A cybersecurity startup says its artificial intelligence agent needed just two hours to break into McKinsey & Company's proprietary generative AI platform, accessing millions of staff messages and thousands of files.

CodeWall published findings earlier this week, disclosing that it also could have rewritten the chatbot's core instructions after its agent exploited a SQL injection flaw.

The startup said its agent gained full read and write access to the production database underpinning McKinsey's AI platform Lilli, an internal platform the high-priced consultancy says could "rewire the way we operate." Roughly three quarters of the firm's more than 40,000 employees use it for strategy work, client research and document analysis. Read more...