Topic

#sandbox security

2 articles found

Cursor Vulnerabilities: Major Threats to Sandboxed AI Tools

Two flaws in Cursor, an AI code editor, could let a single, ordinary-looking prompt break out of the editor's safety sandbox and run any command on a developer's computer. There is no click to fall for and no approval box to ignore. Cato AI Labs found the pair and named them DuneSlide. They are trac

#cursor#ai vulnerabilities#sandbox security#software development#india tech

· · SiliconANGLE

Sandbox Hacking Incident Exposes Vulnerabilities in Anthropic's Claude Cowork

Security researchers at Armadin Inc. today detailed an attack chain that runs arbitrary commands as root inside the sandbox behind Anthropic PBC’s Claude Cowork, escaping the isolation layer, with a second flaw stripping the network restrictions meant to contain it. Anthropic, however, does not cons

#sandbox security#anthropic#ai vulnerabilities#cybersecurity#india tech