Microsoft Copilot for Word Can Copy Hidden Prompts Into New Documents
Summary
Hidden instructions embedded in Word documents can trick Microsoft 365 Copilot (an AI assistant for Microsoft Office) into modifying data, like changing financial figures, and then copying those hidden instructions into newly generated documents. The researcher who discovered this technique reported it to Microsoft 144 days before publishing, and while Microsoft deployed two mitigations (blocking the original prompt wording and upgrading to GPT-5.5), the vulnerability class remained exploitable even after the updates.
Solution / Mitigation
Microsoft deployed two mitigations: the first blocked the original prompt wording, and the second upgraded the underlying model to GPT-5.5. Additionally, the researcher recommends treating external documents as untrusted, reviewing attached documents before starting a Copilot generation or edit operation, and checking Copilot-generated or edited files before reuse or sharing. Microsoft also notes that jailbreak and cross-prompt injection attack classifiers help block high-risk prompts, and Defender for Office 365 adds mail-flow inspection for inbound email.
Classification
Affected Vendors
Related Issues
CVE-2024-27444: langchain_experimental (aka LangChain Experimental) in LangChain before 0.1.8 allows an attacker to bypass the CVE-2023-
CVE-2026-30308: In its design for automatic terminal command execution, HAI Build Code Generator offers two options: Execute safe comman
Original source: https://thehackernews.com/2026/07/microsoft-copilot-for-word-can-copy.html
First tracked: July 30, 2026 at 02:01 PM
Classified by LLM (prompt v3) · confidence: 92%