ClawAudit verdict

video-understand

88
🟢 Trusted
Low risk — reviewed by ClawAudit, behavior matches stated purpose

This skill analyzes videos via Gemini or Kimi/Moonshot AI with the user's own API key and notably includes a security warning about treating video content as untrusted data, behavior matches stated video understanding purpose.

⚠ 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.

35
security
50
transparency
70
maintenance

Permission integrity

Code accesses API keys/tokens but declares no environment variables

credential_access

Findings (2)

Pattern match critical

Possible hardcoded credential

rules/install.md · code · API_KEY="your-key-here

Pattern match high

References sudo — requests elevated privileges

rules/install.md · code · sudo

Permissions & capabilities

No declared permissions — minimal attack surface.

credential_access

Is this flag fair?

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