yt-transcript

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

• Third-party content exposure detected (high risk: 0.90). The skill explicitly fetches and parses public, user-generated YouTube content (see SKILL.md and the script functions like extract_transcript_with_fallback_chain / attempt_subtitle_download and run_youtube_transcript_api_fallback), and it ingests that transcript text to generate summaries/topics and the final artifact—content that could contain instructions and thus materially influence outputs.