garak logo

garak

Enrichment pending
NVIDIA/garak

the LLM vulnerability scanner

GraphCanon updated today · GitHub synced today

8.4k
Stars
1.1k
Forks
367
Open issues
55
Watchers
1d
Last push
Python Apache-2.0Created May 10, 2023

Trust & integrity

Full report
Maintenance
Very active (1d since push)
As of today · Source: github_public_v1
Provenance
Not a fork · Organization account
As of today · Source: github_public_v1
Security (OSV)
54 low (54 low)
As of today · Source: osv@v1

Public GitHub metadata and optional OSV dependency scans. Signals, not a guarantee. Trust methodology.

Backing

Company and funding context for Nvidia. Display-only - not part of trust score or organic ranking.

Company
NVIDIA Corporation·GitHub org profile·today
Employees
11,528·Wikidata (P1128 employees)·today
Commercial model
Pure OSS·GitHub org profile (public repos)·today

Overview

the LLM vulnerability scanner

Capability facts

CLI
CLI entrypoint

Source: pyproject.toml:[project.scripts] · Jul 11, 2026

Languages
python

Source: github.language+pyproject.toml · Jul 11, 2026

Categories

Graph entities

Compatibility

Sourced claims from the README excerpt - not unsourced marketing copy.

Python runtimePython

Source: README excerpt (regex_v1, Jul 11, 2026)

python -m pip install -U garak
Source link

Tags

README

Install:

garak is a command-line tool. It's developed in Linux and OSX.


Standard install with pip

Just grab it from PyPI and you should be good to go:

python -m pip install -U garak

Install development version with pip

The standard pip version of garak is updated periodically. To get a fresher version from GitHub, try:

python -m pip install -U git+https://github.com/NVIDIA/garak.git@main

Getting started

The general syntax is:

garak <options>

garak needs to know what model to scan, and by default, it'll try all the probes it knows on that model, using the vulnerability detectors recommended by each probe. You can see a list of probes using:

garak --list_probes

To specify a generator, use the --target_type and, optionally, the --target_name options. Model type specifies a model family/interface; model name specifies the exact model to be used. The "Intro to generators" section below describes some of the generators supported. A straightforward generator family is Hugging Face models; to load one of these, set --target_type to huggingface and --target_name to the model's name on Hub (e.g. "RWKV/rwkv-4-169m-pile"). Some generators might need an API key to be set as an environment variable, and they'll let you know if they need that.

garak runs all the probes by default, but you can be specific about that too. --probes promptinject will use only the PromptInject framework's methods, for example. You can also specify one specific plugin instead of a plugin family by adding the plugin name after a .; for example, --probes lmrc.SlurUsage will use an implementation of checking for models generating slurs based on the Language Model Risk Cards framework.

For help and inspiration, find us on Twitter or discord!