CYBERSECURITYTRACKER
TRACKING6,506 stories in this site build1,309 vulnerability news stories in this site build
Permanent story citation

Claude Cowork Flaw Could Let AI Agent Escape Its VM and Access Mac Files

This page keeps the story as Cybersecurity Tracker first published it. If the tracker later corrects it, the correction appears below the original and never replaces it.

Back to newsStory 3104

As cited

Copy frozen at (site build).

ai security

Claude Cowork Flaw Could Let AI Agent Escape Its VM and Access Mac Files

Researchers discovered a sandbox escape vulnerability in Anthropic's Claude Cowork that allows an AI agent to break out of its Linux VM and access files on the host macOS system. The flaw potentially affects approximately 500,000 macOS users running the software.

Why it matters: macOS users of Claude Cowork face risk of unauthorized file access on their systems; practitioners should patch or review use of this AI agent until Anthropic addresses the sandbox escape.

Source published
First seen by Cybersecurity Tracker

Source attribution

Correction

Correction recorded as of .

ai security

Claude Cowork Flaw Could Let AI Agent Escape Its VM and Access Mac Files

No summary had been written when this copy was frozen.

First seen by Cybersecurity Tracker

Source attribution

Correction

Correction recorded as of .

ai security

Claude Cowork Flaw Could Let AI Agent Escape Its VM and Access Mac Files

Cybersecurity researchers identified a sandbox escape vulnerability in Anthropic's Claude Cowork that allows artificial intelligence (AI) agents to break out of their Linux virtual machine environment and access files on macOS systems. The flaw potentially affects approximately 500,000 macOS users running the application. Accomplish AI disclosed the vulnerability to The Hacker News prior to public disclosure.

Why it matters: macOS users running Claude Cowork face unauthorized file access risks and should update immediately once a patch is available; security teams should assess whether this AI agent is deployed in their environments.

Source published
First seen by Cybersecurity Tracker

Source attribution

Correction

Correction recorded as of .

ai security

Claude Cowork Flaw Could Let AI Agent Escape Its VM and Access Mac Files

Cybersecurity researchers identified a sandbox escape vulnerability in Anthropic's Claude Cowork that allows artificial intelligence (AI) agents to break out of their Linux virtual machine environment and access files on macOS systems. The flaw potentially affects approximately 500,000 macOS users running the application. Accomplish AI disclosed the vulnerability to The Hacker News prior to public disclosure.

Why it matters: macOS users running Claude Cowork face unauthorized file access risks and should update immediately once a patch is available; security teams should assess whether this AI agent is deployed in their environments.

VendorsApple
Source published
First seen by Cybersecurity Tracker

Source attribution

Glossary