Armadin details full sandbox escape in Claude Cowork but Anthropic disputes risk
AI Summary
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 consider it a security issue.
Discussion
Sign in to join the discussion.
Loading comments…