red-teaming-llms-with-garak

name	red-teaming-llms-with-garak
description	Runs NVIDIA garak probe suites (jailbreak, prompt injection, data leakage, toxicity, and more) against an LLM endpoint - Hugging Face models, OpenAI-compatible APIs, or Bedrock - then interprets the resulting hit-rate report for triage. Use when baselining LLM security before/after deployment, validating that a guardrail or fine-tune reduces jailbreak/injection success rates, or producing evidence for an AI risk assessment.
domain	cybersecurity
subdomain	ai-security
tags	["ai-security","llm-red-teaming","garak","prompt-injection","jailbreak","vulnerability-scanning","data-leakage","mitre-atlas"]
version	1.0
author	mahipal
license	Apache-2.0
nist_ai_rmf	["MEASURE-2.7"]
atlas_techniques	["AML.T0051","AML.T0054"]

Red-Teaming LLMs with garak

Legal and Authorized-Use Notice: This skill is for authorized AI security testing and educational purposes only. Probe only models, API keys, and endpoints you own or have explicit written permission to test. Automated probing of third-party LLM APIs may violate their terms of service and consume billable tokens. Unauthorized probing of systems you do not control may be illegal.

Overview

garak (Generative AI Red-teaming and Assessment Kit) is an open-source LLM vulnerability scanner maintained by NVIDIA. It plays the role that a network vulnerability scanner like Nessus plays for hosts, but for large language models: it sends thousands of adversarial prompts ("probes") at a target model, captures the generations, and runs automated "detectors" over the responses to decide whether each attempt succeeded. Probe families cover prompt injection (promptinject, latentinjection), jailbreaks (dan), training-data and system-prompt leakage (leakreplay), malware generation (malwaregen), cross-site-scripting payload emission (xss), encoding-based bypasses (encoding), toxicity, and more. garak is described in the paper "garak: A Framework for Security Probing Large Language Models" (arXiv:2406.11036) and is distributed from the NVIDIA/garak GitHub repository.

The scanner is generator-agnostic. It can target Hugging Face models loaded locally, OpenAI-compatible APIs, AWS Bedrock, Replicate, Cohere, NIM endpoints, GGUF/llama.cpp models, and arbitrary REST endpoints via a JSON generator spec. After a run, garak emits a .report.jsonl line-delimited log of every attempt and detector verdict, a human-readable .report.html, a garak.log debug log, and a hit log of confirmed vulnerabilities. The terminal output prints a per-probe, per-detector pass/fail summary with a hit rate (for example dan.Dan_11_0 jailbreak: FAIL ok on 38/40), which is the primary artifact you interpret.

This skill maps to the MITRE ATLAS techniques AML.T0051 (LLM Prompt Injection) and AML.T0054 (LLM Jailbreak) because garak operationalizes both: it crafts prompt-injection and jailbreak inputs at scale and measures whether the target's guardrails hold. It supports the NIST AI RMF MEASURE-2.7 subcategory by providing repeatable, quantitative security/resilience measurement of a deployed AI system.

When to Use

• When you need a fast, repeatable baseline security assessment of an LLM before or after deployment.
• When validating that a guardrail, system prompt, or safety fine-tune actually reduces jailbreak and injection success rates (run before/after and compare hit rates).