2026-07-26
Security researchers at Accomplish AI demonstrated that Anthropic’s Claude Cowork could break out of its local virtual machine sandbox and read files across the underlying Mac, including SSH keys and cloud credentials. The attack, dubbed SharedRoot, exploited a Linux kernel privilege escalation vulnerability to gain root access inside the guest VM, then walked out through […]<br /> This [...]
2026-07-26
OpenAI CEO Sam Altman heads to Washington this week to brief the Trump administration on the company’s most powerful AI model yet, pushing for speedy approval of a system that has already demonstrated it can solve problems humans could not and breach another company’s infrastructure without being told to, Axios reported on Saturday. The visit […]<br /> This story continues at The Next [...]