Itwire
Radware Reveals Zero-Click AI Vulnerability in ChatGPT Models
First seen 9 Jan 2026, 10:47 UTC
•
•100% similarity
•29.9
Share:
Export
Ask AI about this cluster
Analyzing cluster data...
Referenced clusters:
Something went wrong. Please try again.
Cluster AI
Ask questions about this threat cluster with AI-powered analysis.
Get Researcher $29.99/moArticle Content
Browse articles
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.
ThreatCluster AI
How this analysis works