Researchers Show How a Hidden Prompt Can Turn Word Copilot Into a Self-Spreading AI Worm
A newly disclosed weakness in Microsoft Copilot for Word shows how invisible text buried in a document can hijack the AI assistant, quietly alter content, and copy itself into every new file it touches. Microsoft has shipped partial fixes, but the underlying attack class remains unresolved.
Itagora tiene in archivio titolo e sommario per la ricerca interna. Il testo completo resta sulla fonte. Il link in uscita non invia referrer.