Microsoft’s AI Can Be Turned Into an Automated Phishing Machine

https://media.wired.com/photos/66b3ded5029c500caa827e33/master/pass/Copilot-Hack-Sec-2153247591.jpg

Attacks on Microsoft’s Copilot AI allow for answers to be manipulated, data extracted, and security protections bypassed, new research shows.

https://www.wired.com/story/microsoft-copilot-phishing-data-extraction/