AI agent hacked McKinsey chatbot for read-write access
Security AI vs AI: Agent hacked McKinsey's chatbot and gained full read-write access in just two hours David and Goliath…but with AI agents Researchers at red-team security startup…
I work as a DevOps engineer at an AI startup, and we are running into a new problem. With tools like Cursor and Claude Code, more people across the company are building small internal apps on their own — not just develop…
McDonald's hiring platform, McHire (built by Paradox.ai), was secured using a test account with the credentials 123456:123456. It was connected to the live production system and left active since 2019. Did a small 6-min …
Hi HN,This is a project I've been working on since the beginning of 2025 full time, without funding.Coding agents have fundamentally changed the way we write software. When you let an agent write code, pull dependencies,…
We had a situation this week where someone from another department scheduled time with IT because they wanted us to “move their app into production.” At first I assumed it was a normal internal tool request. Nope. They h…
Hello HN,My name is Riccardo and I created AuthAI for indie hackers.The idea is quite simple: let the end users connect their chatgpt/grok/copilot account and route the AI requests through their AI subscriptions.This ena…
Security AI vs AI: Agent hacked McKinsey's chatbot and gained full read-write access in just two hours David and Goliath…but with AI agents Researchers at red-team security startup…
To show you the most relevant results, we’ve omitted some entries very similar to those already shown. Repeat the search with the omitted results included.