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
Risk Level
MEDIUM
Analyzed
Mar 10, 2026, 07:25 AM