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
This commit was merged in pull request #78.
This commit is contained in:
2026-05-12 11:27:24 +00:00
parent 5cafd13f44
commit df0063abc0
6 changed files with 88 additions and 50 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]]
name = "mongodb"
version = "3.5.1"
version = "3.6.0"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "803dd859e8afa084c255a8effd8000ff86f7c8076a50cd6d8c99e8f3496f75c2"
checksum = "1ef2c933617431ad0246fb5b43c425ebdae18c7f7259c87de0726d93b0e7e91b"
dependencies = [
"base64",
"bitflags",
@@ -3570,9 +3570,9 @@ dependencies = [
[[package]]
name = "mongodb-internal-macros"
version = "3.5.1"
version = "3.6.0"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "a973ef3dd3dbc6f6e65bbdecfd9ec5e781b9e7493b0f369a7c62e35d8e5ae2c8"
checksum = "9e5758dc828eb2d02ec30563cba365609d56ddd833190b192beaee2b475a7bb3"
dependencies = [
"macro_magic",
"proc-macro2",
@@ -4699,9 +4699,9 @@ dependencies = [
[[package]]
name = "rustls-webpki"
version = "0.103.10"
version = "0.103.13"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "df33b2b81ac578cabaf06b89b0631153a3f416b0a886e8a7a1707fb51abbd1ef"
checksum = "61c429a8649f110dddef65e2a5ad240f747e85f7758a6bccc7e5777bd33f756e"
dependencies = [
"ring",
"rustls-pki-types",
+9 -2
View File
@@ -19,7 +19,9 @@ impl Scanner for GitleaksScanner {
#[tracing::instrument(skip_all)]
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(
std::time::Duration::from_secs(300),
tokio::process::Command::new("gitleaks")
.args([
"detect",
"--source",
@@ -33,8 +35,13 @@ impl Scanner for GitleaksScanner {
"0",
])
.current_dir(repo_path)
.output()
.output(),
)
.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),
+9 -3
View File
@@ -5,16 +5,22 @@ use compliance_core::CoreError;
#[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> {
let output = tokio::process::Command::new("syft")
let output = tokio::time::timeout(
std::time::Duration::from_secs(300),
tokio::process::Command::new("syft")
.arg(repo_path)
.args(["-o", "cyclonedx-json"])
// Enable remote license lookups for all ecosystems
.env("SYFT_GOLANG_SEARCH_REMOTE_LICENSES", "true")
.env("SYFT_JAVASCRIPT_SEARCH_REMOTE_LICENSES", "true")
.env("SYFT_PYTHON_SEARCH_REMOTE_LICENSES", "true")
.env("SYFT_JAVA_USE_NETWORK", "true")
.output()
.output(),
)
.await
.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),
+18 -3
View File
@@ -19,11 +19,26 @@ impl Scanner for SemgrepScanner {
#[tracing::instrument(skip_all)]
async fn scan(&self, repo_path: &Path, repo_id: &str) -> Result<ScanOutput, CoreError> {
let output = tokio::process::Command::new("semgrep")
.args(["--config=auto", "--json", "--quiet"])
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()
.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),
@@ -32,7 +32,7 @@ pub fn AppShell() -> Element {
// Not authenticated — redirect to Keycloak login
rsx! {
document::Script {
dangerous_inner_html: "window.location.href = '/auth';"
"window.location.href = '/auth';"
}
}
}