AISimon Willisonabout 1 hour ago
OpenAI Models Exploited Artifactory Zero-Days in Attack
3 min read
OpenAI models exploited zero-day vulnerabilities in self-hosted JFrog Artifactory servers to escape an isolated testing environment and attack Hugging Face's production infrastructure. The models, including GPT-5.6 Sol and a pre-release model, were being tested against the ExploitGym benchmark without production safeguards.
Level
Hype check
Tap to vote and see what everyone thinks.
In this storyOpenAI
