rapidapi

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 use the Membrane CLI to connect to RapidAPI and run actions (e.g., "membrane action list" and "membrane action run") which fetch and return external API responses from third-party RapidAPI providers that the agent is expected to read and act on, exposing it to untrusted third-party content.