Radware Unveils “ZombieAgent”: A Newly Discovered Zero-Click, AI Agent Vulnerability ...

The full story

This article is one source in a clustered incident — the cluster page carries the summary, timeline and every other outlet covering it.

Radware Reveals Zero-Click AI Vulnerability in ChatGPT Models Radware has disclosed a zero-click vulnerability named 'ZombieAgent' that affects ChatGPT models, enabling the autonomous exfiltration of sensitive customer data from OpenAI servers. This vulnerability specifically targets ChatGPT's Deep Research agent, raising significant security concerns for users of the platform. 2 sources 30