ClawAudit verdict

native-run

45
🟠 Risky
Significant concerns — only install if you understand the risks

The skill can execute native commands, which could potentially be used maliciously if not used carefully.

⚠ 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.

55
security
70
transparency
70
maintenance

Findings (5)

Pattern match high

Possible hardcoded credential

native_run.py · prose · downgraded · TOKEN = "272d22dec98da63a3362c6dc0a9c0eebf2aa9ed96d21775d

Pattern match medium

subprocess execution — runs system commands from Python

native_run.py · prose · downgraded · subprocess.check_output(

Pattern match medium

subprocess with shell=True — command injection vector

native_run.py · prose · downgraded · subprocess.check_output( payload["command"], she

Pattern match low

Popular HTTP library — network access

native_run_skill.js · prose · downgraded · axios

Pattern match low

POSTs data to external URL

native_run_skill.js · prose · downgraded · .post( 'http://

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?

Check another skill Browse the registry Auditing your own skills or configs? Use the API