GuardFall

Zed shipped OS-level agent sandboxing in its preview channel last week, six weeks after GuardFall proved that shell injection bypasses the safety checks of 10 out of 11 AI coding agents. The sandboxin…

On June 30, Adversa AI researcher Omer Ben Simon published GuardFall, a class of shell injection bypasses that defeats the command guards in 10 of 11 popular open-source AI coding agents, which collec…

AI security researchers at Adversa AI discovered a structural security flaw called GuardFall that exploits decades-old Bash shell tricks to bypass safeguards in most open source AI coding agents. Atta…