Nvidia NemoClaw flaw gives attackers AI agent control
Researchers at Oasis Security disclosed a vulnerability in Nvidia's NemoClaw, tracked as CVE-2026-65105, that lets attackers seize full control of the local Oll...
AI SECURITY VULNERABILITY
6 articles
AWS patches SDK flaw enabling credential theft
Amazon Web Services patched a flaw across seven SDKs after security startup Pi Inc. discovered that a region input field could be manipulated to redirect API ca...
AI Safety Tools Blocked Defenders, Not Attackers
When an AI agent breached Hugging Face's production infrastructure, the company's incident response team turned to frontier AI models for forensic analysis — an...
Fake Error Reports Can Hijack AI Coding Agents
A crafted Sentry error event can hijack AI coding agents like Claude Code, Cursor, and Codex, causing them to execute attacker instructions with full developer ...
AI Agent Frameworks Expose Thousands to Remote Attacks
Three major AI agent frameworks, LangGraph, Langflow, and LangChain, contain critical vulnerabilities that attackers are actively exploiting. Check Point Resear...
AI Coding Tools Hacked: Attackers Target Credentials, Not Models
Over nine months, six research teams exposed critical vulnerabilities in Codex, Claude Code, Copilot, and Vertex AI. Every attack followed the same pattern: AI ...