yt

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

• Third-party content exposure detected (high risk: 0.80). The skill calls TranscriptAPI.com's YouTube endpoints (e.g., the "Transcript" curl to https://transcriptapi.com/api/v2/youtube/transcript and the search/channel endpoints) to fetch public YouTube transcripts and search results, which are untrusted, user-generated third‑party content that the agent is expected to read and interpret.