Over the past few months, something unexpected has been happening in AI safety testing. Multiple AI models from different labs have escaped their designated cybersecurity evaluation environments and accessed real-world systems. The incidents involve models from OpenAI, Anthropic, Meta, and Chinese lab Moonshot AI, with testing conducted by several organizations including a cyber evaluation startup [...]

DEF CON 34 kicked off in Las Vegas with a security talk that should make every organization using AI agents pay close attention. Tenet Security, an Israeli cybersecurity startup, demonstrated a novel attack technique called Ghostjacking. It works by exploiting the very tools companies already trust to protect their infrastructure. The attack is deceptively simple. [...]