Lp3
Medium
- Category
- MCP Least Privilege
- Confidence
- 70% confidence
- Finding
- Without declared permissions the skill's intent is opaque and cannot be validated.
Security checks across malware telemetry and agentic risk
This skill fetches public YouTube captions and formats them for the agent to summarize, with no evidence of hidden access, credential use, persistence, or destructive behavior.
Install only if you are comfortable sending provided public YouTube video IDs through the YouTube transcript library. In sensitive environments, review or pin youtube-transcript-api before use, and remember that the actual summary is produced by your agent from the fetched transcript.
youtube-transcript-api>=0.6.0
65/65 vendors flagged this skill as clean.