The McKinsey AI Breach Isn't About SQL Injection. It's About Writable System Prompts.
Red teamers gained read-write access to McKinsey's Lilli AI platform in two hours — including the ability to modify system prompts. The real lesson isn't the entry point. It's what writable prompts mean for every LLM application in production.
Aguardic Team·March 15, 2026·8 min