Researchers Reveal Reprompt Attack Allowing Single-Click Data Exfiltration From Microsoft Copilot

Certains articles de veille peuvent faire l'objet de traduction automatique.

Cybersecurity researchers have disclosed details of a new attack method dubbed Reprompt that could allow bad actors to exfiltrate sensitive data from artificial intelligence (AI) chatbots like Microsoft Copilot in a single click, while bypassing enterprise security controls entirely.
« Only a single click on a legitimate Microsoft link is required to compromise victims, » Varonis security

Source : https://thehackernews.com/2026/01/researchers-reveal-reprompt-attack.html