delighted

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

• Third-party content exposure detected (high risk: 0.80). The skill explicitly proxies requests to the Delighted API via Membrane (see "membrane request CONNECTION_ID /path/to/endpoint" and the Survey/Survey Response/Person actions), which fetches user-generated survey data from a third-party service that the agent is expected to read and could materially influence subsequent actions.