agentmail-cli

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

• Third-party content exposure detected (high risk: 0.90). The SKILL.md explicitly includes commands to retrieve and list inbox messages/threads (e.g., "agentmail inboxes:messages retrieve", "inboxes:threads retrieve") and to reply/forward/send emails, which means the agent will fetch and act on untrusted, user-generated email content that could contain instructions influencing subsequent actions.