// ChatgptHIGH
Zenity researchers disclosed two zero-click browser hacking techniques targeting ChatGPT Atlas in Chrome and other AI assistants. The vulnerabilities, reported to OpenAI in late 2025 and early 2026, remain unpatched and can enable account takeovers, phishing attacks, and unauthorized actions like Amazon purchases through malicious links in emails and social media posts.
- Zero-Click AI Browser Hacking: Claude and ChatGPT Atlas Hijacked(opens in a new tab)
- Zero-Click AI Browser Hacking: Claude and ChatGPT Atlas Hijacked(opens in a new tab)
- Cybersecurity News Review - Week 32 (2026)(opens in a new tab)
- Claude in Chrome Exploit Lets Attackers Steal Gmail Codes and Ta(opens in a new tab)
// Get alerts for Chatgpt