ClawAudit verdict
skill-vetter-2
This is an automated skill security audit tool that scans workspace/skills directory for dangerous code patterns, applies risk scoring, and generates markdown reports; it explicitly operates read-only and does not block installation, only reports.
⚠ 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 (10)
Uses eval() — can execute arbitrary code
SKILL.md · prose · downgraded · eval(
Accesses sensitive system files
SKILL.md · prose · downgraded · /etc/passwd
Uses exec() — may execute shell commands
SKILL.md · prose · downgraded · exec(
References sudo — requests elevated privileges
SKILL.md · prose · downgraded · sudo
Accesses .ssh directory
SKILL.md · prose · downgraded · .ssh/
os.system/popen — direct OS command execution
README.md · prose · downgraded · os.system(
subprocess execution — runs system commands from Python
scan_skills.py · prose · downgraded · subprocess.run(
Python urllib.request — network access
SKILL.md · prose · downgraded · urllib.request
Python directory traversal
SKILL.md · code · os.walk(
Changes file ownership
scan_skills.py · prose · downgraded · chown
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.
dir_traversal Is this flag fair?
Thanks — recorded.