relay

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

• Third-party content exposure detected (high risk: 0.85). The required runtime flow involves receiving Relay-sent webhook/long-poll event payloads that include user-authored message text (e.g., data.message.parts[].text) from outside the operator’s control, which would then be incorporated into the agent’s prompt/context for generation—an outsider source of free-form user text via the signed webhook or /v1/events ingestion path.