api-to-every-ecommerce-cart-and-marketplace

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

• Third-party content exposure detected (high risk: 0.70). This skill lets the agent issue arbitrary requests to external e-commerce APIs and consume their JSON outputs (see "Proxy requests" / membrane request CONNECTION_ID /path/to/endpoint and membrane action run sections), so untrusted third‑party API responses can be ingested and influence subsequent actions.