ingest-youtube
Warn
Audited by Snyk on Mar 17, 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 fetches and ingests transcripts and video/audio from public YouTube (see SKILL.md and cli.py which call youtube-transcript-api/yt-dlp) and persona_monitor.py which lists channel videos with yt-dlp, so untrusted/user-generated third‑party content is read and then used to drive transcription, memory learning, and downstream agent actions.
Issues (1)
W011
MEDIUMThird-party content exposure detected (indirect prompt injection risk).
Audit Metadata