Caveat verdict

video-summary

88
🟢 Trusted
No high-risk patterns surfaced by the deep scan — automated capability review, not behavioral proof.

This skill explicitly declares its security posture: downloads subtitles via yt-dlp, outputs structured LLM requests without calling APIs directly, and notes cookies are never transmitted externally, consistent with stated summarization purpose.

⚠ Flagged for review — coarse, uncorroborated signal, not a confirmed exploit. Review the config yourself before installing.

Automated static analysis — not a human review. Caveat flags capabilities, not confirmed intent, and can produce false positives. Disagree with this verdict? Use Dispute below.

50
security
60
transparency
90
maintenance

Permission integrity

Code accesses API keys/tokens but declares no environment variables

credential_access

Installs packages at runtime — transitive dependencies are not auditable

package_install

Findings (1)

Pattern match critical

Possible hardcoded credential

SKILL.md · code · API_KEY="your-api-key-here

Permissions & capabilities

Requires 5 system binaries.

credential_accesspackage_installnetwork_in

Is this flag fair?

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