mailbox

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

• Third-party content exposure detected (high risk: 0.85). The required runtime workflow is the mailbox “check”/“wait” path that drains inbox/*.md files and then the agent reads/ingests the message body (outsider-authored content) into its LLM context; the body is free-form Markdown handoff text written by other agents.