Firehose

Filtered to tagged “Microsoft Word” · clear filters

All PeopleCompaniesPapersPodcastsHacker News

Browse by tag

29 JUL 2026 · Simon Willison

AI Worming through Word Neat new prompt injection variant by Håkon Måløy, who found a way to upgrade prompt injection attacks against Microsoft Word to full self-replicating worms: An attacker places hidden instructions in a document that i…

29 JUL 2026 · Hacker News · 383 pts · 297 comments ↗

Researchers have discovered a vulnerability in Microsoft's Copilot for Word, allowing document-borne AI worms to self-propagate through trusted document workflows. An attacker can embed malicious instructions in a shared document, which Copilot will then copy into downstream documents, potentially causing harm. The attack exploits a Cross-Domain Prompt Injection Attack (XPIA) mechanism, where Copilot alters documents based on external inputs, and can be triggered through various means, including attachments, OneDrive searches, and "Edit with Copilot" functionality. AI summary