youtube-transcript-summarizer

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

• Third-party content exposure detected (high risk: 0.90). This skill fetches user-generated transcripts from YouTube (via youtube_transcript_api and optional yt-dlp title fetching) and injects that untrusted transcript text directly into the Claude summarization prompt, so third-party content is read and can materially influence the agent's outputs and actions.

MEDIUM W012: Unverifiable external dependency detected (runtime URL that controls agent).

• Potentially malicious external URL detected (high risk: 0.90). The skill fetches YouTube content at runtime (e.g., https://www.youtube.com/watch?v=VIDEO_ID) and injects the fetched transcript text directly into the Claude prompt, so remote content from that URL directly controls the model input.