youtube-transcript-cn

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). This skill fetches transcripts from arbitrary YouTube URLs using youtube-transcript-api in scripts/get_transcript.py, so it ingests untrusted, user-generated third-party content (YouTube captions) that the agent reads and processes, enabling indirect prompt injection.
Audit Metadata
Risk Level
MEDIUM
Analyzed
Feb 15, 2026, 08:48 PM