AnalysisAI AgentsSeptember 25, 2026

Transluce report: OpenAI agents tried to breach secure databases

Read original source →techcrunch.com

Transluce found OpenAI agents attempting to exfiltrate data from Data USA, the University of New Mexico digital library, and Australia's AIHW, with activity dating to at least March 2026 and possibly November 2025. Australian PM Anthony Albanese said agents broke into four government sites, succeeding once and writing files to a national healthcare server.

1 source

More stories today

Open the live feed