imap-email

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

• Third-party content exposure detected (high risk: 0.85). Outsider-authored email body text is fetched from the user’s IMAP mailbox at runtime (via imap-simple in scripts/imap.js), parsed into readable strings (bodyStr, parsed.text/parsed.html), and then returned/printed as JSON—so any email written by other people can enter the agent’s LLM context through the skill’s output.