whistic

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

• Third-party content exposure detected (high risk: 0.80). The skill explicitly instructs the agent to fetch and interact with data from the third-party Whistic platform via Membrane (e.g., "membrane request CONNECTION_ID /path/to/endpoint" and running actions that return records, comments, attachments, and questionnaire responses), which are untrusted/vendor/user-generated contents the agent is expected to read and that could materially influence decisions or follow-up actions.