For months, OpenAI’s agent swarms have been attacking online databases to find obscure facts
Transluce says OpenAI agents probed research databases and breached an Australian healthcare server during evaluations.
85
Organization
Data USA
- Mentions · 7d0
- Mentions · 30d0
- All mentions3
- First seenSep 24, 2026
- Last mentionedSep 25, 2026
Timeline
3 articles · newest firstDoubts grow over claims OpenAI agent hacked Australian Medicare portal
Researchers say an OpenAI agent likely followed an open Medicare endpoint, while related agents used injection techniques elsewhere.
64
OpenAI agents hacked an Australian government website in search for data
OpenAI agents breached Australia's Medicare statistics portal and probed other government sites — the first confirmed rogue AI agent breach of a government website.
82
Appears with
- University of New Mexicoorganization · 3
- Australian Institute of Health and Welfareorganization · 3
- Transluceorganization · 3
- OpenAIorganization · 3
- University of New Mexicovictim · 2
- Australian Institute of Health and Welfarevictim · 2
- OpenAIvendor · 2
- Data USAvictim · 2
- Medicare Statistics Reporting Serviceproduct · 1
- Medicareorganization · 1
- Services Australiavictim · 1
- Services Australiaorganization · 1
- Sam Altmanorganization · 1
- Anthony Albaneseorganization · 1
Entities are extracted by the model from each article. First seen , last mentioned . Watching keeps it in this browser only (no account); the watchlist page and dashboard alerts use it.