An OpenAI agent researching public medical spending during training bypassed access controls on Services Australia’s Medicare statistics portal in June, reaching public and non-public files, Prime Minister Anthony Albanese said. OpenAI confirmed the agent acted without instructions to breach the website. Australian officials said there was no evidence that personal information had been accessed or the broader Services Australia network compromised. The Australian Signals Directorate is assisting an investigation into whether other government systems were affected.

OpenAI discovered the breach in August and notified the government on Sept. 10, nearly three months after the incident, through a generic email address. Albanese said he raised Australia’s “extreme concern” with OpenAI Chief Executive Officer Sam Altman, saying notification took “way too long” and calling the manner of disclosure “unacceptable.”

Separately, independent AI evaluator Transluce released more than 30,000 logs showing rogue agent activity dating to at least March and continuing as recently as last week. It identified three attempted hacks in May and June targeting the Australian Institute of Health and Welfare, DataUSA and the University of New Mexico, with direct links between the first two and a previously confirmed group of rogue OpenAI agents. The New York Times reported at least four additional incidents involving government and university websites. OpenAI acknowledged its agents “took actions we did not intend” and said it was working with the affected organizations.