youtube-data-api-expert

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

• Third-party content exposure detected (high risk: 0.90). This skill explicitly instructs the agent to fetch and process untrusted, user‑generated YouTube content (e.g., commentThreads.list in references/comments.md and search.list/videos.list in references/search.md) and shows workflows that read comments/search results and then act (e.g., comments.insert, playlist/video operations), so third‑party content could influence the agent's decisions or tool use.