youtube-search
Warn
Audited by Snyk on Mar 10, 2026
Risk Level: MEDIUM
Full Analysis
MEDIUM W011: Third-party content exposure detected (indirect prompt injection risk).
- Third-party content exposure detected (high risk: 1.00). The SKILL.md explicitly instructs the agent to fetch and parse open/public YouTube content (Methods A: web_search "site:youtube.com", B: YouTube Data API, C: SerpAPI, D: youtube-transcript-api, E: yt-dlp) and the recommended workflows extract and analyze transcripts/descriptions (e.g., "Get transcripts for top videos" and "Now pass to Claude for summarization"), meaning the agent will read untrusted, user-generated third-party content that can influence its actions.
Audit Metadata