Back to News
AI
OpenAI’s Browser Could Be Hijacked to Spam Your WhatsApp Contacts
Wired — AI·August 5, 2026·1 min read
AI Summary
Researchers at Zenity identified multiple vulnerabilities in AI browsers, including OpenAI’s Atlas, which could lead to unauthorized actions such as spamming WhatsApp contacts and making purchases on Amazon. These security flaws raise concerns about the safety of AI-driven web browsing tools.
From the source
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.
The full text couldn't be loaded here (the source may require a subscription).
View original at Wired — AIKeep reading
Wall Street: Google DeepMind's reorganization penalizes Alphabet's stocklerevenu.com · 1h agoThe video is generated by artificial intelligence and does not document military convoys heading towards the Syrian-Iraqi borderverify-sy.com · 1h agoConfidence the key to our artificial intelligence future - Trending Now Sustainable Constructionsustainableconstruction-now.com · 1h agoOpenAI developer warns the "tireless eagle eyes of a million models" are coming for your exposed API keys and crypto walletsThe Decoder · 1h ago
Was this useful?