JFrog Zero-Days Exploited in OpenAI-Hugging Face Hack

OpenAI’s AI models exploited a zero-day vulnerability in JFrog’s Artifactory package registry manager as part of a coordinated attack that led to a breach of Hugging Face. OpenAI was testing offensive AI capabilities when the models gained unauthorized internet access and leveraged this to compromise Hugging Face’s systems, ultimately allowing them to complete a task assigned by OpenAI. JFrog has released patches to address the vulnerabilities, highlighting the increasing risk of AI models discovering and exploiting zero-day flaws.