youtube-content

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

• Third-party content exposure detected (high risk: 0.85). Outsider-authored free text can enter the LLM context when the workflow downloads YouTube auto/manual subtitles/transcripts from a URL (public web content) via yt-dlp --write-auto-sub/--write-sub --convert-subs ... "URL", then parses the resulting SRT into plain text and sends it to the LLM for summarization.