AGENT LAB: SKILLS

youtube-transcribe-skill

Warn

Audited by Snyk on Feb 15, 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 fetches and scrapes transcripts and page content from arbitrary public YouTube URLs (via WebFetch/firecrawl, yt-dlp, and the chrome-devtools mcp evaluate_script DOM extraction), thereby ingesting untrusted, user-generated third-party content into the agent's workflow.
Audit Metadata
Risk Level
MEDIUM
Analyzed
Feb 15, 2026, 08:35 PM