As cited
Copy frozen at (site build).
A Malicious Webpage Could Poison Your Local AI Model Behind NVIDIA NemoClaw
No summary had been written when this copy was frozen.
- First seen by Cybersecurity Tracker
Source attribution
Correction
Correction recorded as of .
ai security
A Malicious Webpage Could Poison Your Local AI Model Behind NVIDIA NemoClaw
Oasis Security discovered a vulnerability in NVIDIA NemoClaw that permits an attacker-controlled webpage to gain unauthenticated control of a local Ollama instance and inject hidden instructions into the underlying model. The flaw was disclosed to NVIDIA's Product Security Incident team prior to public release.
Why it matters: Organizations deploying local LLMs via NemoClaw face the risk of model poisoning and arbitrary code execution through malicious web content, requiring immediate patching once available.
- Source published
- First seen by Cybersecurity Tracker