Early rogue AI agent activity and attempts to hack found on urlquery.net

Summary by Cyber Security News24 Sep 2026, 02:00 CEST

About this summary. This is a short, independently written summary of an article first published by AI Incident Database. Cyber Security News did not report or verify the underlying story. Read the original: https://transluce.org/agent-activity

We present evidence that AI agents used the web security service urlquery.net to bypass restrictions and expand their access to the public internet. The agents also tried on three occasions to hack public data providers, including an Austra ... (https://incidentdatabase.ai/cite/1707#7992)

Read the full article at AI Incident Database →

Source attribution: headline and facts are from AI Incident Database (transluce.org). Summary method: excerpt of the source description. See our source attribution policy.

Related coverage

Coding Agents Aren't Enough! Evaluating an Enterprise Security Brain for Agentic Cloud Investigations

Subjects, Not Authors: The Authorship Hazard in Agentic Dataspaces

Prompt Injection Detection for Email Agents Through Attack Chain Modeling

Werracle: Sub-Cent Intra-Block AI Reflex Oracles and Flash-Loan Circuit Breakers for EVM Smart Contracts

Input-Layer Starvation: Why Per-Layer Pruning Breaks IoT Intrusion Detectors

XPhysICS: Cross-Physical-Domain Threat Grounding for Industrial Control Systems Security