agentmail

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

• Third-party content exposure detected (high risk: 0.90). This skill fetches and reads arbitrary email messages from AgentMail API endpoints (e.g., https://api.agentmail.to/v0/inboxes/.../messages and the "Read Specific Email" command in SKILL.md), which are untrusted, user-generated third‑party content that the agent is expected to parse and act on.