Tag: ollama
2 articles
NVIDIA NemoClaw Exposes AI Models to Poisoning via Webpage
NVIDIA's NemoClaw exposes AI models to poisoning via webpage, allowing attackers to take control of the model server by binding it to every network interface. This configuration vulnerability makes it easy for hackers to access and manipulate the Ollama API from outside the loopback address.
Ollama Vulnerability Exposes Servers to Remote Memory Leak
A newly discovered vulnerability in Ollama, dubbed "Bleeding Llama," exposes over 300,000 servers worldwide to a severe remote memory leak, with a CVSS score of 9.1. This critical flaw, tracked as CVE-2026-7482, allows attackers to exploit a weakness in the GGUF model loader.