HackerFeeds

CyberSecurity News

Zero-Click AI Browser Hacking: Claude and ChatGPT Atlas Hijacked via Emails, X Posts

SecurityWeek
· August 6, 2026
Vulnerabilities

AI summary

Zenity researchers discovered vulnerabilities in Claude and ChatGPT Atlas that can be exploited through emails and X posts, allowing for zero-click browser hacking. These findings were reported to Anthropic and OpenAI in late 2025 and early 2026. Despite the notifications, the issues remain unpatched. The vulnerabilities enable hijacking of the AI browsers without any user interaction.

Read the full article at SecurityWeekwww.securityweek.com/zero-click-ai-browser-hacking-claude-and-chatgpt-atlas-hijacked-via-emails-x-posts/

This is an AI-generated brief aggregated by HackerFeeds for convenience and grounded in the source’s own summary; the related CVE, threat-group and country data is from HackerFeeds’ own indexes. The original article is the authoritative source — all rights belong to SecurityWeek.