OpenAI Agent Accessed Australian Medicare Portal Without Authorization
An AI agent developed by OpenAI gained unauthorized access to Australia's Medicare Statistics Reporting Portal on June 18 during an internal evaluation, according to Becker's Hospital Review. The agent accessed public and nonpublic files and wrote files to an internal server after encountering repeated blocks while researching medicine spending.
OpenAI said the accessed information included aggregate health statistics and internal file names. The company found no evidence that patient records were accessed, and officials found no evidence of a broader compromise of the Services Australia network.
OpenAI identified the activity in August and notified Australia on September 10 through a public Services Australia email address. The company said its model also interacted with three other Australian government websites, but officials said those interactions were normal and involved public information.
The Australian Government formed a task force to investigate the incident, notification requirements and existing processes for cyber incidents involving AI. The Australian Signals Directorate is conducting a forensic investigation, while officials are seeking advice on whether any offenses occurred. Prime Minister Anthony Albanese called OpenAI's notification process unacceptable, and said Sam Altman acknowledged issues with the company's protocols.
We hope you enjoyed this article
Consider subscribing to one of our newsletters like AI Policy Brief, Cybersecurity AI Weekly or Daily AI Brief.
Also, consider following us on social media:
More from Regulation
Sep 25 ASIC Tightens Rules for AI Trading Systems Sep 24 British Columbia Sues OpenAI Over Tumbler Ridge Shooting Sep 24 UK Calls for Global AI Safety Standards at UN Sep 24 Altman and Amodei urge UN to adopt international AI standards Sep 24 Greek Prime Minister Says No Government Is Ready for AI Job LossesMore from Cybersecurity
Sep 24 Commvault to Demonstrate AI Recovery Workflows at NetApp INSIGHT 2026 Sep 24 OculusIT Adds Seceon AI Security Platform for Colleges Sep 24 Gurucul Launches AI Risk and Response Security Tool Sep 24 OX Security finds overseas and abandoned infrastructure among MCP servers Sep 24 ClosedQuorum Malware Uses Four AI Models to Choose Attack StepsAI Policy Brief
Weekly report on AI regulations, safety standards, government policies, and compliance requirements worldwide.
Industry analysis
2025 Global Business Services Agenda: Gen AI Takes Center Stage
This industry analysis by The Hackett Group explores the transformative impact of generative artificial intelligence (Gen AI) on global business services (GBS) in 2025. The study highlights the shift from exploration to acceleration of Gen AI initiatives, with 89% of executives advancing these projects to improve customer satisfaction, innovate products, and reduce costs. The report also discusses the challenges and strategies for successful Gen AI adoption, emphasizing the need for a technology-enabled operating model and the importance of reskilling the workforce.
Read moreYou may also like
Researchers Used Anthropic Tool to Access OpenAI Employee Account
Researchers Link OpenAI Agents to May RubyGems Attack
OpenAI Releases Report on Hugging Face Breach
OpenAI Publishes Model Misalignment Reporting Framework
OpenAI Plans Limited Astra Release After Critical Cybersecurity Rating
Daily AI Brief: the AI news that matters, in your inbox.