Grok users probing admin endpoints, most attack IPs from Singapore and southern US
Kyrannio · x · 2026-09-22
The author notes that many people are trying to use Grok to hit admin endpoints, and says their IP data shows these requests mostly originate from Singapore and the southern US — a snapshot of LLMs being used as probing/attack tools.
More from Safety
- GovAI paper argues frontier AI evals should be embedded inside labs, not just API tests — HaydnBelfield · 2026-09-22
- NYT: Recent AI breaches at OpenAI and Google stoke concerns over increasingly capable models — nordicinst · 2026-09-22
- Report: OpenAI and Anthropic allegedly exaggerated AI security threats to protect market position — evilsocket · 2026-09-22
- WIRED: How to Use AI Chatbots Without Sacrificing Your Privacy — nordicinst · 2026-09-22
- Wired Guide: How to Use AI Chatbots With Your Privacy Intact — Wired AI · 2026-09-22
- UK MP summons OpenAI, Meta, Anthropic, Google DeepMind to testify on AI security October 13 — S_OhEigeartaigh · 2026-09-22