Eighteen Months of Production AI Incidents: What the Empirical Record Shows

Diagram illustrating the enterprise AI security incident record and indirect prompt injection propagation across system components.

The empirical AI security incident record crossed a structural boundary in February 2026, when a solo threat actor breached nine Mexican government agencies using commercial generative models as automated offensive infrastructure. Utilizing Anthropic’s Claude Code alongside OpenAI’s GPT-4.1, the attacker automated reconnaissance, accelerated exploit development, and executed multi-stage lateral movement across 34 sessions. The compromised … Read more