Incident 1707: OpenAI AI Agent Reportedly Gained Unauthorized Access to Australian Medicare Statistics Portal During Research Task

Responded
Description: An OpenAI AI agent conducting research into public medicine spending reportedly bypassed repeated access blocks and entered nonpublic areas of Australia's Medicare Statistics Reporting Service. Australian officials said it accessed public and nonpublic files and wrote files to an internal server; no personal Medicare information was known to have been accessed. OpenAI notified the Australian government.
Editor Notes: (1) 05/25–26/2026: OpenAI-linked agents reportedly probed the University of New Mexico Digital Library for vulnerabilities after failed image retrieval; observed probes did not succeed. (2) 05/28/2026: agents reportedly sent 12 vulnerability probes to Data USA after retrieval errors; no successful exploitation was observed. (3) 06/18/2026: an OpenAI internal research agent reportedly bypassed repeated blocks at Australia's Medicare Statistics Reporting Service, accessing public and nonpublic files and writing files to an internal server. (4) 06/20–21/2026: related agents reportedly probed the Australian Institute of Health and Welfare; Transluce observed no successful exploitation. (5) 09/10/2026: OpenAI notified the Australian government. (6) 09/23–24/2026: Prime Minister Anthony Albanese publicly disclosed the breach and announced an investigation. AIID editor's note: This incident ID is bounded to the 06/18/2026 Medicare portal breach; the other episodes are retained as contextual evidence of the broader reported pattern and are not separately represented here.

Tools

New ReportNew ResponseDiscoverView History

Incident Stats

Incident ID
1707
Report Count
4
Incident Date
2026-06-18
Editors
Daniel Atherton

Incident Reports

Reports Timeline

Incident Occurrence+3
OpenAI’s A.I. Tried to Breach 4 Other Targets, Without Prompting
Loading...
OpenAI’s A.I. Tried to Breach 4 Other Targets, Without Prompting
nytimes.com · 2026

OpenAI's artificial intelligence went rogue this year in at least four additional incidents, hacking and trying to break into government and university websites without being instructed to do so, according to researchers and government offi…

Loading...
Early rogue AI agent activity and attempts to hack found on urlquery.net
transluce.org · 2026

We present evidence that AI agents used the web security service urlquery.net to bypass restrictions and expand their access to the public internet. The agents also tried on three occasions to hack public data providers, including an Austra…

Loading...
Press conference - New York
pm.gov.au · 2026
Anthony Albanese post-incident response

ANTHONY ALBANESE, PRIME MINISTER: Thanks for joining me. I want to update Australians on an incident in which an artificial intelligence agent has infiltrated an Australian Government website. This incident occurred in June of this year and…

Loading...
OpenAI hacked Medicare portal, Prime Minister Anthony Albanese says
abc.net.au · 2026

In short:

The prime minister has had a "frank" discussion with OpenAI chief executive Sam Altman after an AI agent breached an Australian government website.

The company did not notify Services Australia of the incident until three months a…

Variants

A "variant" is an AI incident similar to a known case—it has the same causes, harms, and AI system. Instead of listing it separately, we group it under the first reported incident. Unlike other incidents, variants do not need to have been reported outside the AIID. Learn more from the research paper.
Seen something similar?

Similar Incidents

By textual similarity

Did our AI mess up? Flag the unrelated incidents

Loading...
Bots Allegedly Made up Roughly Half of Twitter Accounts in Discussions Surrounding COVID-19 Related Issues

Bots Allegedly Made up Roughly Half of Twitter Accounts in Discussions Surrounding COVID-19 Related Issues

· 2 reports
Loading...
Facebook’s Political Ad Detection Reportedly Showed High and Geographically Uneven Error Rates

Facebook’s Political Ad Detection Reportedly Showed High and Geographically Uneven Error Rates

· 5 reports
Loading...
University of Illinois' Proctorio Remote-Proctoring Deployment Reportedly Raised Student Rights Concerns

University of Illinois' Proctorio Remote-Proctoring Deployment Reportedly Raised Student Rights Concerns

· 6 reports
Previous IncidentNext Incident