A single click mounted a covert, multistage attack against Copilot
Microsoft has fixed a vulnerability in its Copilot AI assistant that allowed hackers to pluck a host of sensitive user data with a single click on a legitimate URL.
Reported by Ars Technica AI. Good journalism, but verify key claims with the original source they cite.
Microsoft has fixed a vulnerability in its Copilot AI assistant that allowed hackers to pluck a host of sensitive user data with a single click on a legitimate URL.
TLDR
Microsoft has fixed a vulnerability in its Copilot AI assistant that allowed hackers to pluck a host of sensitive user data with a single click on a legitimate URL.