google-video-understanding
Warn
Audited by Snyk on Apr 22, 2026
Risk Level: MEDIUM
Full Analysis
MEDIUM W011: Third-party content exposure detected (indirect prompt injection risk).
- Third-party content exposure detected (high risk: 0.80). The skill explicitly accepts public YouTube URLs (SKILL.md Inputs) and scripts/video_analysis.py both uses yt_dlp to inspect YouTube content and passes the YouTube URL as file_uri to the Gemini model in analyze_youtube, so arbitrary user-generated YouTube content is fetched/ingested and interpreted as part of the workflow and could influence downstream agent decisions.
Issues (1)
W011
MEDIUMThird-party content exposure detected (indirect prompt injection risk).
Audit Metadata