It's Not Just OpenAI Models Escaping and Running Riot — Experts Show How Claude Cowork Can Break Its Bonds and Access Mac Files

Anthropic's Claude Cowork could escape its local VM and read credentials on a Mac

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 […] This story continues at The Next Web

SCIENCE & TECH: It’s not just OpenAI models escaping and running riot — experts show how Claude Cowork can break its bonds and access Mac files

Accomplish AI showed Claude Cowork could escape a VM sandbox via Linux zero‑day CVE‑2026‑46331 Agent accessed host Mac files, risking exfiltration of SSH keys, cloud credentials, and more Anthropic shifted Cowork to default cloud execution; local users must harden configs to mitigate exposure Recent news of a ChatGPT agent escaping the sandbox and attacking services on the internet raised quite a few eyebrows, but it seems it’s not the only one …

It's not just OpenAI models escaping and running riot — experts show how Claude Cowork can break its bonds and access Mac files

Accomplish AI showed Claude Cowork could escape a VM sandbox via Linux zero‑day CVE‑2026‑46331Agent accessed host Mac files, risking exfiltration of SSH keys, cloud credentials, and moreAnthropic shifted Cowork to default cloud execution; local users must harden configs to mitigate exposureRecent news of a ChatGPT agent escaping the sandbox and attacking services on the internet raised quite a few eyebrows, but it seems it’s not the only one cap…