qm

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

• Third-party content exposure detected (medium risk: 0.65). The required workflow ingests outsider-authored free text from watchbill.json fetched at runtime in the “Retrieve the rigging, the watchbill, and the base” step (it explicitly reads and validates watchbill.json, and watchbill entries are free-form scenario references that the LLM would incorporate into context for processing/dispatch decisions).