sent-two-way-messaging

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

• Third-party content exposure detected (medium risk: 0.30). The runtime workflow described is an inbound webhook/bot that subscribes to message.received events and reads the attacker-controlled inbound free-text field value.text (and mirrored conversation history), so outsider-authored message content directly enters the agent at runtime.