cleaning-auto-transcripts

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

• Third-party content exposure detected (medium risk: 0.30). Required runtime path scripts/prepare_video.py → ytdlp.download_transcript() → loads outsider-authored YouTube auto-subtitle text from raw_transcript.json into cleaner.correct_transcript() / anibon.ytdlp.flatten_json3(), then further processes it into chunks that other substeps consume.