youtube
Warn
Audited by Snyk on Feb 27, 2026
Risk Level: MEDIUM
Full Analysis
MEDIUM W011: Third-party content exposure detected (indirect prompt injection risk).
- Third-party content exposure detected (high risk: 0.90). The SKILL.md clearly fetches and ingests public, user-generated YouTube content (video details, descriptions, and transcripts via the YouTube Data API or yt-dlp from youtube.com) and instructs the agent to read and analyze those transcripts (e.g., "Get Transcript for Research" and "Analyze transcript for interesting topics"), so third-party content can directly influence tool use and decisions.
MEDIUM W012: Unverifiable external dependency detected (runtime URL that controls agent).
- Potentially malicious external URL detected (high risk: 0.80). The skill's setup instructs cloning, building, and running the external MCP server at https://github.com/ZubeidHendricks/youtube-mcp-server, so it requires fetching and executing remote code from that URL (runtime depends on that fetched code).
Audit Metadata