Compare commits

...

2 Commits

Author SHA1 Message Date
Sharang Parnerkar 4d5eedcc8b fix: add HTTP timeout to reqwest client and CVE stage timeout
CI / Check (pull_request) Successful in 9m39s
CI / Detect Changes (pull_request) Has been skipped
CI / Deploy Agent (pull_request) Has been skipped
CI / Deploy Dashboard (pull_request) Has been skipped
CI / Deploy Docs (pull_request) Has been skipped
CI / Deploy MCP (pull_request) Has been skipped
Without a timeout on the reqwest client, sequential NVD API calls
for each CVE alert could hang indefinitely. With 1098 SBOM entries
producing hundreds of alerts, this would stall the scan pipeline.

Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
2026-05-13 08:48:03 +02:00
sharang df0063abc0 fix: scanner timeouts, semgrep memory cap, syft remote lookups, Script error (#78)
CI / Check (push) Has been skipped
CI / Detect Changes (push) Successful in 5s
CI / Deploy Agent (push) Successful in 9m41s
CI / Deploy Dashboard (push) Successful in 15m19s
CI / Deploy Docs (push) Has been skipped
CI / Deploy MCP (push) Successful in 3m7s
## Summary

- **Scan produces no results in Orca** — semgrep (`--config=auto`, unbounded memory) and syft (remote license network calls) were getting OOM-killed or hanging in resource-constrained Orca containers. Scan would "complete" with 0 findings/SBOMs silently because each scanner failure is caught and logged as a warning.
- **Dashboard Script error spam** — `document::Script` in Dioxus 0.7 needs a single text node child for inline scripts; `dangerous_inner_html` was invalid and spammed the error log on every unauthenticated page load.

## Changes

| File | Change |
|------|--------|
| `semgrep.rs` | Add `--max-memory 500 --jobs 1`; 10-minute timeout |
| `syft.rs` | Remove remote license lookup env vars; 5-minute timeout |
| `gitleaks.rs` | 5-minute timeout |
| `app_shell.rs` | Fix `dangerous_inner_html` → text child in `document::Script` |

## Test plan

- [ ] Trigger a scan on a repo in Orca — findings and SBOM entries should now appear
- [ ] Agent logs should show timeout/error warnings rather than silent empty results when tools are killed
- [ ] Navigate to dashboard unauthenticated — Script error gone from logs
- [ ] Verify scans work end-to-end with `docker compose up`

---------

Co-authored-by: Sharang Parnerkar <30073382+mighty840@users.noreply.github.com>
Reviewed-on: #78
2026-05-12 11:27:24 +00:00
8 changed files with 109 additions and 59 deletions
+10
View File
@@ -0,0 +1,10 @@
[advisories]
ignore = [
# hickory-proto 0.25.x pulled in transitively via mongodb → hickory-resolver.
# MongoDB 3.x has not yet released with hickory-resolver 0.26.x, so we cannot
# upgrade past this without a mongodb release. Both are DNS-layer DoS vectors
# requiring a MITM/controlled DNS server against MongoDB's hostname resolution —
# not a realistic attack surface here. Revisit when mongodb bumps hickory.
"RUSTSEC-2026-0118", # NSEC3 loop, no fix available upstream
"RUSTSEC-2026-0119", # O(n²) name compression, fixed in hickory-proto >=0.26.1
]
Generated
+6 -6
View File
@@ -3524,9 +3524,9 @@ checksum = "224484c5d09285a7b8cb0a0c117e847ebd14cb6e4470ecf68cdb89c503b0edb9"
[[package]] [[package]]
name = "mongodb" name = "mongodb"
version = "3.5.1" version = "3.6.0"
source = "registry+https://github.com/rust-lang/crates.io-index" source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "803dd859e8afa084c255a8effd8000ff86f7c8076a50cd6d8c99e8f3496f75c2" checksum = "1ef2c933617431ad0246fb5b43c425ebdae18c7f7259c87de0726d93b0e7e91b"
dependencies = [ dependencies = [
"base64", "base64",
"bitflags", "bitflags",
@@ -3570,9 +3570,9 @@ dependencies = [
[[package]] [[package]]
name = "mongodb-internal-macros" name = "mongodb-internal-macros"
version = "3.5.1" version = "3.6.0"
source = "registry+https://github.com/rust-lang/crates.io-index" source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "a973ef3dd3dbc6f6e65bbdecfd9ec5e781b9e7493b0f369a7c62e35d8e5ae2c8" checksum = "9e5758dc828eb2d02ec30563cba365609d56ddd833190b192beaee2b475a7bb3"
dependencies = [ dependencies = [
"macro_magic", "macro_magic",
"proc-macro2", "proc-macro2",
@@ -4699,9 +4699,9 @@ dependencies = [
[[package]] [[package]]
name = "rustls-webpki" name = "rustls-webpki"
version = "0.103.10" version = "0.103.13"
source = "registry+https://github.com/rust-lang/crates.io-index" source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "df33b2b81ac578cabaf06b89b0631153a3f416b0a886e8a7a1707fb51abbd1ef" checksum = "61c429a8649f110dddef65e2a5ad240f747e85f7758a6bccc7e5777bd33f756e"
dependencies = [ dependencies = [
"ring", "ring",
"rustls-pki-types", "rustls-pki-types",
+6 -1
View File
@@ -35,11 +35,16 @@ impl ComplianceAgent {
config.litellm_model.clone(), config.litellm_model.clone(),
config.litellm_embed_model.clone(), config.litellm_embed_model.clone(),
)); ));
let http = reqwest::Client::builder()
.timeout(std::time::Duration::from_secs(30))
.connect_timeout(std::time::Duration::from_secs(10))
.build()
.unwrap_or_default();
Self { Self {
config, config,
db, db,
llm, llm,
http: reqwest::Client::new(), http,
session_streams: Arc::new(DashMap::new()), session_streams: Arc::new(DashMap::new()),
session_pause: Arc::new(DashMap::new()), session_pause: Arc::new(DashMap::new()),
session_semaphore: Arc::new(Semaphore::new(DEFAULT_MAX_CONCURRENT_SESSIONS)), session_semaphore: Arc::new(Semaphore::new(DEFAULT_MAX_CONCURRENT_SESSIONS)),
+27 -20
View File
@@ -19,26 +19,33 @@ impl Scanner for GitleaksScanner {
#[tracing::instrument(skip_all)] #[tracing::instrument(skip_all)]
async fn scan(&self, repo_path: &Path, repo_id: &str) -> Result<ScanOutput, CoreError> { async fn scan(&self, repo_path: &Path, repo_id: &str) -> Result<ScanOutput, CoreError> {
let output = tokio::process::Command::new("gitleaks") let output = tokio::time::timeout(
.args([ std::time::Duration::from_secs(300),
"detect", tokio::process::Command::new("gitleaks")
"--source", .args([
".", "detect",
"--report-format", "--source",
"json", ".",
"--report-path", "--report-format",
"/dev/stdout", "json",
"--no-banner", "--report-path",
"--exit-code", "/dev/stdout",
"0", "--no-banner",
]) "--exit-code",
.current_dir(repo_path) "0",
.output() ])
.await .current_dir(repo_path)
.map_err(|e| CoreError::Scanner { .output(),
scanner: "gitleaks".to_string(), )
source: Box::new(e), .await
})?; .map_err(|_| CoreError::Scanner {
scanner: "gitleaks".to_string(),
source: "timed out after 5 minutes".into(),
})?
.map_err(|e| CoreError::Scanner {
scanner: "gitleaks".to_string(),
source: Box::new(e),
})?;
if output.stdout.is_empty() { if output.stdout.is_empty() {
return Ok(ScanOutput::default()); return Ok(ScanOutput::default());
+15 -8
View File
@@ -174,19 +174,26 @@ impl PipelineOrchestrator {
k.expose_secret().to_string() k.expose_secret().to_string()
}), }),
); );
let cve_alerts = match async { let cve_alerts = match tokio::time::timeout(
cve_scanner std::time::Duration::from_secs(600),
.scan_dependencies(&repo_id, &mut sbom_entries) async {
.await cve_scanner
} .scan_dependencies(&repo_id, &mut sbom_entries)
.instrument(tracing::info_span!("stage_cve_scanning")) .await
}
.instrument(tracing::info_span!("stage_cve_scanning")),
)
.await .await
{ {
Ok(alerts) => alerts, Ok(Ok(alerts)) => alerts,
Err(e) => { Ok(Err(e)) => {
tracing::warn!("[{repo_id}] CVE scanning failed: {e}"); tracing::warn!("[{repo_id}] CVE scanning failed: {e}");
Vec::new() Vec::new()
} }
Err(_) => {
tracing::warn!("[{repo_id}] CVE scanning timed out after 10 minutes");
Vec::new()
}
}; };
// Stage 4: Pattern Scanning (GDPR + OAuth) // Stage 4: Pattern Scanning (GDPR + OAuth)
+20 -14
View File
@@ -5,20 +5,26 @@ use compliance_core::CoreError;
#[tracing::instrument(skip_all, fields(repo_id = %repo_id))] #[tracing::instrument(skip_all, fields(repo_id = %repo_id))]
pub(super) async fn run_syft(repo_path: &Path, repo_id: &str) -> Result<Vec<SbomEntry>, CoreError> { pub(super) async fn run_syft(repo_path: &Path, repo_id: &str) -> Result<Vec<SbomEntry>, CoreError> {
let output = tokio::process::Command::new("syft") let output = tokio::time::timeout(
.arg(repo_path) std::time::Duration::from_secs(300),
.args(["-o", "cyclonedx-json"]) tokio::process::Command::new("syft")
// Enable remote license lookups for all ecosystems .arg(repo_path)
.env("SYFT_GOLANG_SEARCH_REMOTE_LICENSES", "true") .args(["-o", "cyclonedx-json"])
.env("SYFT_JAVASCRIPT_SEARCH_REMOTE_LICENSES", "true") .env("SYFT_GOLANG_SEARCH_REMOTE_LICENSES", "true")
.env("SYFT_PYTHON_SEARCH_REMOTE_LICENSES", "true") .env("SYFT_JAVASCRIPT_SEARCH_REMOTE_LICENSES", "true")
.env("SYFT_JAVA_USE_NETWORK", "true") .env("SYFT_PYTHON_SEARCH_REMOTE_LICENSES", "true")
.output() .env("SYFT_JAVA_USE_NETWORK", "true")
.await .output(),
.map_err(|e| CoreError::Scanner { )
scanner: "syft".to_string(), .await
source: Box::new(e), .map_err(|_| CoreError::Scanner {
})?; scanner: "syft".to_string(),
source: "timed out after 5 minutes".into(),
})?
.map_err(|e| CoreError::Scanner {
scanner: "syft".to_string(),
source: Box::new(e),
})?;
if !output.status.success() { if !output.status.success() {
let stderr = String::from_utf8_lossy(&output.stderr); let stderr = String::from_utf8_lossy(&output.stderr);
+24 -9
View File
@@ -19,15 +19,30 @@ impl Scanner for SemgrepScanner {
#[tracing::instrument(skip_all)] #[tracing::instrument(skip_all)]
async fn scan(&self, repo_path: &Path, repo_id: &str) -> Result<ScanOutput, CoreError> { async fn scan(&self, repo_path: &Path, repo_id: &str) -> Result<ScanOutput, CoreError> {
let output = tokio::process::Command::new("semgrep") let output = tokio::time::timeout(
.args(["--config=auto", "--json", "--quiet"]) std::time::Duration::from_secs(600),
.arg(repo_path) tokio::process::Command::new("semgrep")
.output() .args([
.await "--config=auto",
.map_err(|e| CoreError::Scanner { "--json",
scanner: "semgrep".to_string(), "--quiet",
source: Box::new(e), "--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() { if !output.status.success() && output.stdout.is_empty() {
let stderr = String::from_utf8_lossy(&output.stderr); let stderr = String::from_utf8_lossy(&output.stderr);
@@ -32,7 +32,7 @@ pub fn AppShell() -> Element {
// Not authenticated — redirect to Keycloak login // Not authenticated — redirect to Keycloak login
rsx! { rsx! {
document::Script { document::Script {
dangerous_inner_html: "window.location.href = '/auth';" "window.location.href = '/auth';"
} }
} }
} }