Mar 09, 2026 • Data Leak | #SQL injection #IDOR #Unauthenticated Endpoints

McKinsey's AI agent "Lilli" hacked - by another AI agent - thestack.technology

McKinsey's internal AI agent "Lilli" was breached through classic application security flaws, including an unauthenticated endpoint with a SQL in...

Read Analysis →

Aug 25, 2025 • Vulnerability | #IDOR #API Security #Legacy Application

Chatbots, APIs & AI Security Risks: Lessons from a Real Breach - Qualys

An Insecure Direct Object Reference (IDOR) vulnerability in an exposed API, combined with an unpatched legacy web application and weak credential hygiene, allow...

Read Analysis →

Jul 11, 2025 • Vulnerability | #Weak Password #IDOR #Paradox.ai

McDonald’s AI Chatbot Breach Exposes 64 Million Records - Cyber Magazine

Security researchers gained unauthorized administrative access to Paradox.ai's McHire platform by exploiting a weak, decommissioned test account with "...

Read Analysis →