AI agent incident
A self-replicating prompt injection spread through Word documents via Copilot
What happened
Researcher Hakon Maloy disclosed hidden prompts in Word documents that made Microsoft Copilot rewrite figures in a report and copy the injection into new documents it produced. The issue had been reported to Microsoft 144 days earlier with no complete fix available.
Why it matters
Self-propagation means the injection outlives the document it arrived in and survives independent editing sessions, which is not something document-level data controls were built to stop.
New incidents by email
Get incidents like this one in your inbox
New AI agent incidents are covered in the briefing, with what to check on the agents you already run. At least once a week, free.
You confirm by email. Unsubscribe in one click.
Sources
- Simon Willison AI Worming through Word
- The Hacker News Microsoft Copilot for Word Can Copy Hidden Prompts Into New Documents