youtube

Warn

Audited by Snyk on Mar 8, 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 and ingests public, user-generated YouTube content (videos, subtitles, and playlist metadata) via yt-dlp — e.g., scripts/transcript.py downloads and cleans VTT subtitles and SKILL.md explicitly directs using transcripts for AI analysis — which exposes the agent to untrusted third-party content that could contain instructions influencing subsequent actions.
Audit Metadata
Risk Level
MEDIUM
Analyzed
Mar 8, 2026, 01:07 PM