geoapify

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

• Third-party content exposure detected (high risk: 0.80). The skill calls the public Geoapify APIs (via Membrane commands like membrane action run and membrane request) to fetch place details, geocoding/search results and other external data that the agent is expected to read and act on, exposing it to untrusted third-party content from the open web.