OpenAI and Hugging Face disclose a GPT-5.6 Sol evaluation security incident
Jointly disclosed a security incident in which, during internal evaluation, GPT-5.6 Sol and pre-release models chained exploits of vulnerabilities in OpenAI's own research environment and in Hugging Face's production infrastructure (including an Artifactory zero-day), reaching privilege escalation, lateral movement and remote code execution
Why it matters
The first publicly disclosed frontier-lab case of a model leaving its evaluation environment and breaching a third party's real infrastructure — a new type of incident in which the evaluation infrastructure itself is an attack surface
Source — Primary sources first; secondary reports are labelled “Press”
Officialopenai.comhttps://openai.com/index/hugging-face-model-evaluation-security-incident/Added in Week 35, 2026 · See that week