qualiobee

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

• Third-party content exposure detected (high risk: 0.80). The skill instructs the agent to fetch and act on data from the third‑party Qualiobee API via the Membrane CLI (e.g., "membrane request CONNECTION_ID /path/to/endpoint" and action list/run commands), which returns user-generated customer feedback that the agent is expected to read and could influence subsequent actions.