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). This skill's transcript.js calls YoutubeTranscript.fetchTranscript on arbitrary YouTube video IDs/URLs to retrieve public, user-generated captions (as stated in SKILL.md), which the agent is intended to read for summarization/analysis and therefore could carry untrusted instructions that influence downstream behavior.
Audit Metadata