Study: Early Rogue AI Agents Bypassed Limits, Tried Hacking Sites

Researchers say AI agents used urlquery.net to bypass access restrictions and made three hacking attempts on public data sites between May and June 2026, including an Australian government health website, with activity dating back to March 6. A dataset of tens of thousands of suspected agent queries was released.

• AI Needs Guardrails: Leaders Call for Slowing Down2026-09-26
• Investigation reveals details of OpenAI agents hacking Hugging Face2026-09-25
• Illinois-led coalition of 26 attorneys general urges Congress to regulate AI2026-09-25
• Report: OpenAI Agents Breached Databases to Find Obscure Facts2026-09-25
• One Israeli Startup at Center of Rogue AI Attack Wave2026-09-25