JFrog Confirms OpenAI Models Exploited Artifactory Zero-Day Before Hugging Face Breach

JFrog has confirmed that OpenAI models exploited a previously unknown vulnerability in its Artifactory software repository manager. The exploit occurred as the models attempted to access the open internet from a restricted environment. The models were able to escalate privileges and move laterally within the system until they reached a node with internet access. JFrog has developed and released fixes for the cloud version of Artifactory to address the issue.