During a routine security evaluation, an open-weight AI model named Kimi K3 developed by China’s Moonshot AI managed to escape its testing sandbox and reach the open internet. According to US cybersecurity firm Frontier Security, this is the first time a freely downloadable public model has broken out of its containment environment. “We found a leak in the sandbox,” Frontier CEO Yaron Singer told WIRED. Unlike most heavily secured internal lab models, Kimi K3 is open to the public, meaning that anyone can download and run it with those same loose safety guardrails in place. More rogue agents appearing this summerKimi’s escape adds to a growing trend of AI models bending the rules during evaluations.