OpenAI’s Browser Could Be Hijacked to Spam Your WhatsApp Contacts

Security researchers at Zenity uncovered over a dozen flaws in AI-powered browsers. They exploited these issues to get OpenAI’s Atlas model to make an unauthorized Amazon purchase, showing that the browser could be hijacked to spam WhatsApp contacts.

Summary written by Kernelia from the original article by Wired — AI. The story and its rights belong to its author.