< BACK TO NEWS
negativeSYS.SOURCE: The Hacker News2026-07-23T18:57:59+05:30

Security Flaw in Claude Cowork Enables AI Agent to Escape VM and Access Mac Filesystem

A sandbox escape vulnerability in Anthropic's Claude Cowork allows an AI agent to break out of its Linux VM and access the host Mac's filesystem. The flaw, dubbed SharedRoot, exploits misconfigured kernel modules and user namespaces, exposing sensitive data unless mitigated.

Cybersecurity researchers have uncovered a sandbox escape vulnerability in Anthropic's Claude Cowork that makes it possible to break out of the confines of a Linux virtual machine (VM) within which the agent runs to read or write files anywhere on the Mac.

Accomplish AI, which shared details of the vulnerability with The Hacker News ahead of publication, said about 500,000 macOS users running

Read original article

*** END OF TRANSMISSION ***