media-understand
Warn
Audited by Snyk on Feb 16, 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 and analyzes YouTube URLs (public, user-generated content) as part of its normal workflow (e.g., "YouTube video summary"), meaning the agent ingests and interprets untrusted third‑party media that could contain indirect prompt injection.
Audit Metadata