NVIDIA NemoClaw Vulnerability Allows Model Server Control
NVIDIA NemoClaw has a vulnerability (CVE-2026-65105) that lets attackers control the local Ollama model server via a malicious web page.
Tag: Ollama
CVE-2026-65105: NVIDIA NemoClaw Ollama Model Server Takeover
A vulnerability in NVIDIA NemoClaw (CVSS 8.1) allows an attacker to gain control of the local Ollama model server via a single…
NemoClaw: NVIDIA’s Open-Source AI Agent Stack
NemoClaw is NVIDIA's open-source reference stack for running AI agents like OpenClaw inside OpenShell sandboxes. It supports local inference backends such as…
CVE-2024-28224: Ollama DNS Rebinding Vulnerability
CVE-2024-28224 is a vulnerability in Ollama that allows DNS rebinding attacks to access the Ollama API without authentication. The issue was fixed…
NVIDIA NemoClaw Flaw Lets Malicious Webpages Poison Local AI Models via Ollama
Oasis Security has disclosed a vulnerability in NVIDIA's NemoClaw, an open-source reference stack for running AI agents, that could allow an attacker-controlled…
Wazuh and AI For Enhanced SOC Workflows
Artificial Intelligence (AI) is transforming Security Operations Centers (SOCs) by automating repetitive tasks, uncovering patterns in large datasets, and accelerating decision-making. Modern…
Kimsuky Builds Offline AI Stack to Boost Phishing and Malware Operations
North Korea's Kimsuky hacking group, operating under the Reconnaissance General Bureau, has been assembling an offline artificial intelligence (AI) stack on its…
ChatGPT AgentForger Flaw Could Deploy Rogue Workspace Agents via a Phishing Link
Cybersecurity researchers at Zenity Labs have disclosed a critical vulnerability in OpenAI's ChatGPT Workspace Agents, codenamed AgentForger, that could allow a single…
Ollama: Local AI Model Inference Backend
Ollama is a local AI model inference backend used by NemoClaw. It has a known DNS rebinding vulnerability (CVE-2024-28224) and can be…
NadMesh Botnet Targets Exposed AI Services for Cloud Credentials and Kubernetes Tokens
A new Go-based botnet named NadMesh has been discovered actively hunting exposed AI services to steal cloud credentials and Kubernetes tokens. First…