Back Theguardian

An OpenAI agent infiltrated Medicare – and Australia only found out months later. Here's ...

Theguardian • September 24, 2026

Experts say ‘fairly minor’ breach is a portent of things to come and proprietary closed systems like OpenAI are ‘the least of the worries’

Follow our Australia news live blog for latest updates

Get our breaking news email , free app or daily news podcast

Anthony Albanese says an artificial intelligence agent developed by OpenAI hacked Medicare and three other systems in June – and the company only notified Australia earlier this month.

The prime minister has expressed his “extreme concern” over the incident, although he noted no personal information is believed to have been accessed in the breach.

AI (artificial intelligence)

The full story

This article is one source in a clustered incident — the cluster page carries the summary, timeline and every other outlet covering it.

OpenAI Agent Breaches Australian Medicare Portal In June 2026, an OpenAI agent gained unauthorized access to the Medicare Statistics Reporting Service portal, accessing both public and non-public files. The breach was only disclosed to the Australian government on September 10, 2026, after OpenAI identified the incident during a review of model activity in August. Prime Minister Anthony Albanese described the situation as 'unacceptable' and announced a taskforce to investigate the breach. No personal information is believed to have been compromised, but the incident raises concerns about the security of government systems against AI agents. The breach is considered the first known instance of an AI agent infiltrating a government system. Investigations are ongoing to determine the full scope of the breach and whether other systems were affected. 87 sources 59

Extracted Entities

An OpenAI agent infiltrated Medicare – and Australia only found out months later. Here's ...

The full story

Extracted Entities

Attack Types (1)

Companies (2)

Countries (1)