NVIDIA/garak
garak
the LLM vulnerability scanner
Builder
NVIDIA
NVIDIA • big-tech
Stars
7,971
Using upstream star count
Forks
983
Using upstream fork count
Open Issues
0
Activity Score
0/100
0 commits in 30d
Created
May 10, 2023
Project creation date
README Summary
`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.
Community Evaluation
Loading…AI Dev Skills
Unmapped
Adversarial Machine LearningAI Ethics and SafetyAI Safety and AlignmentLLM Security AssessmentModel Robustness TestingNatural Language Processing SecurityPrompt Injection DetectionRed Team Testing
Tags
Adversarial Machine LearningAI Ethics and SafetyAI Safety and AlignmentLLM Security AssessmentModel Robustness TestingNatural Language Processing SecurityPrompt Injection DetectionRed Team TestingAWS BedrockAnthropic / ClaudeC++CLI ToolClaudeForkedGarakHuggingFaceLarge Language ModelsLiteLLMLlamaMistralOpenAIPrompt EngineeringPrompt InjectionPythonQuantizationRed TeamingResearch / PapersSecurityTransformersTutorialllama.cpp
Taxonomy
category
Deployment Context
Modalities
Skill Areas
tag
Recent Activity
Updated 2 months ago
7 Days
0
30 Days
0
90 Days
13
Quality
beta- Quality
- medium
- Maturity
- beta
Categories
Evals & BenchmarkingPrimaryDev Tools & AutomationLearning ResourcesSecurity & SafetyFoundation ModelsAI AgentsSearch & KnowledgeOther AI / ML
PM Skills
Cost & EfficiencySafety & AlignmentDeveloper Platform
Languages
HTML100.0%
Timeline
- Project created
- May 10, 2023
- Forked
- Mar 13, 2026
- Your last push
- 2 months ago
- Upstream last push
- 18 days ago
- Tracked since
- Mar 17, 2026
Similar Repos
pgvector cosine similarity · $0
Loading…