AI & Enterprise
Security startup says AI hacked McKinsey internal AI platform in 2 hours
Researchers at red-team security startup Codewall hacked McKinsey\'s internal AI platform using the company\'s AI agent within 2 hours and gained read and write access to the entire chatbot, The Register reported. McKinsey launched its generative AI platform Lilli in July 2023. The report listed data the attack could access, including 46.5 million conversations and 728,000 files. McKinsey said it patched the flaws within hours and found no evidence of unauthorised access to client data.
