AI Agent Security Faces a Claude Cowork Leak
The newest wake-up call in AI agent security does not look like a dramatic movie hack. It looks more like a normal productivity workflow, the kind where someone connects a folder, asks an AI coworker to help, and expects the tool to stay inside the lines. That is why the reported Claude Cowork vulnerability feels […]
Januscape Linux Vulnerability Threatens VM Isolation
A virtual machine is supposed to behave like a locked room inside a much larger building. Even when someone controls everything inside that room, the walls should prevent them from reaching the hallway, the control systems, or neighboring tenants. The newly disclosed Januscape Linux vulnerability challenges that basic promise by exposing a path from a […]