok(Vec::new());

View File

@@ -41,12 +41,7 @@ impl GitOps {
let head_ref = repo.head()?;
let head_name = head_ref.name().unwrap_or("HEAD");
repo.reference(
head_name,
fetch_commit.id(),
true,
"fast-forward",
)?;
repo.reference(head_name, fetch_commit.id(), true, "fast-forward")?;
repo.checkout_head(Some(git2::build::CheckoutBuilder::default().force()))?;
tracing::info!("Fetched and fast-forwarded {}", repo_path.display());
@@ -68,6 +63,7 @@ impl GitOps {
}
}
#[allow(dead_code)]
pub fn get_changed_files(
repo_path: &Path,
old_sha: &str,

View File

@@ -29,14 +29,15 @@ impl PipelineOrchestrator {
llm: Arc<LlmClient>,
http: reqwest::Client,
) -> Self {
Self { config, db, llm, http }
Self {
config,
db,
llm,
http,
}
}
pub async fn run(
&self,
repo_id: &str,
trigger: ScanTrigger,
) -> Result<(), AgentError> {
pub async fn run(&self, repo_id: &str, trigger: ScanTrigger) -> Result<(), AgentError> {
// Look up the repository
let repo = self
.db
@@ -48,7 +49,9 @@ impl PipelineOrchestrator {
// Create scan run
let scan_run = ScanRun::new(repo_id.to_string(), trigger);
let insert = self.db.scan_runs().insert_one(&scan_run).await?;
let scan_run_id = insert.inserted_id.as_object_id()
let scan_run_id = insert
.inserted_id
.as_object_id()
.map(|id| id.to_hex())
.unwrap_or_default();
@@ -57,29 +60,35 @@ impl PipelineOrchestrator {
// Update scan run status
match &result {
Ok(count) => {
self.db.scan_runs().update_one(
doc! { "_id": &insert.inserted_id },
doc! {
"$set": {
"status": "completed",
"current_phase": "completed",
"new_findings_count": *count as i64,
"completed_at": mongodb::bson::DateTime::now(),
}
},
).await?;
self.db
.scan_runs()
.update_one(
doc! { "_id": &insert.inserted_id },
doc! {
"$set": {
"status": "completed",
"current_phase": "completed",
"new_findings_count": *count as i64,
"completed_at": mongodb::bson::DateTime::now(),
}
},
)
.await?;
}
Err(e) => {
self.db.scan_runs().update_one(
doc! { "_id": &insert.inserted_id },
doc! {
"$set": {
"status": "failed",
"error_message": e.to_string(),
"completed_at": mongodb::bson::DateTime::now(),
}
},
).await?;
self.db
.scan_runs()
.update_one(
doc! { "_id": &insert.inserted_id },
doc! {
"$set": {
"status": "failed",
"error_message": e.to_string(),
"completed_at": mongodb::bson::DateTime::now(),
}
},
)
.await?;
}
}
@@ -91,9 +100,7 @@ impl PipelineOrchestrator {
repo: &TrackedRepository,
scan_run_id: &str,
) -> Result<u32, AgentError> {
let repo_id = repo.id.as_ref()
.map(|id| id.to_hex())
.unwrap_or_default();
let repo_id = repo.id.as_ref().map(|id| id.to_hex()).unwrap_or_default();
// Stage 0: Change detection
tracing::info!("[{repo_id}] Stage 0: Change detection");
@@ -140,7 +147,10 @@ impl PipelineOrchestrator {
k.expose_secret().to_string()
}),
);
let cve_alerts = match cve_scanner.scan_dependencies(&repo_id, &mut sbom_entries).await {
let cve_alerts = match cve_scanner
.scan_dependencies(&repo_id, &mut sbom_entries)
.await
{
Ok(alerts) => alerts,
Err(e) => {
tracing::warn!("[{repo_id}] CVE scanning failed: {e}");
@@ -163,7 +173,10 @@ impl PipelineOrchestrator {
}
// Stage 5: LLM Triage
tracing::info!("[{repo_id}] Stage 5: LLM Triage ({} findings)", all_findings.len());
tracing::info!(
"[{repo_id}] Stage 5: LLM Triage ({} findings)",
all_findings.len()
);
self.update_phase(scan_run_id, "llm_triage").await;
let triaged = crate::llm::triage::triage_findings(&self.llm, &mut all_findings).await;
tracing::info!("[{repo_id}] Triaged: {triaged} findings passed confidence threshold");
@@ -223,16 +236,19 @@ impl PipelineOrchestrator {
// Issue creation is handled by the trackers module - deferred to agent
// Stage 7: Update repository
self.db.repositories().update_one(
doc! { "_id": repo.id },
doc! {
"$set": {
"last_scanned_commit": &current_sha,
"updated_at": mongodb::bson::DateTime::now(),
self.db
.repositories()
.update_one(
doc! { "_id": repo.id },
doc! {
"$set": {
"last_scanned_commit": &current_sha,
"updated_at": mongodb::bson::DateTime::now(),
},
"$inc": { "findings_count": new_count as i64 },
},
"$inc": { "findings_count": new_count as i64 },
},
).await?;
)
.await?;
tracing::info!("[{repo_id}] Scan complete: {new_count} new findings");
Ok(new_count)
@@ -240,13 +256,17 @@ impl PipelineOrchestrator {
async fn update_phase(&self, scan_run_id: &str, phase: &str) {
if let Ok(oid) = mongodb::bson::oid::ObjectId::parse_str(scan_run_id) {
let _ = self.db.scan_runs().update_one(
doc! { "_id": oid },
doc! {
"$set": { "current_phase": phase },
"$push": { "phases_completed": phase },
},
).await;
let _ = self
.db
.scan_runs()
.update_one(
doc! { "_id": oid },
doc! {
"$set": { "current_phase": phase },
"$push": { "phases_completed": phase },
},
)
.await;
}
}
}

View File

@@ -7,6 +7,15 @@ use regex::Regex;
use crate::pipeline::dedup;
fn compile_regex(pattern: &str) -> Regex {
Regex::new(pattern).unwrap_or_else(|e| {
tracing::warn!("Invalid regex pattern '{pattern}': {e}, using empty fallback");
// SAFETY: "^$" is a known-valid regex that matches only empty strings
#[allow(clippy::unwrap_used)]
Regex::new("^$").unwrap()
})
}
pub struct GdprPatternScanner {
patterns: Vec<PatternRule>,
}
@@ -31,7 +40,7 @@ impl GdprPatternScanner {
id: "gdpr-pii-logging".to_string(),
title: "PII data potentially logged".to_string(),
description: "Logging statements that may contain personally identifiable information (email, SSN, phone, IP address).".to_string(),
pattern: Regex::new(r#"(?i)(log|print|console\.|logger\.|tracing::)\s*[\.(].*\b(email|ssn|social.?security|phone.?number|ip.?addr|passport|date.?of.?birth|credit.?card)\b"#).unwrap_or_else(|_| Regex::new("^$").unwrap()),
pattern: compile_regex(r#"(?i)(log|print|console\.|logger\.|tracing::)\s*[\.(].*\b(email|ssn|social.?security|phone.?number|ip.?addr|passport|date.?of.?birth|credit.?card)\b"#),
severity: Severity::High,
file_extensions: vec!["rs", "py", "js", "ts", "java", "go", "rb"].into_iter().map(String::from).collect(),
},
@@ -39,7 +48,7 @@ impl GdprPatternScanner {
id: "gdpr-no-consent".to_string(),
title: "Data collection without apparent consent mechanism".to_string(),
description: "Data collection endpoint that doesn't reference consent or opt-in mechanisms.".to_string(),
pattern: Regex::new(r#"(?i)(collect|store|save|persist|record).*\b(personal|user.?data|pii|biometric)\b"#).unwrap_or_else(|_| Regex::new("^$").unwrap()),
pattern: compile_regex(r#"(?i)(collect|store|save|persist|record).*\b(personal|user.?data|pii|biometric)\b"#),
severity: Severity::Medium,
file_extensions: vec!["rs", "py", "js", "ts", "java", "go"].into_iter().map(String::from).collect(),
},
@@ -47,7 +56,7 @@ impl GdprPatternScanner {
id: "gdpr-no-delete-endpoint".to_string(),
title: "Missing data deletion capability".to_string(),
description: "User data models or controllers without corresponding deletion endpoints (right to erasure).".to_string(),
pattern: Regex::new(r#"(?i)(class|struct|model)\s+User(?!.*[Dd]elete)"#).unwrap_or_else(|_| Regex::new("^$").unwrap()),
pattern: compile_regex(r#"(?i)(class|struct|model)\s+User"#),
severity: Severity::Medium,
file_extensions: vec!["rs", "py", "js", "ts", "java", "go", "rb"].into_iter().map(String::from).collect(),
},
@@ -55,7 +64,7 @@ impl GdprPatternScanner {
id: "gdpr-hardcoded-retention".to_string(),
title: "Hardcoded data retention period".to_string(),
description: "Data retention periods should be configurable for GDPR compliance.".to_string(),
pattern: Regex::new(r#"(?i)(retention|ttl|expire|keep.?for)\s*[=:]\s*\d+"#).unwrap_or_else(|_| Regex::new("^$").unwrap()),
pattern: compile_regex(r#"(?i)(retention|ttl|expire|keep.?for)\s*[=:]\s*\d+"#),
severity: Severity::Low,
file_extensions: vec!["rs", "py", "js", "ts", "java", "go", "yaml", "yml", "toml", "json"].into_iter().map(String::from).collect(),
},
@@ -74,7 +83,13 @@ impl Scanner for GdprPatternScanner {
}
async fn scan(&self, repo_path: &Path, repo_id: &str) -> Result<ScanOutput, CoreError> {
let findings = scan_with_patterns(repo_path, repo_id, &self.patterns, ScanType::Gdpr, "gdpr-patterns")?;
let findings = scan_with_patterns(
repo_path,
repo_id,
&self.patterns,
ScanType::Gdpr,
"gdpr-patterns",
)?;
Ok(ScanOutput {
findings,
sbom_entries: Vec::new(),
@@ -89,7 +104,7 @@ impl OAuthPatternScanner {
id: "oauth-implicit-grant".to_string(),
title: "OAuth implicit grant flow detected".to_string(),
description: "Implicit grant flow is deprecated and insecure. Use authorization code flow with PKCE instead.".to_string(),
pattern: Regex::new(r#"(?i)(response_type\s*[=:]\s*["']?token|grant_type\s*[=:]\s*["']?implicit)"#).unwrap_or_else(|_| Regex::new("^$").unwrap()),
pattern: compile_regex(r#"(?i)(response_type\s*[=:]\s*["']?token|grant_type\s*[=:]\s*["']?implicit)"#),
severity: Severity::High,
file_extensions: vec!["rs", "py", "js", "ts", "java", "go", "yaml", "yml", "json"].into_iter().map(String::from).collect(),
},
@@ -97,7 +112,7 @@ impl OAuthPatternScanner {
id: "oauth-missing-pkce".to_string(),
title: "OAuth flow without PKCE".to_string(),
description: "Authorization code flow should use PKCE (code_challenge/code_verifier) for public clients.".to_string(),
pattern: Regex::new(r#"(?i)authorization.?code(?!.*code.?challenge)(?!.*pkce)"#).unwrap_or_else(|_| Regex::new("^$").unwrap()),
pattern: compile_regex(r#"(?i)authorization.?code"#),
severity: Severity::Medium,
file_extensions: vec!["rs", "py", "js", "ts", "java", "go"].into_iter().map(String::from).collect(),
},
@@ -105,7 +120,7 @@ impl OAuthPatternScanner {
id: "oauth-token-localstorage".to_string(),
title: "Token stored in localStorage".to_string(),
description: "Storing tokens in localStorage is vulnerable to XSS. Use httpOnly cookies or secure session storage.".to_string(),
pattern: Regex::new(r#"(?i)localStorage\.(set|get)Item\s*\(\s*["'].*token"#).unwrap_or_else(|_| Regex::new("^$").unwrap()),
pattern: compile_regex(r#"(?i)localStorage\.(set|get)Item\s*\(\s*["'].*token"#),
severity: Severity::High,
file_extensions: vec!["js", "ts", "jsx", "tsx"].into_iter().map(String::from).collect(),
},
@@ -113,7 +128,7 @@ impl OAuthPatternScanner {
id: "oauth-token-url".to_string(),
title: "Token passed in URL parameters".to_string(),
description: "Tokens in URLs can leak via referrer headers, server logs, and browser history.".to_string(),
pattern: Regex::new(r#"(?i)(access_token|bearer)\s*[=]\s*.*\b(url|query|param|href)\b"#).unwrap_or_else(|_| Regex::new("^$").unwrap()),
pattern: compile_regex(r#"(?i)(access_token|bearer)\s*[=]\s*.*\b(url|query|param|href)\b"#),
severity: Severity::High,
file_extensions: vec!["rs", "py", "js", "ts", "java", "go"].into_iter().map(String::from).collect(),
},
@@ -132,7 +147,13 @@ impl Scanner for OAuthPatternScanner {
}
async fn scan(&self, repo_path: &Path, repo_id: &str) -> Result<ScanOutput, CoreError> {
let findings = scan_with_patterns(repo_path, repo_id, &self.patterns, ScanType::OAuth, "oauth-patterns")?;
let findings = scan_with_patterns(
repo_path,
repo_id,
&self.patterns,
ScanType::OAuth,
"oauth-patterns",
)?;
Ok(ScanOutput {
findings,
sbom_entries: Vec::new(),
@@ -211,7 +232,16 @@ fn scan_with_patterns(
fn walkdir(path: &Path) -> Result<Vec<walkdir::DirEntry>, CoreError> {
// Simple recursive file walk, skipping hidden dirs and common non-source dirs
let skip_dirs = [".git", "node_modules", "target", "vendor", ".venv", "__pycache__", "dist", "build"];
let skip_dirs = [
".git",
"node_modules",
"target",
"vendor",
".venv",
"__pycache__",
"dist",
"build",
];
let entries: Vec<_> = walkdir::WalkDir::new(path)
.into_iter()

View File

@@ -72,7 +72,9 @@ async fn run_syft(repo_path: &Path, repo_id: &str) -> Result<Vec<SbomEntry>, Cor
entry.license = c.licenses.and_then(|ls| {
ls.first().and_then(|l| {
l.license.as_ref().map(|lic| {
lic.id.clone().unwrap_or_else(|| lic.name.clone().unwrap_or_default())
lic.id
.clone()
.unwrap_or_else(|| lic.name.clone().unwrap_or_default())
})
})
});
@@ -99,8 +101,10 @@ async fn run_cargo_audit(repo_path: &Path, _repo_id: &str) -> Result<Vec<AuditVu
source: Box::new(e),
})?;
let result: CargoAuditOutput = serde_json::from_slice(&output.stdout)
.unwrap_or_else(|_| CargoAuditOutput { vulnerabilities: CargoAuditVulns { list: Vec::new() } });
let result: CargoAuditOutput =
serde_json::from_slice(&output.stdout).unwrap_or_else(|_| CargoAuditOutput {
vulnerabilities: CargoAuditVulns { list: Vec::new() },
});
let vulns = result
.vulnerabilities
@@ -116,7 +120,7 @@ async fn run_cargo_audit(repo_path: &Path, _repo_id: &str) -> Result<Vec<AuditVu
Ok(vulns)
}
fn merge_audit_vulns(entries: &mut Vec<SbomEntry>, vulns: Vec<AuditVuln>) {
fn merge_audit_vulns(entries: &mut [SbomEntry], vulns: Vec<AuditVuln>) {
for vuln in vulns {
if let Some(entry) = entries.iter_mut().find(|e| e.name == vuln.package) {
entry.known_vulnerabilities.push(VulnRef {

View File

@@ -66,11 +66,10 @@ 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.and_then(|m| {
m.get("cwe")
.and_then(|v| v.as_str())
.map(|s| s.to_string())
});
finding.cwe = r
.extra
.metadata
.and_then(|m| m.get("cwe").and_then(|v| v.as_str()).map(|s| s.to_string()));
finding
})
.collect();