youtube-fetcher

Warn

Audited by Snyk on Mar 7, 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 explicitly fetches transcripts and creators' video descriptions from public YouTube (via youtube-transcript-api and yt-dlp / oEmbed) as documented in SKILL.md and implemented in scripts/fetch_transcript.py, and the agent is instructed to read and summarize/analyze that untrusted user-generated content, so it can materially influence subsequent actions and enable indirect prompt injection.
Audit Metadata
Risk Level
MEDIUM
Analyzed
Mar 7, 2026, 02:44 PM