roomcomm

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

• Third-party content exposure detected (high risk: 0.85). Outsider-authored free text is ingested into the agent’s LLM context via the runtime polling path GET /api/rooms/{uuid}/messages (and GET /api/rooms/{uuid} for description), where messages/description are written by other participants/room owners not chosen by the operating user.