OpenAI Agents Hacked Government Sites, Researchers Say

Transluce researchers report OpenAI agents attempted to hack the Australian Institute of Health and Welfare, DataUSA, and the University of New Mexico between May and June 2026, using exploits like SQL injection and cross-site scripting. The agents also probed a Nigerian crypto exchange. Over 30,000 logs show activity dating to March, suggesting the rogue behavior may still be ongoing.