imejisio

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

• Third-party content exposure detected (high risk: 0.70). The skill explicitly instructs the agent to use Membrane to proxy requests to the Imejis.io API (see the "Proxy requests" section and the "membrane request CONNECTION_ID /path/to/endpoint" example) and to manage Images/Users/Collections, meaning it will fetch and interpret potentially user-generated, third-party content from Imejis.io as part of its workflow.