retently

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

• Third-party content exposure detected (high risk: 0.80). The SKILL.md explicitly supports sending proxy requests to the Retently API via Membrane ("membrane request CONNECTION_ID /path/to/endpoint") and the integration is for managing Retently survey Responses (user-generated feedback), so the agent would fetch and act on untrusted third‑party content that could alter follow-up actions.