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 accepts a user-provided YouTube URL/ID and uses transcript.py (see download_transcript in transcript.py and the SKILL.md Workflow steps 1–4) to fetch captions/subtitles from YouTube (public, user-generated/untrusted content) which are read and then used for summarization/analysis, so third-party content can influence agent behavior.
Audit Metadata
Risk Level
MEDIUM
Analyzed
Mar 1, 2026, 07:15 AM