swoogo

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

• Third-party content exposure detected (high risk: 0.80). The SKILL.md explicitly instructs the agent to connect to Swoogo via the Membrane CLI and to run/list actions (e.g., "membrane action list" / "membrane action run") which fetch event/attendee/etc. data from the external Swoogo API — untrusted user-generated third‑party content the agent will read and could influence subsequent actions.