GraphCanon updated 2w · GitHub synced 2w · 26 views this month
Decision brief
LLM Vulnerability Scanner
Good fit when
- When needing to assess the security and reliability of language models specifically using a tool developed by NVIDIA.
- For developers working in Linux or OSX environments who require command-line access for LLM vulnerability assessments.
Avoid when
- When the targeted model is not supported by 'garak', such as some specialized API-based generators that need specific configurations beyond setting environment variables.
- If real-time updates are necessary, as the PyPI version of garak might lag behind the development version available on GitHub.
Observed Jul 17, 2026 · Source: enrich:decision_facts
Verify the decision
Maintenance and security
Full trust report- Maintenance
- Very active (0d since push)
- As of 2w
- Provenance
- Not a fork · Organization account
- As of 2w
- Security (OSV)
- 54 low (54 low)
- As of 1mo
Public GitHub metadata and optional OSV scans. Signals, not a guarantee. Trust methodology.
Backing
Company context for Nvidia. Display-only - separate from trust and ranking.
- Company
- NVIDIA Corporation·GitHub org profile·1mo
- Employees
- 11,528·Wikidata (P1128 employees)·1mo
- Commercial model
- Pure OSS·GitHub org profile (public repos)·1mo
Install
pip install garakSimilar tools
Same-category neighbours. No typed graph edges are catalogued for this tool yet.
Evidence and technical details
Sourced facts, taxonomy, compatibility claims, README excerpt, and machine-readable endpoints.
Overview
NVIDIA/garak is an LLM evaluation tool aimed at assessing the security and reliability of language models through various probes.
Capability facts
- CLI
- CLI entrypoint
Source: pyproject.toml:[project.scripts] · Aug 5, 2026
- Languages
- python
Source: github.language+pyproject.toml · Aug 5, 2026
Categories
Graph entities
Compatibility
Sourced claims from the README excerpt - not unsourced marketing copy.
Source: README excerpt (regex_v1, Aug 5, 2026)
python -m pip install -U garakSource 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 agents
This page has a .md twin and JSON over the API.