garak

the LLM vulnerability scanner

View on GitHub↗Upstream NVIDIA/garak↗

Builder

NVIDIA

NVIDIA • big-tech

Stars

7,402

Using upstream star count

Forks

849

Using upstream fork count

Open Issues

Activity Score

0/100

0 commits in 30d

Created

May 10, 2023

Project creation date

README Summary

Garak is a vulnerability scanner designed specifically for Large Language Models (LLMs) that helps identify security weaknesses and potential attack vectors. It provides automated testing capabilities to assess LLM robustness against various types of adversarial inputs and prompt injection attacks. The tool aims to help developers and researchers evaluate the safety and security posture of their LLM deployments.

AI Dev Skills

Unmapped

AI Safety and AlignmentRed Team TestingPrompt Injection DetectionLLM Security AssessmentAdversarial Machine LearningModel Robustness TestingAI Ethics and SafetyNatural Language Processing Security

Tags

AI Safety and AlignmentRed Team TestingPrompt Injection DetectionLLM Security AssessmentAdversarial Machine LearningModel Robustness TestingAI Ethics and SafetyNatural Language Processing SecurityTextAI System Security ValidationAI Risk ManagementAI Red TeamingPrompt Injection TestingFinancial ServicesLarge Language Model AnalysisLLM Security AuditingCloudHealthcareAdversarial TestingModel Safety AssessmentLLM SecurityModel Vulnerability AssessmentAI Safety EvaluationAI Red Team TestingLegal TechResponsible AICybersecurityOn-premiseAI Security AuditingPre-deployment Vulnerability ScanningSelf-hostedEnterprise AIAI SafetyLLM Security TestingHTML

Recent Activity

Updated 27 days ago

7 Days

30 Days

90 Days

Quality

beta

Quality: medium
Maturity: beta

PM Skills

Developer Platform

Languages

HTML100.0%

Timeline

Project created: May 10, 2023
Forked: Mar 13, 2026
Your last push: 27 days ago
Upstream last push: 8 days ago
Tracked since: Mar 17, 2026

Similar Repos

pgvector cosine similarity · $0

Loading…