CodeWall: ‘How We Hacked McKinsey’s AI Platform’
This story is only covered by news sources that have yet to be evaluated by the independent media monitoring agencies we use to assess the quality and reliability of news outlets on our platform. Learn more here.4 Articles
4 Articles
The security company CodeWall let an AI agent go to the internal chat platform of the management consultancy McKinsey. The result should give IT security managers in large companies to think. CodeWall, a startup specialized in offensive security tests, compromised with an autonomous agent the generative AI platform Lilli of McKinsey. Human help was apparently not necessary at all. McKinsey introduced the chatbot in the summer of 2023. He is used…
CodeWall: ‘How we hacked McKinsey’s AI platform’
Published by CodeWall.ai earlier this week: McKinsey & Company – the world’s most prestigious consulting firm – built an internal AI platform called Lilli for its 43,000+ employees. Lilli is a purpose-built system: chat, document analysis, RAG over decades of proprietary research, AI-powered search across 100,000+ internal documents. Launched in 2023, named after the first professional woman hired by the firm in 1945, adopted by over 70% of McKi…
An AI agent hacked McKinsey's internal AI platform in two hours using a decades-old technique
Security firm Codewall turned an offensive AI agent loose on McKinsey's internal AI platform Lilli, a system used by over 43,000 employees for strategy work, client research, and document analysis. No credentials, no insider knowledge, no human assistance. Within two hours, the agent had full read and write access to the production database. The article An AI agent hacked McKinsey's internal AI platform in two hours using a decades-old technique…
The security company Codewall let go of an offensive AI agent on McKinsey's internal AI platform Lilli, a system that uses over 43,000 employees for strategy work, client research and document analysis. Without access data, no insider knowledge, no human help. Within two hours, the agent had complete read and write access to the production database. The article An AI agent hacks McKinsey's AI platform Lilli with a vulnerability from the 1990s fi…
Coverage Details
Bias Distribution
- There is no tracked Bias information for the sources covering this story.
Factuality
To view factuality data please Upgrade to Premium
