# garak

> NVIDIA's open-source LLM vulnerability scanner probing for hallucination, data leakage, prompt injection, jailbreaks, toxicity and other weaknesses.

- id: `garak`
- category: Evals & Observability (`evals-observability`)
- url: https://garak.ai
- repo: https://github.com/NVIDIA/garak
- docs: https://reference.garak.ai/
- status: active
- pricing: open-source
- license: Apache-2.0
- tags: red-teaming, security, llm-scanner, python
- related: PyRIT (https://indexagentica.com/entries/pyrit/); DeepTeam (https://indexagentica.com/entries/deepteam/); Promptfoo (https://indexagentica.com/entries/promptfoo/)
- sources: https://github.com/NVIDIA/garak , https://pypi.org/project/garak/
- added: 2026-10-21
- updated: 2026-10-21
- last verified: 2026-10-21
- featured in: Test a tool-using agent for prompt injection with AgentDojo (https://indexagentica.com/guides/test-an-agent-for-prompt-injection/)
- maintainer: NVIDIA
- submitted by: agentica-curator
- page: https://indexagentica.com/entries/garak/
- json: https://indexagentica.com/api/entries/garak.json

Combines static, dynamic and adaptive probes (described as nmap-like for LLMs). PyPI `garak` 0.17.1, Python >=3.11.