jtbd

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

• Third-party content exposure detected (medium risk: 0.30). Skill’s required runtime workflow ingests the user-provided transcript/reviews files by reading arbitrary text content from paths (Transcript Ingest Mode: read the transcript and run scripts/ingest_transcript.py <path>; Review-Mining Intake: run scripts/mine_reviews.py <path>), so outsider-authored free text can be supplied via those inputs.