issues

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

• Third-party content exposure detected (high risk: 0.70). The required workflow reads elicitation (and topic/topic_slug) from ./reports/*/state.json for the active session, and that JSON content is then passed into the swarm via TaskCreate/Agent(... prompt=...), so outsider-authored free text from those reports can enter the LLM context.