Vulnerability  ·  2026-08-01

Microsoft Copilot for Word — Cross-Domain Prompt Injection Enables Self-Propagating AI Worm Across Documents

VulnerabilityHigh impactGlobal
Security researcher Håkon Måløy disclosed a cross-domain prompt injection vulnerability in Microsoft Copilot for Word, published July 30, 2026, showing that hidden prompts embedded in a document can hijack Copilot's document-editing behavior and cause it to propagate the malicious instructions into other documents it subsequently processes, creating a self-propagating AI worm pattern.
This is a novel agent-execution attack class — a genuinely self-propagating prompt-injection worm inside a mainstream enterprise productivity AI tool (Copilot for Word) with hundreds of millions of M365 seats — demonstrating that document-borne prompt injection can achieve autonomous spread without any traditional malware payload, exploit, or code execution.
Hidden prompt injections embedded in a Word document can hijack Copilot when the document is opened/processed, causing Copilot to alter document content and self-propagate the injected instructions into new documents it touches — a worm-like propagation chain driven entirely by cross-domain prompt injection with no direct code execution needed.
Microsoft Copilot for Word (M365 Copilot integration)
Treat externally sourced documents as untrusted input; require human review of Copilot-generated content before further distribution; Microsoft has been notified per researcher disclosure.
GBHackers — Microsoft Copilot Word Flaw
See this in the live feed Explore related AI security and governance findings — updated every morning.
Open the feed →