AI Worming through Word: Hidden Instructions Enable Self-Replicating Attacks

Simon Willison · rss · 2026-07-30

Security researcher Håkon Måløy discovered a new prompt injection variant targeting Copilot in Microsoft Word, which can escalate into a self-replicating worm.

How it works:

The vulnerability was responsibly disclosed to Microsoft, but no full mitigation has been deployed after 144 days.

Original post →

More from Safety

Safety channel →