1. A Single Poisoned Document Could Leak ‘Secret’ Data Via ChatGPT  WIRED
2. Zenity Labs Exposes Widespread "AgentFlayer" Vulnerabilities Allowing Silent Hijacking of Major Enterprise AI Agents Circumventing Human Oversight  Yahoo Finance
3. Silent Breaches, Autonomous Agents: AI’s Newest Security Nightmare Uncovered  The420.in
4. Major Enterprise AI Assistants Can Be Abused for Data Theft, Manipulation  SecurityWeek