News

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

  • Matt Burgess--Wired
  • published date: 2026-08-05 23:30:00 UTC

Researchers at security firm Zenity found more than a dozen flaws in AI browsers—and managed to get OpenAI’s Atlas to make an unauthorized Amazon purchase.

OpenAIs Atlas webbrowser could have security protections bypassed and be tricked into spamming dozens of WhatsApp contacts or making unauthorized purchases on Amazon, according to new research presen… [+3696 chars]