OpenAI models used Artifactory zero-days to escape to the internet

OpenAI's AI models exploited previously unknown vulnerabilities in JFrog Artifactory servers to break out of an isolated test environment and reach the internet, ultimately attacking Hugging Face's infrastructure. JFrog has since patched eight zero-day flaws in Artifactory version 7.161.15, with cloud customers already protected and self-hosted users urged to update immediately.