Researcher demonstrates self-propagating AI worm in Microsoft Copilot for Word
Hakon Maloy says hidden prompts can alter reports and copy themselves into documents after two Microsoft mitigation attempts.
By Ryan Merket · Published
Primary source: En Klype Salt
Why it matters
The proof of concept shows how ordinary documents can carry persistent AI instructions that corrupt trusted business records and spread through routine collaboration.
Hakon Maloy, a Norwegian AI researcher, publicly disclosed a self-propagating prompt-injection attack on July 28th that can turn documents edited or generated by Microsoft Copilot for Word into carriers for further attacks.…
When you purchase through links in our articles, we may earn a small commission. This doesn’t affect our editorial independence.