proposal

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

• Third-party content exposure detected (low risk: 0.10). SKILL runtime reads only a first-party donor profile JSON via load_profile(...) and optionally a user-supplied concept-brief file path (If a concept-brief path was supplied, read it), but it does not ingest any third-party feed/chat/tickets/issue text or require fetching arbitrary outsider-authored content.