youtube
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: 0.90). The skill makes direct YouTube Data API calls (e.g., commentThreads, videos?part=snippet, search endpoints) to fetch public video titles, descriptions and user comments from YouTube, which are untrusted, user-generated third‑party content the agent would read and could contain indirect prompt injections.
Audit Metadata