sms-partner

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

• Third-party content exposure detected (high risk: 0.70). The skill's workflow explicitly instructs the agent to fetch and run actions against third-party SMS Partner data (e.g., via "membrane action run ..." and the proxy "membrane request CONNECTION_ID /path/to/endpoint"), which will ingest user-generated messages/conversations from the SMS Partner API that the agent is expected to read and that could materially influence subsequent actions.