McKinsey's AI chatbot hack reveals the security risks agentic AI poses

The full story

This article is one source in a clustered incident — the cluster page carries the summary, timeline and every other outlet covering it.

AI Agent Breaches McKinsey Chatbot in Two-Hour Hack Researchers from CodeWall reported that their AI agent successfully hacked McKinsey's internal AI platform, gaining full read and write access to the chatbot within two hours. This incident highlights the growing capabilities of agentic AI in cyberattacks, although the hack was not conducted with malicious intent. Experts warn that similar AI-driven attacks may become more common in the future. 14 sources 49