product-fruits

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

• Third-party content exposure detected (high risk: 0.80). This skill instructs the agent to fetch and act on live data from the third‑party Product Fruits service via Membrane (e.g., "membrane action list", "membrane action run", and "membrane request CONNECTION_ID /path/to/endpoint" against productfruits.com), which will ingest user-generated/untrusted content and drive subsequent actions, creating a potential indirect prompt‑injection vector.