Claude model builds exploits for multiple mainstream browsers and operating systems
Claude Model Builds Exploits Across Major Browsers & OSes
Anthropic said this week that an unreleased version of Claude found critical vulnerabilities in Chrome, Safari, Android, Windows and Linux and chained them into 5 usable exploit chains requiring little or no human interaction; all affected vendors have fixed them. The Chrome exploit chain combined four vulnerabilities to escape the browser sandbox; Anthropic said it reported 62 vulnerabilities to Google in total, all of which received CVE numbers and were fixed in Chrome 156. The Safari exploit chain bypassed the same-origin policy and could read browsing history, cookies and data from logged-in websites. The Android exploit chain extracted photos and other personal information on a locked Pixel 9. The Windows one was an out-of-bounds read in the kernel implementation of the transport protocol used by HTTP/3, remotely triggerable for denial of service. The Linux one was a zero-click remote code execution with root privileges, corresponding to CVE-2026-98432, fixed upstream and backported to each maintained stable kernel branch.
The article presents Anthropic's demonstration of the model chaining multiple vulnerabilities into usable exploit chains, and also includes security practitioners' assessment of the gap between proof of concept and real-world attacks.