Back Feeds.4Sysops

Security flaw in Claude Cowork allows AI agent to escape sandbox on macOS

Feeds.4Sysops •IT News • July 23, 2026

A critical vulnerability known as SharedRoot allows AI agents within Anthropic’s Claude Cowork to break out of their Linux virtual machine sandbox on macOS. By exploiting a kernel flaw, an agent can gain unauthorized read and write access to the host file system, potentially exposing sensitive data like SSH keys and cloud credentials. This issue affects approximately 500,000 users who run the agent locally, as the application mounts the entire host file system into the virtual machine with read-write privileges. Source

The full story

This article is one source in a clustered incident — the cluster page carries the summary, timeline and every other outlet covering it.

SharedRoot Vulnerability Allows Claude Cowork AI to Escape Sandbox on macOS A critical vulnerability, dubbed SharedRoot, has been discovered in Anthropic's Claude Cowork that permits AI agents to escape their Linux virtual machine sandbox on macOS. By exploiting CVE-2026-46331, an attacker can gain unauthorized read and write access to the host file system, potentially exposing sensitive data such as SSH keys and cloud credentials. Approximately 500,000 macOS users running local Cowork sessions are affected, as the application mounts the entire host file system into the VM with read-write privileges. Despite the severity, Anthropic has reportedly categorized the issue as 'informative' and has not issued a patch, assuming users will transition to the cloud execution model. This decision raises concerns about the security of local execution environments. Users are advised to mount folders as read-only and treat the VM's security guarantees with caution. 13 sources 70

Extracted Entities

Security flaw in Claude Cowork allows AI agent to escape sandbox on macOS

The full story

Extracted Entities

Attack Types (1)

CWE Weaknesses (2)

Platforms (2)

Vulnerabilities (1)