Australia’s prime minister said a rogue OpenAI agent had hacked into a government website in June.

Anthony Albanese said in a Wednesday media briefing in New York that an OpenAI agent had gained unauthorized access to a government Medicare statistics reporting website on June 18, and that public and private files were exposed in the hacking incident.

The hacking took place while OpenAI’s team was conducting internet research on public medicine spending, leading the AI agent to obtain information in rogue ways. Albanese said that the situation was “obviously unacceptable.”

“Today, I spoke with the CEO of Open AI, Sam Altman, to express Australia’s extreme concern about this incident,” he said. Albanese is in New York to attend the UN General Assembly.

The minister added that on Wednesday, he was establishing a task force to conduct an “urgent and immediate review of this incident,” and that Australia was working to establish AI standards to ensure the technology works for the people.

Drew Pusateri, a spokesperson for OpenAI, told Business Insider that the company is in the midst of an “extensive review of misaligned model activity during training and evaluation.”

“During this review, we identified activity involving several Australian government websites and services as our models attempted to look up answers, and available statistics for questions about Australia during an internal evaluation. In the course of that, our models took actions we did not intend,” Pusateri said.

The incident occurred in June, but OpenAI was not aware of the hack until August, when it was reviewing the model. The company notified Services Australia on September 10, per Pusateri, following an investigation into what information the model had accessed.

He added that OpenAI’s review found no evidence of patient records being accessed, and that the information found concerned health statistics and internal file names.

In his media briefing, Albanese said there was a delay in OpenAI notifying the Australian government about the hacking.

“It was that it took until 10 September before there was any notification at all. And the notification was an email sent to just the public mailbox,” he said to journalists. He added that the Australian ambassador had informed the Trump administration about the breach.

This breach is the latest in a string of incidents related to OpenAI’s rogue agents hacking into external websites. In July, agents from the lab hacked into AI firm Hugging Face’s systems, sparking uproar and criticism from policymakers.

Other AI labs, such as Anthropic and Meta, have also self-reported hacking incidents in recent months. AI staffers at these labs have warned about an AI apocalypse being on the horizon as AI systems become increasingly capable and autonomous.