Australia Says an OpenAI Agent Hacked Into a Government Health Site
An AI agent made by OpenAI accessed a government health website in Australia without authorization. OpenAI discovered the breach in August but did not notify authorities until September. This incident is among several reported security breaches involving advanced AI systems from major companies, though some observers have questioned whether these incidents were presented as more serious than they actually were.
50 across the spectrum. Choose a side on the bar to jump to it.
National story. 86 articles from 55 sources. 50 are on the bar; 5 are international, entertainment or tech outlets, listed separately. Updated 25d ago.
Part of The 2026 hacks by AI agents and the calls to slow AI development
Left
13 sourcesOpenAI’s agent hacking Australia is a warning for governments everywhere
An OpenAI agent hacked Australia's Medicare portal, and the country's PM is furious
Australia says OpenAI agent breached government health data portal
Center
27 sourcesOpenAI breach of Australian government linked to wider AI hacking campaign
Why Australia chose the world's biggest political stage to reveal OpenAI hack
Right
10 sourcesOpenAI reveals more rogue AI incidents — attempted hacks of government, education websites
Report reveals yet more cases of OpenAI’s ‘rogue AI’ agents hacking websites—and suggests they may still have been active in recent weeks
OpenAI Claims Rogue AI Agent Hacked Australian Government Site, Prime Minister Warns of 'Legal Consequences'
OpenAI says its AI agent breached an Australian government website without authorization
Other outlets
International, entertainment and tech outlets, by their rating. Not counted in the bar above. How we count coverage
Left
8 articles‘This Situation Is Obviously Unacceptable’: Australian PM Displeased by OpenAI Agent Hacking His Country
Center
0 articlesNone
Right
0 articlesNone
The story so far
3 developments- Sep 18Security Researchers Hacked Into OpenAI Using Anthropic’s Claude
- Sep 18Researchers used Claude to hack OpenAI employees' ChatGPT accounts
- Sep 23Australia Says an OpenAI Agent Hacked Into a Government Health Site
Who covered each development
No new developments
Quiet for 26 daysLast development · Sep 23 — Australia Says an OpenAI Agent Hacked Into a Government Health Site