AISiliconANGLEabout 1 hour ago
Nvidia NemoClaw flaw enables model poisoning
1 min read
Oasis Security disclosed CVE-2026-65105 in Nvidia's NemoClaw, letting attackers control the local Ollama server behind a developer's AI agent via DNS rebinding. The flaw allows model poisoning through Go template injection. Nvidia released NemoClaw at GTC in March.
Level
Hype check
Tap to vote and see what everyone thinks.
In this storyNvidia
Summary by ByteBrief
