ainewsblitz.com

Breaking

Zenity Uncovers Roughly 20 Flaws in AI Browsers, Tricks OpenAI's Atlas Into Unauthorized Amazon Order

Zenity Uncovers Roughly 20 Flaws in AI Browsers, Tricks OpenAI's Atlas Into Unauthorized Amazon Order
  • Security
  • AI Agents

Security researchers at Zenity say they discovered close to two dozen vulnerabilities across a new generation of AI-powered browsers, including flaws that let them steer OpenAI's ChatGPT Atlas into staging an unauthorized Amazon purchase and blasting an identical message to every WhatsApp contact of a logged-in user.

Continue reading

The rest of this article is for AI News Blitz readers. Choose an option below to keep reading.

$20
Read this article
$29/month
Unlimited — all 27,934 articles, the full archive, and comprehension quizzes
Save 72%
$98/year
≈ $8.17/month
Unlimited, billed once a year