youtube-transcript

Warn

Audited by Snyk on Mar 1, 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 and parses public YouTube pages and caption tracks (see getVideoPage() fetching https://www.youtube.com/watch?v=..., extractJSON()/extractCaptions() reading ytInitialPlayerResponse and captionTracks, and then using selectedTrack.baseUrl to fetch transcripts), so it ingests untrusted, user-generated third-party content that directly influences which URLs are fetched and what the agent does next.
Audit Metadata
Risk Level
MEDIUM
Analyzed
Mar 1, 2026, 05:13 AM