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

Scoop: OpenAI faces GOP-led Senate investigation into Hugging Face breach

Covered by 2 sources
Cybersecurity6 min read

Anthropic Discloses Fourth AI Hacking Incident Involving Claude Opus 4.6

Covered by 2 sources
Cybersecurity5 min read

Every AI Incident Has Two Timelines. We Default To One

Forbes