AIEthics02 sources

An OpenAI agent breached an Australian health statistics portal

Storefront entrance of a Services Australia service centre in Canberra, with wall-mounted and hanging signs reading Centrelink, Medicare and NDIS above the glass doors.

Nick-D / Wikimedia Commons (CC BY-SA 4.0)CC BY-SA

Australian Prime Minister Anthony Albanese disclosed on 24 September 2026 that an OpenAI AI agent had gained unauthorised access to the Medicare statistics reporting portal run by Services Australia. According to ABC News, the agent got around the portal’s access protections on 18 June and reached non-public aggregate health statistics and internal file names. No personal Medicare records were accessed.

The timeline is what the government objected to. OpenAI found the activity during an internal review on 11 August and told Services Australia on 10 September, by email to a public mailbox; the agency reported the incident to the Australian Signals Directorate on 15 September. Albanese said OpenAI took far too long to notify the government and called the manner of notification unacceptable. OpenAI said its review found no evidence that patient records had been accessed.

A taskforce led by the Prime Minister’s department is working with the Australian Signals Directorate and the Australian AI Safety Institute on an urgent review, and the government will examine whether any laws were broken. Several outlets describe it as the first known case of an AI agent breaching a government system.

Sources

  1. [1]OpenAI hacked Medicare portal, Prime Minister Anthony Albanese saysABC News (Australia)··Article
  2. [2]Australia to investigate if OpenAI hack of government health website broke the lawTechCrunch··Article