clean-transcript

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

• Third-party content exposure detected (medium risk: 0.65). SKILL.md:7-19 indicates the workflow may accept “Pasted text or file” from the operating user or “Monologue note” content via $monologue-notes; that latter path ingests monologue note body text authored outside the immediate chat context (outsider-authored free text) into the LLM for cleaning.