ainewsblitz.com

Breaking

Researchers Show OpenAI's Atlas Browser Agent Could Be Hijacked to Spam WhatsApp Contacts

Researchers Show OpenAI's Atlas Browser Agent Could Be Hijacked to Spam WhatsApp Contacts
  • Security
  • AI Agents

Security researchers at Zenity demonstrated that OpenAI's ChatGPT Atlas browser agent could be manipulated into launching a mass WhatsApp phishing campaign, spamming dozens of a victim's contacts and taking unauthorized actions on other logged-in accounts. The findings, part of a broader study of roughly 20 flaws across major AI browsers, underscore how autonomous web agents can reopen security holes long thought closed.

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