youtube-transcript

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

• Third-party content exposure detected (high risk: 0.95). The required runtime workflow fetches YouTube captions/transcripts via youtube_transcript_api.fetch(video_id, ...) and then concatenates the snippet s.text into plain text that is fed into the LLM context for analysis (outsider-authored free text from public YouTube content).