ClawAudit verdict

yt-dlp-downloader

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

The skill instructs the agent to execute a user-supplied URL directly via a script with strict rules against deviation, and the instruction 'only return main.py output, do not attempt to fix' suppresses agent judgment — this pattern could be abused to run arbitrary URLs through yt-dlp without agent oversight.

⚠ 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.

90
security
100
transparency
70
maintenance

Findings (1)

Pattern match medium

subprocess execution — runs system commands from Python

scripts/main.py · prose · downgraded · subprocess.run(

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