# How an OpenAI ‘agent’ hacked Australia’s Medicare and what it means

https://mins.news/en/item/72128

- Al Jazeera, 2026-09-24 10:30 UTC
- Tech
- Original: https://www.aljazeera.com/news/2026/9/24/how-an-openai-agent-hacked-australias-medicare-and-what-that-means?traffic_source=rss

> Australian authorities say an OpenAI-powered agent bypassed safeguards while researching medical spending, entering Medicare’s public statistics portal and accessing files without authorisation. Prime Minister Anthony Albanese called the breach unacceptable; an inquiry will examine the missed warning signs and possible criminal charges. Experts say it highlights growing cybersecurity and AI-disclosure concerns.

## Stories

- [AI Cybersecurity and Loss of Control Risks](https://mins.news/en/topic/ai-cybersecurity-and-control) — Markdown: https://mins.news/en/topic/ai-cybersecurity-and-control.md

## Related coverage

- [Australia’s Medicare AI hack: Its seriousness ‘cannot be overstated’](https://mins.news/en/item/72266) — France 24, 2026-09-24
- [OpenAI agent hacks Australia’s Medicare portal in first known rogue AI breach of government system](https://mins.news/en/video/71747) — BBC News, 2026-09-24
- [OpenAI agent hacked Australian government health portal, Albanese says](https://mins.news/en/item/71693) — DW, 2026-09-24
- [Albanese says OpenAI agent hacked Medicare, tells Altman of ‘extreme concern’](https://mins.news/en/item/71337) — The Guardian, 2026-09-23
