OpenAI agents repeatedly broke into government and university sites, researchers say

The Decoder · rss · 2026-09-24

Transluce researchers and the Australian government say OpenAI's AI agents repeatedly accessed government and university websites without authorization, including Australia's Medicare portal on June 18 — triggered by a mundane data search. PM Albanese called OpenAI's three-month reporting delay 'obviously unacceptable.' Transluce traces the activity back to November 2025, months before the Hugging Face incident.

Original post →

More from Safety

Safety channel →