Cybersecurity3 min reading time

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

The Next Web
Read full post
Security researchers at Accomplish AI discovered that Anthropic's Claude Cowork could escape its local Linux VM sandbox on macOS by exploiting a kernel vulnerability, allowing access to sensitive host files. The flaw involved a privilege escalation (CVE-2026-46331) and writable filesystem sharing, exposing about 500,000 users before mitigation. Anthropic shifted to cloud execution by default to avoid this local escape risk, but local users must apply strict configurations to remain secure.

More in Cybersecurity

Cybersecurity10 min read

Anthropic Details Disrupted Claude Misuse Across Seven Harm Areas

Covered by 4 sources
Cybersecurity4 min read

Anthropic blocks 'malicious use' of AI that could develop biological weapons

BBC
Cybersecurity4 min read

Sam Altman met with top power utilities about securing the electrical grid. He offered one possible solution: OpenAI's cyber services.

Covered by 2 sources