SPIN Unprocessed July 23, 2026 ai_technology cybersecurity
Claude Cowork Flaw Could Let AI Agent Escape Its VM and Access Mac Files
View original on thehackernews.comOverview
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
SpinGraph analysis pending — check back after processing.
Ask AI about this story
Opens with the SpinGraph .md URL and structured context — one click, prompt included.
More from The Hacker News
View all →- China-Nexus JadeProx Uses New TriBack Loader in Government and Healthcare Attacks
- Chaos Ransomware Uses msaRAT to Route C2 Traffic Through Headless Chrome and Edge
- ThreatsDay: Android Spyware, PLC Attacks, AI Image Prompt Injection + 12 More Stories
- Check Point Patches Exploited SmartConsole Flaw Allowing Full Admin Access
- Google Adds Selfie Video Recovery for Users Locked Out of Their Accounts
- How Synthetic Identity Fraud is Coming for Machine Identities
Markdown (.md) · JSON-LD schema (.json) · Machine-readable for AI & GEO