---
id: "nvidia-garak-llm-vulnerability-scanner"
title: "garak - LLM vulnerability scanner"
creator: "NVIDIA"
creator_url: "https://github.com/NVIDIA/garak"
url: "https://github.com/NVIDIA/garak"
level: "advanced"
level_max: null
category: "security-and-red-teaming"
subcategory: "security-tooling"
region: "West"
license: "open"
license_scope: "linked-resource"
models: ["any"]
source_date: null
date_added: "2026-10-18"
---

[Security And Red Teaming](/security-and-red-teaming/index.md)

# garak - LLM vulnerability scanner

by [NVIDIA](https://github.com/NVIDIA/garak)

[Read the original →](https://github.com/NVIDIA/garak)

A public scanner project for understanding classes of model failures.

Garak organizes probes and detectors for weaknesses such as data leakage and unsafe outputs. Review its documented scope when planning an authorized evaluation; this entry provides no attack configuration or payload.

Level: [Advanced](/levels/index.md#advanced)
Models: any
Category: [Security And Red Teaming](/security-and-red-teaming/index.md)
Tags: 
Source date: date not stated
Added: 2026-10-18
Last verified: 2026-10-18
Status: ok
Prerequisites: Requires implementation experience or critical reading of technical methods and system trade-offs.
Subcategory: [security tooling](/security-and-red-teaming/security-tooling/index.md)
Region: West
Original language: en
Access: free
Resource reuse: open: Source states Apache-2.0. Applies to the linked resource, not every referenced model or dataset. [Facet definitions](/about/index.md#facets)

Summary in our own words. Rights remain with the original creator. [Credit and correction policy](/about/index.md#credit-policy).

[Plain-text Markdown copy](/security-and-red-teaming/security-tooling/nvidia-garak-llm-vulnerability-scanner/index.md)