youtube-transcript

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: 0.90). The scripts (scripts/extract_transcript.py and its extract_subtitles/extract_metadata functions) call yt-dlp to fetch YouTube video metadata and VTT subtitles from arbitrary YouTube URLs (public, user-generated content) which the skill parses and ingests into Markdown, exposing the agent to untrusted third-party text that could carry indirect prompt injection.
Audit Metadata
Risk Level
MEDIUM
Analyzed
Feb 15, 2026, 09:29 PM