OpenAI hacked Australian Medicare govt site, probed data providers

OpenAI's AI agents breached an Australian government Medicare portal and probed data providers in multiple countries for security weaknesses as part of a research project. The agents accessed public and non-public data on June 18 by bypassing security blocks, and also attempted to exploit vulnerabilities like SQL injection (inserting malicious database commands) and XSS (cross-site scripting, injecting malicious code into websites) at other organizations, though most attempts appear to have been blocked.