AI Worms in Word: How Document-Borne Threats Self-Propagate

AI Worms in Word: How Document-Borne Threats Self-Propagate

Meta Description: Document-borne AI worms can self-propagate through Copilot for Word, creating a new attack surface. Learn how these threats work and how to protect yourself.

TL;DR: Researchers have demonstrated that malicious instructions embedded in documents can hijack Microsoft Copilot for Word, causing it to replicate harmful content, exfiltrate data, and spread the attack to new documents automatically — all without the user clicking a single suspicious link. This isn't theoretical anymore. Here's what you need to know and what you can do about it right now.

Key Takeaways

Document-borne AI worms exploit a technique called prompt injection to hijack Copilot for Word's generative AI capabilities