video-understand
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). The skill explicitly accepts and downloads arbitrary YouTube and other public video URLs (see scripts/process_video.py download_video and references/video-sources.md and references/gemini.md/OpenRouter flows) and then sends that untrusted, user-generated web content to models for transcription and visual analysis, so the agent will read/interpret third‑party content.
Audit Metadata