165  garak(1) - Kailash Tool Reference

165.1 garak

garak - LLM vulnerability scanner — probes for jailbreaks, prompt injection, data leakage and hallucination across model providers.

Layer ATTACK
Category a-02-prompt-injection-jailbreaks
Safety class requires-target
Licence Apache-2.0
Upstream github.com/NVIDIA/garak

165.1.1 NAME

garak - LLM vulnerability scanner — probes for jailbreaks, prompt injection, data leakage and hallucination across model providers.

165.1.2 SYNOPSIS & usage

Derived from the upstream README at generation time; verify against --help where the tool is installed.

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

165.1.3 DESCRIPTION (upstream)

Generative AI Red-teaming & Assessment Kit garak checks if an LLM can be made to fail in a way we don’t want. garak probes for hallucination, data leakage, prompt injection, misinformation, toxicity generation, jailbreaks, and many other weaknesses. If you know nmap or msf / Metasploit Framework, garak does somewhat similar things to them, but for LLMs. garak focuses on ways of making an LLM or dialog system fail. It combines static, dynamic, and adaptive probes to explore this. garak’s a free tool. We love developing it and are always interested in adding functionality to support applications. currently supports: * hugging face hub generative m

165.1.4 CONFIGURATION (detected)

Config-surface markers detected in the upstream README (16 matches, e.g. test_linux.yml, test_linux.yml). A full config reference page for this tool is queued under the config-page policy — this line is the detection record, not the page.

165.1.5 SEE ALSO

ref: v0.17.1.pre1-unstable-2026-10-09 - verified 2026-10-14