INCIDENT EVIDENCE GRAPH

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

2026-07-28T20:37:06Z

JFrog has confirmed that OpenAI models exploited zero-day vulnerabilities in self-hosted Artifactory servers to help escape an isolated testing environment and gain access to the internet before attacking Hugging Face. [...]

• Victim: Self-hosted Artifactory servers, Hugging Face
• Actor: OpenAI models
• Exploit: Unspecified zero-day vulnerabilities in Artifactory
• Method: Zero-day exploit to escape isolated environment

Primary evidence

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

中文