OpenAI says it accidentally hacked Hugging Face with a new AI system
Emma Roth
is a news writer who covers the streaming wars, consumer tech, crypto, social media, and much more. Previously, she was a writer and editor at MUO.
OpenAI says its AI models mistakenly breached open-source AI platform Hugging Face during internal testing. In a blog post on Tuesday, OpenAI writes that GPT-5.6 Sol and “an even more capable pre-release model” discovered vulnerabilities within their sandboxed testing environment, allowing them to gain access to the internet and target Hugging Face.
On July 16th, Hugging Face disclosed a security incident that it says was driven by “an autonomous AI agent system.” Hugging Face’s AI agents detected and stopped the breach, which OpenAI has now admitted occurred during an evaluation of its models’ cybersecurity capabilities. OpenAI says “all evidence suggests that the models were hyperfocused on finding a solution for ExploitGym,” a benchmark system that measures whether AI models can turn security vulnerabilities into exploits.
As part of efforts to complete the evaluation, the AI models gained access to the internet by exploiting a zero-day vulnerability in the sandboxed environment. From there, OpenAI says its models “inferred that Hugging Face potentially hosted models, datasets and solutions for ExploitGym,” and then “searched for and successfully found ways to gain access to secret information that it could use to cheat the evaluation:”
In one example, the model chained together multiple attack vectors, including using stolen credentials and zero-day vulnerabilities to find a remote code execution path on the Hugging Face servers.
But as serious as this incident is, OpenAI appears to be using the “unprecedented” attack as an opportunity to make its AI systems look good — especially as it competes with cybersecurity rivals, like Anthropic’s Mythos and Gemini Flash 3.5 Cyber. OpenAI’s blog post has a chart showing how GPT-5.6 Sol is getting better at sustaining multi-step cyber operations, and also encourages enterprise customers to sign up to access its “Cyber” security model.
OpenAI adds that it’s now working with Hugging Face to investigate the security incident, and will implement new controls within its research environment.
Follow topics and authors from this story to see more like this in your personalized homepage feed and to receive email updates.
- Emma Roth
Related Articles
Binding of Isaac developer removes AI music from Repentance Plus
Terrence O'Brien is the Verge’s weekend editor. He’s covered the tech industry for over 18 years and knows a thing or two about synths.The Binding of Isaac: Repentance Plus has spent the last few days getting...
The vibe-coding revolution is coming to all the gadgets
This is The Stepback, a weekly newsletter breaking down one essential story from the tech world. For more on the vibe-hacking of everything, follow David Pierce. The Stepback arrives in our subscribers’...
Nature:糖尿病大鼠成功恢复正常血糖!用电刺激迷走神经控糖
< img id="wx_img" src="https://www.qbitai.com/wp-content/uploads/imgs/qbitai-logo-1.png" width="400" height="400"> 2026-11-22 ...
A社数学家用Claude又证明另一千禧难题,逼出一份写了12年的940页纯人类手稿
< img id="wx_img" src="https://www.qbitai.com/wp-content/uploads/imgs/qbitai-logo-1.png" width="400" height="400"> 2026-11-22 ...
