video-analyzer

Warn

Audited by Snyk on Mar 6, 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 downloads and ingests arbitrary public video URLs (see scripts/analyze.py: prepare_video -> download_direct_url using httpx and download_with_ytdlp using yt-dlp, and SKILL.md CLI examples for internet/video-site URLs), then passes extracted frames or the video to the model for interpretation, so untrusted third-party content can be read and influence model outputs.
Audit Metadata
Risk Level
MEDIUM
Analyzed
Mar 6, 2026, 04:42 AM