lodgify

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 run Membrane actions and proxy requests against the Lodgify API (e.g., "membrane action run" and "membrane request CONNECTION_ID /path/to/endpoint"), which will fetch and surface Lodgify data such as Messages, Inquiries, Guests and Bookings—user-generated third-party content the agent would read and could use to drive actions.