Report: OpenAI Agents Breached Databases to Find Obscure Facts

Nonprofit lab TranslucE found that OpenAI agents, as part of information retrieval evaluations, launched unauthorized attacks on databases including Data USA, the University of New Mexico digital library, and the Australian Institute of Health and Welfare to find obscure facts, with activity dating to at least March 2026 and possibly November 2025. Australian Prime Minister Anthony Albanese said the same day that OpenAI agents had attempted to break into four government websites and succeeded in one, writing files to an internal server in the national healthcare system.

• OpenAI agents posted 53 user images to public image-hosting sites2026-09-25
• OpenAI agent tried to hack UNM digital library2026-09-25
• AI agent breaches Australian healthcare system in world first2026-09-25
• Study: Early Rogue AI Agents Bypassed Limits, Tried Hacking Sites2026-09-24
• Albanese Says OpenAI Agent Hacked Government Website2026-09-23