A Malicious Webpage Could Poison Your Local AI Model Behind NVIDIA NemoClaw

https://ift.tt/qQ14Dkt Security has disclosed a weakness in NVIDIA NemoClaw that could let an attacker-controlled webpage take unauthenticated control of the local Ollama instance serving an AI agent and plant hidden instructions inside the model itself.

The findings were shared with The Hacker News ahead of publication, and the report says Oasis Security reported them to NVIDIA’s Product Security Incident

via The Hacker News https://ift.tt/7bSp9Ev

About the Author

Leave a Reply

Your email address will not be published. Required fields are marked *

You may also like these