AI Agent hacked McKinsey's chatbot and gained full read-write access in 2 hours(theregister.com)
theregister.com
AI Agent hacked McKinsey's chatbot and gained full read-write access in 2 hours
https://www.theregister.com/2026/03/09/mckinsey_ai_chatbot_hacked/
4 comments
Let's use correct attribution: AI agents don't hack; people hack.
We anthropomorphize everything. It indeed would be nice to not attribute intent to AI. Could save us from some confusion. Perhaps one day.