yt-transcribe

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

• Third-party content exposure detected (high risk: 1.00). This skill ingests spoken content from arbitrary public YouTube videos (via commands like yt-transcribe "https://youtube.com/watch?v=VIDEO_ID" -q) and explicitly instructs the agent to read and summarize those transcripts, exposing it to untrusted, user-generated third-party content.