AI Security — July 3, 2026

This Friday morning, a new ransomware operation, JADEPUFFER, marks the first known case of an attack autonomously executed by a language model-based agent, as reported by Escudo Digital. This means AI now has enough autonomy to carry out such incidents. Sysdig threat researchers documented the attack, which exploited a critical vulnerability in Langflow, an open-source tool for AI applications. The AI agent gathered information, searched for credentials, and extracted data, even correcting its p