youtube-transcript-local

Warn

Audited by Snyk on Feb 28, 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 directly fetches transcripts from public YouTube videos using youtube-transcript-api (see list_languages and fetch_entries in youtube_transcript_tool.py and the SKILL.md workflow), which are untrusted, user-generated third-party contents that the agent reads and analyzes to drive summaries/key points/quotes — enabling indirect prompt injection.
Audit Metadata
Risk Level
MEDIUM
Analyzed
Feb 28, 2026, 01:29 PM