Quality & Security / Security & Red Teaming

NVIDIA garak

LLM vulnerability scanner.

RepoModel-agnostic
8.9kstars
1.2kforks
Aug 19, 2026last commit

Operator context

Best for

Teams testing AI systems for security weaknesses and unsafe behavior who want an inspectable project they can evaluate directly.

Why it's here

LLM vulnerability scanner. It belongs in the Index as a focused security & red teaming resource that can support a real workflow, comparison, or implementation decision.

When to use it

  • Red-team an AI application
  • Identify security risks before production
  • Inspect or test the underlying project before adding it to a workflow

Where this fits

Indexed under Quality & SecuritySecurity & Red Teaming. Captured in the August 2026 edition, sourced via Curated Web.

Common questions

What is NVIDIA garak? +

NVIDIA garak is LLM vulnerability scanner.

Which AI models does NVIDIA garak work with? +

It is tagged for: Model-agnostic.

Where can I access NVIDIA garak? +

It is available at github.com.

The AI Operator's Index is maintained by EE Solutions. EE Solutions is a senior technology team for private capital firms and their portfolio companies.

Talk to EE Solutions ↗