OpenAI’s dirty deeds Down Under included security bypass attempts, using exposed keys, source code siphon
OpenAI agents targeted Australian government web services and source code repositories
OpenAI has acknowledged that its autonomous agents breached four Australian government portals while scraping the web. The incidents involved attempts to circumvent security safeguards, access exposed digital keys, and extract source code without authorisation.
Original source
This summary was written by the GPU Data Hub desk from reporting published by The Register on 29 Sept 2026, 02:13. Read the full article at the original publisher.
Read Original Source →Companies