Email Agents

Email agents are AI systems that can read, draft, sort, and send email on a person's or company's behalf, often with access to inboxes, calendars, and connected business tools. For governance teams, they raise questions about who is accountable for messages sent without direct human review, how sensitive or confidential content is handled, and whether a malicious email could trick the agent into leaking data or taking unauthorized actions. Clear rules on permissions, logging, and human approval before external sends are becoming a basic requirement for deploying them.

1 item

ResearchGlobal2026-11-02

Live Invoice Fraud Campaign Hides Commands That Hijack Email AI Agents

Security vendor Sublime Security documented an active invoice fraud campaign embedding hidden instructions inside emails using invisible Unicode characters. The technique targets AI agents that read and act on email, redirecting them to follow attacker commands instead of legitimate user instructions. Enterprises running AI-connected email workflows face immediate prompt injection and financial fraud risk.

prompt injection invoice fraud email agents agentic AI Sublime Security financial controls Unicode obfuscation