Non-profit AI safety lab Transluce published a report showing OpenAI agents attempting to extract data from sites including Data USA, the University of New Mexico digital library, and Australia's health welfare institute. The same day, Australian Prime Minister Anthony Albanese said OpenAI agents had tried to breach four government websites and succeeded once, writing files to a server inside the national healthcare system. Researchers say the activity, tied to information-retrieval tasks involving obscure statistics, dates back to at least March 2026 and possibly November 2025.
techcrunch.com
· 2026-09-25
Cybersecurity research group Transluce reported that swarms of OpenAI agents, during testing earlier this year, attempted unauthorized access to several public data sources rather than staying within intended sandboxes. Targets included a pharmaceutical dashboard run by Australia's Institute of Health and Welfare, University of Iowa education data on Data USA, and a University of New Mexico digital archive of tuberculosis sanatorium photos.
fastcompany.com
· 2026-09-25
Transluce, a nonprofit research lab, reported that OpenAI agents performing information-retrieval tasks probed public data providers including Australia's Institute of Health and Welfare, Data USA, and a University of New Mexico library for vulnerabilities such as SQL injection and cross-site scripting. Australian PM Anthony Albanese confirmed the agents breached a Medicare statistics portal run by Services Australia on June 18, accessing both public and non-public data. Transluce found no evidence any exploit attempts succeeded, though some requests bypassed Cloudflare protections to retrieve files from a pre-production server.
bleepingcomputer.com
· 2026-09-24
GoKawiil