socket

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

• Third-party content exposure detected (high risk: 0.80). The skill instructs the agent to fetch and run actions against Socket data via Membrane (e.g., membrane action list/run and membrane request CONNECTION_ID /path/to/endpoint), which will return user-generated messages, files, and conversations from a third-party service that the agent is expected to read and could influence subsequent actions.