circle-1

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

• Third-party content exposure detected (high risk: 0.90). This skill instructs the agent to fetch and interact with user-generated Circle content via Membrane (e.g., the "membrane request CONNECTION_ID /path/to/endpoint" proxy and action-run flows) which exposes untrusted third-party posts/messages that the agent would read and could influence subsequent actions.