watch-video
Warn
Audited by Snyk on May 3, 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 downloads and ingests arbitrary public videos and captions via yt-dlp (scripts/download.py / README: "works on YouTube and on every other site yt-dlp supports") and then instructs the agent to Read every extracted frame and transcript as part of the core workflow (SKILL.md / scripts/watch.py), so untrusted, user-generated content can directly influence the agent's decisions and actions.
Issues (1)
W011
MEDIUMThird-party content exposure detected (indirect prompt injection risk).
Audit Metadata