agent-email-inbox

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

• Third-party content exposure detected (high risk: 0.95). The required runtime workflow fetches outsider-authored email body text (from Resend’s resend.emails.receiving.get(...) for an email.received webhook) and then constructs a free-text message including ${email.body} / ${emailContent.text||emailContent.html} that is sent into the agent LLM context via processEmailForAgent → agent.processEmail(...) / sendToAgent(message).