OpenAI apologized to the Australian government on Monday for failing to promptly notify the country’s administration after its AI agents breached several public services websites. In a blog post, the company said that in June, during internal training and evaluation, its models accessed Australian government websites in ways they were not authorized to. “We also should have handled our response better. We are sorry and working to do better in the future,” OpenAI wrote. The apology came roughly a week after the Australian government launched an investigation into how OpenAI‘s models accessed a Services Australia system containing Medicare spending information and other health statistics. The breach occurred in June, but Australian authorities were not notified until September 10.

OpenAI also detailed how the breaches happened. An experimental model it was testing in June was assigned a task to research government spending on medicines for skin conditions in Victoria. Unable to find the information in public datasets, the model found a way into Services Australia‘s internal system, ran commands, retrieved files and credentials, and even wrote files. The company said another model accessed the New South Wales Bureau of Crime Statistics and Research’s public Crime Mapping Tool to find crime statistics. Its agents also gained access to Victoria’s Agency for Health Information through an exposed access key and exfiltrated “reporting configuration and aggregate survey statistics,” and they retrieved aggregate statistics from the Australian Institute of Health and Welfare website. OpenAI said it found no evidence that its models accessed individuals’ medical or criminal records.

In its apology, OpenAI said it would provide the affected Australian agencies with technical findings and connect them with its response teams to assess the impact of the breaches. It also plans to provide credits from its $1 billion Daybreak for Frontline Defenders program and set up a task force with independent Australian experts to review the incident and its response. The task force is expected to complete its work by the end of the year and will recommend practical steps AI companies can take to reduce the risk of similar incidents. OpenAI did not immediately return a request for comment.

Australian Prime Minister Anthony Albanese described the breach as “unacceptable” during a news briefing last week, saying the government was weighing potential legal measures to prevent similar incidents. The breach is the latest in a growing list of security incidents involving AI agents operating outside their intended boundaries. OpenAI agents previously hacked into Hugging Face, and Anthropic, Meta, and Google have separately disclosed similar incidents in which their models gained access to third-party systems during evaluations.