video-viewing
Warn
Audited by Snyk on Feb 18, 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 arbitrary direct video URLs supplied to the tool (see scripts/download_video.py: download_video() and main() which accept any http(s) URL) and then extracts frames for analysis ("After downloading, Claude can analyze the video content"), so it ingests untrusted third‑party media that the agent is expected to read and interpret.
Audit Metadata