OpenAI has disclosed another incident involving an AI agent accessing an Australian government system without permission, just over a week after a separate incident involving a Medicare statistics portal became public.
The original incident occurred on June 18, when an OpenAI agent accessed an Australian government Medicare statistics portal during an internal training exercise. The agent reportedly executed commands, retrieved internal files and credentials, accessed non-public statistics, and created files. OpenAI said the activity involved an internal-only model being tested in a controlled exercise.
Australian authorities said the agent accessed both public and non-public information but did not access patients’ medical records or personal Medicare information.
Further investigation later found that OpenAI agents had also accessed systems belonging to the Australian Institute of Health and Welfare, the Victorian Department of Health, and the NSW Bureau of Crime Statistics and Research. ABC reported that hundreds of agents attempted different methods over nearly a week to access data held by the Australian Institute of Health and Welfare.
OpenAI has now disclosed another incident involving an AI agent and the New South Wales National Parks and Wildlife Service. The company became aware of the activity on Tuesday and carried out a 48-hour review, concluding that the model did not retrieve any personal information.
According to OpenAI, the agent went beyond its intended use and accessed non-public fire statistics held by a New South Wales government agency. The company said it believes the incident occurred in June.
“After being made aware of this activity … we conducted an urgent internal technical and legal review to understand the nature of the activity against the research being carried out,” an OpenAI spokesperson said.
The NSW Department of Climate Change, Energy, the Environment and Water, which oversees the National Parks and Wildlife Service, is working with the state’s cybersecurity agency to investigate the incident. OpenAI also said it notified the Australian Signals Directorate on October 1 after completing its internal review.
The latest disclosure comes amid criticism over how quickly OpenAI notified Australian authorities about the earlier Medicare incident. Prime Minister Anthony Albanese said he had spoken with OpenAI CEO Sam Altman and expressed Australia’s concern about the incident and the delay in notification.
OpenAI discovered the Medicare breach on August 11 but informed the Australian government on September 10. The notification was reportedly sent in a five-paragraph message to a public Services Australia email address.
If this article helped you, please consider supporting our work. Every small contribution keeps Abijita.com independent and running.
Australian Greens MP Abigail Boyd also criticized the incident, arguing that government agencies should not have to rely on technology companies to identify and report cases where their AI systems gain unauthorized access to government systems.
OpenAI AI Agent Accesses Another Australian Government System Without Permission
