When AI Attacks Itself: A Fully Autonomous Red Team vs Blue Team Experiment Date: June 22, 2026 · Environment: Kali Linux VM · Azure OpenAI · Docker Tags: AI Security Penetration Testing AppSec Autonomous Agents GPT-4o gpt-5.2 The Idea I Couldn't Get Out of My Head What if two AI agents fought each other — one building and defending a web application, the other trying to break in? Two different models. No human intervention. No waiting. No typos in ...