ClawAudit verdict
pr-triage
repo-pr-triage
GitHub PR triage skill using the gh CLI to score and prioritize PRs; executionSinkDetected reflects legitimate gh and python script invocations for the stated triage purpose.
⚠ Flagged for review — coarse, uncorroborated signal, not a confirmed exploit. Review the config yourself before installing.
Automated static analysis — not a human review. ClawAudit flags capabilities, not confirmed intent, and can produce false positives. Disagree with this verdict? Use Dispute below.
Findings (6)
Accesses sensitive system files
scripts/test_onboard.py · prose · downgraded · /etc/passwd
Recursive delete from root or home — destructive command
scripts/test_onboard.py · prose · downgraded · rm -rf /
Prompt injection — tries to override agent instructions
scripts/test_scan.py · prose · downgraded · ignore all previous instructions
subprocess execution — runs system commands from Python
scripts/scan.py · prose · downgraded · subprocess.run(
Possible prompt injection — attempts to redefine agent identity
scripts/test_scan.py · prose · downgraded · you are now
Fake system prompt — attempts to inject instructions
scripts/test_scan.py · prose · downgraded · system: you are
Why the tier is capped
Execution sink present in raw bytes (Hard Floor: class D). Final tier capped at Caution — cannot be lifted by any downgrade, example-payload opt-in, or allowlist.
Permissions & capabilities
No declared permissions — minimal attack surface.
Is this flag fair?
Thanks — recorded.