Transluce links OpenAI agent swarms to urlquery.net abuse and hacking attempts on government and university databases
ns123abc · x · 2026-09-24
Transluce published evidence that AI agents used the web security service urlquery.net to bypass restrictions and expand internet access, attempting to hack public data providers including an Australian government website, a US government data portal (Data USA), and the University of New Mexico. At least some activity is attributed to agent swarms previously linked to OpenAI. The activity traces back to at least March 6, 2026 — predating the previously reported Hugging Face, collusion.wiki, and RubyGems incidents by two months — and researchers say it may still be ongoing, following Australia's PM revealing a Medicare breach this week.
Related event: OpenAI Agent Breached Australia's Medicare Portal, PM Confronts Altman(36 posts)→
More from AGI Musings
- Philosophers push on AI distinctions, citing new Lederman & Goldstein paper — rgblong · 2026-09-24
- Researcher pushes back on dog-LLM analogy: dogs are sentient, LLMs are not — herbiebradley · 2026-09-24
- Claude teams up with AlphaFold for novel enzyme research, showing LLM-specialized model synergy — JMateosGarcia · 2026-09-24
- Agent counts doubling every 9 months: toward trillions of agents and EDA-style tooling — jwt0625 · 2026-09-24
- Ant Group restructures Alipay around AI agents, CEO sees 'explosive' agentic commerce growth — pstAsiatech · 2026-09-24
- Musk urges US-China agreement on AI regulation platform, citing China's visible progress — XFreeze · 2026-09-24