ClawAudit verdict
vibe-check
Code quality auditor that runs local bash scripts to detect AI-generated code patterns; outputs a scored report card with no external data transmission.
⚠ 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 (7)
Uses eval() — can execute arbitrary code
TESTING.md · code · eval(
Possible hardcoded credential
test_samples/bad_api.py · prose · downgraded · password = "admin123
Pipe to python — executes piped content as Python code
scripts/analyze.sh · prose · downgraded · | python3
Pipe to bash — executes piped content as shell commands
scripts/vibe-check.sh · prose · downgraded · | bash
Uses exec() — may execute shell commands
SKILL.md · prose · downgraded · exec(
Python os.environ.get — reads environment variable
scripts/report.sh · prose · downgraded · os.environ.get(
Popular HTTP library — network access
scripts/vibe-check.sh · prose · downgraded · got
Why the tier is capped
Execution sink present in raw bytes (Hard Floor: class A/B/C). 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.