youtube-full

MEDIUM W011: Third-party content exposure detected (indirect prompt injection risk).

• Third-party content exposure detected (high risk: 0.90). This skill explicitly fetches and parses user-generated YouTube content (e.g., transcripts via GET https://www.googleapis.com/youtube/v3/captions and comments via /youtube/v3/commentThreads) as part of its documented workflow in SKILL.md, so untrusted third‑party content can be read and could influence agent decisions.