Anthropic's unreleased model builds working browser and kernel exploits [Oct 28 2026]
Anthropic says an unreleased internal research model chained bugs into five working exploits, including one-click remote code execution in Chrome on macOS and zero-click root on Linux servers running a multipath TCP listener. It says 62 CVEs it reported to Google have been assigned and patched as of Chrome 156, all rated critical or high, 13 of them sandbox escapes. On the Linux chain the model took 48 minutes to leak a kernel pointer and another five minutes to reach shell command execution, after what Anthropic calls "initial prompting". None of the exploits was seen in attacks. Separately…
The skinny
The skinny isn't ready yet — notes appear once the transcript is processed.