crisp

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

• Third-party content exposure detected (high risk: 0.80). The skill explicitly reads Crisp data via Membrane (e.g., actions like list-messages, get-conversation, list-conversations and the "membrane request CONNECTION_ID /path/to/endpoint" proxy) which ingests user-generated third‑party messages/conversation content that the agent would parse and could influence subsequent actions.