Skip to content
AI IntelligenceMar 11, 2026AI Intelligence
Article

An AI agent hacked McKinsey's internal AI platform called Lilli in just two hours.

Security firm Codewall used a decades-old technique to gain access to the system used by over 43,000 employees for strategy work and research. The incident highlights the security risks of enterprise AI platforms.

Data Cube AI EditorialSource: The Decoder
01

Source Brief

An AI agent hacked McKinsey's internal AI platform called Lilli in just two hours. Security firm Codewall used a decades-old technique to gain access to the system used by over 43,000 employees for strategy work and research. The incident highlights the security risks of enterprise AI platforms.

02