youtube-content

Warn

Audited by Snyk on Feb 17, 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 explicitly fetches transcripts and metadata from public YouTube videos via scripts/fetch_youtube.py (using youtube-transcript-api and yt-dlp) and then reads and analyzes those user-generated/untrusted transcripts as part of its workflow, exposing the agent to potential indirect prompt injection.
Audit Metadata
Risk Level
MEDIUM
Analyzed
Feb 17, 2026, 12:34 AM