video-content-analyzer

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: 1.00). The skill ingests public, user-generated content: it reads platform video URLs (e.g., TikTok webVideoUrl / Instagram / YouTube URLs) from the input and either passes those URLs to Gemini for analysis or downloads them via download_video (requests.get) and uploads to Gemini in scripts/analyze_videos.py, so the agent will fetch and interpret untrusted third‑party web/media content.
Audit Metadata
Risk Level
MEDIUM
Analyzed
Feb 15, 2026, 08:51 PM