The report under the headline says the agents tried three times, and that none of the attempts it found appear to have got in.
“AI agents linked to OpenAI carried out what researchers call the first reported instance of agents hacking a government, attempting to compromise the Australian Institute of Health and Welfare's public data site; ABC News headlined it the 'first' government hack by autonomous AI.”
Transluce researchers (report 'Early rogue AI agent activity and attempts to hack found on urlquery.net'); amplified by ABC News, 23 September 2026
Recorded 25 September 2026. Our ruling means: literally true, materially misleading.
None of the hacking attempts we identified appear to have succeeded, though the public artifacts we analyzed are incomplete and we cannot rule out successful attempts through private scans or means other than urlquery.net.
Agents working on a pharmaceutical-data task probed for a vulnerability and retrieved a public file from a pre-production server after bot protection blocked the main site.
We classified 6,467 reports as containing significant evidence of agent-like activity, based on distinctive task-specific programs, task-linked exploit probes, or exact connections to known activity.
Our initial review suggests that much of the activity described in Transluce's report overlaps with cases at varying stages of investigation in our ongoing review of misaligned model activity
It follows revelations announced by Prime Minister Anthony Albanese this morning that OpenAI's AI agents had also accessed non-public Medicare health statistics held by Services Australia.
These two near-simultaneous incidents have not yet been publicly connected, however two sources with knowledge of the government's investigations said they believe they are.
An OpenAI spokesperson confirmed the company’s models “took actions we did not intend” and that the accessed material “included aggregate health statistics and internal file names.”
Marles confirmed that the agent’s interactions with three other government websites – the Australian Institute of Health and Welfare (AIHW), the Victorian Department of Health and the NSW Bureau of Crime Statistics and Research – were “entirely normal” and involved only publicly available information.
First membership: 30 days free, then A$89 a year. One introductory trial per customer. Card required; renews annually until cancelled. Cancel before the trial ends to avoid the first charge.
Free · one story a night
Don't take the AI industry's word for it.
“AI is dramatically accelerating AI research at Anthropic right now, roughly doubling the pace of capabilities progress.”
TRUE, BUTLab Not FieldAjeya Cotra on Planned Obsolescence, reading METR's assessment and Anthropic's S-1 statement that it may imminently meet its own threshold
That's the latest lead check. One a day, receipts attached, in your inbox before someone repeats it at you. Free.
No spam. Unsubscribe in one click. Receipts or it didn't happen.
Pranjal Gupta writes every check himself. Former enterprise architect, from the implementation side. Not a team of anonymous raters.
