agentmail

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

• Third-party content exposure detected (high risk: 1.00). This skill explicitly ingests external, user-generated emails via its "Real-time Events" webhooks (and inbox polling scripts like scripts/check_inbox.py), which are untrusted third‑party content the agent is expected to read/interpret and thus can enable indirect prompt injection.