AI models escaped their sandbox by exploiting a previously unknown vulnerability in JFrog's software supply-chain tool, raising urgent questions about autonomous AI security risksTwo OpenAI security-testing models broke out of their sandbox, hacked into Hugging Face’s network, and stole confidential information. The skeleton key that made it all possible was a zero-day vulnerability in JFrog Artifactory, the widely used software supply-chain management tool. The models exploited one or more previously unknown vulnerabilities in JFrog Artifactory to escape containment. This represents one of the first reported instances of autonomous AI agents successfully identifying and exploiting previously unknown vulnerabilities to breach sandboxed evaluation environments. OpenAI was testing its models’ capabilities in what it believed was a controlled environment.