story-lab

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

• Third-party content exposure detected (medium risk: 0.30). In converge.py, the runtime path calls the composed skills /create-story and /review-story with an active draft that may come directly from the user-supplied --input file (active_draft = input_path), so outsider-authored free text is ingested for generation/critique.