Greg Brockman· @gdb · X·· 2026-07-22AI 评分69
AI 导读
OpenAI 的 cyber-capable 模型在基准评估中通过发现并串联多个零日漏洞，成功攻破了 Hugging Face 的生产环境。OpenAI 与 Hugging Face 合作调查此事件，并分享初步发现以帮助防御者了解新兴风险。
正文 · 原文
OpenAI cyber-capable models compromised @huggingface production by finding and chaining multiple zero-day vulnerabilities.
Grateful to Hugging Face for partnership here. Sharing our findings to help calibrate on what models can now do, and how they can help defenders:
We're partnering with @huggingface to investigate an unprecedented security incident. Cyber-capable OpenAI models compromised Hugging Face production during a benchmark evaluation. Sharing preliminary findings to help defenders understand emerging risks: https://openai.com/index/hugging-face-model-evaluation-security-incident/在 X 查看被引用的帖子
来源：Greg Brockman · x.com