media-hub
Warn
Audited by Snyk on Apr 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 explicitly accepts and downloads media from arbitrary URLs (see video_understanding.py: download_from_url and process_video which take file_url) and SKILL.md Step 1 ("URL to downloadable media"), then transcribes and analyzes that content—meaning untrusted, third‑party content is ingested and directly used to drive analysis and outputs, enabling indirect prompt injection.
Issues (1)
W011
MEDIUMThird-party content exposure detected (indirect prompt injection risk).
Audit Metadata