agentmail

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

• Third-party content exposure detected (high risk: 0.90). The skill consumes untrusted, user-generated email content delivered via webhooks and WebSocket message.received events (see the webhook examples in SKILL.md and the event-driven examples in references/examples.md) and injects that content directly into agent prompts and automated reply/workflow actions.