nicereply

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

• Third-party content exposure detected (high risk: 0.70). The SKILL.md explicitly instructs the agent to fetch data from the Nicereply API via Membrane (e.g., "membrane request CONNECTION_ID /path/to/endpoint" and running actions that return survey data), which exposes user-generated customer survey content that the agent is expected to read and could materially influence subsequent actions.