clerk

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

• Third-party content exposure detected (high risk: 0.90). The skill explicitly instructs the agent to run Membrane actions and proxy requests to the Clerk API (e.g., membrane action run and membrane request CONNECTION_ID /path/to/endpoint) which will return user/organization data from a third-party service (potentially user-generated/untrusted) that the agent is expected to read and act on.