OpenAI reveals cyberattack caused by rogue AI agent was worse than initially reported | TAG24

All results for #PLACEHOLDER#

USA

2026-07-29 17:41:13

OpenAI reveals cyberattack caused by rogue AI agent was worse than initially reported

San Francisco, California - ChatGPT maker OpenAI has revealed that an autonomous AI agent that hacked a popular platform for computer programmers also attempted to breach four other companies during the incident.

OpenAI has shared concerning new details about the recent cyberattack caused by a rogue AI agent. © IMAGO / NurPhotoIn an update late Tuesday to a blog post detailing its probe into the incident, OpenAI said its AI agent also got into accounts on four "publicly-available services," though it did not name the companies.<br>The revelation broadens a cyber incident that OpenAI described as unprecedented and that began when two of its models hacked Hugging Face, a site developers use to store and share AI models and code.<br>OpenAI admitted last week that during testing, the models powering the agent broke out of their confined environment and connected to the internet to find ways to infiltrate Hugging Face.<br>In the company's update of the events leading to the hack, OpenAI said it found a handful of instances where the AI models came across login details that other companies had left exposed online, and used them to get into accounts on outside services.<br>In the Hugging Face episode, the models broke into four accounts across four different services, OpenAI said.<br>One served as a "staging path" – a kind of pit stop to route the agent's activity and cover its tracks – and another as a place to store data.<br>The remaining two were only looked at in a "read-only manner" and did not use them to help break into Hugging Face, OpenAI said.

OpenAI agent attempted to breach four other companies<br>The company said it was contacting the owners of the affected accounts and had "not seen evidence of broader impact to these providers or other accounts on their services".<br>OpenAI CEO Sam Altman said in an interview published Tuesday that the company had "paused" its own testing after the incident while it improved the security around its "sandboxing" – the process of isolating safety testing in a controlled environment.

The incident also triggered a petition signed by over 1,000 employees at cutting-edge AI companies, including Anthropic CEO Dario Amodei, calling on the US government to help slow down the release of the most advanced AI models.

Cover photo: IMAGO / NurPhoto

More on Tech:

Apple reaches major new market capitalization milestone<br>Humanoid robots manufactured abroad banned by Trump administration<br>US chip stocks slide on report of Chinese technological breakthrough