NVIDIA/garak
the LLM vulnerability scanner
Build with Backblaze B2
SDKs, agent skills, IDE extensions, and reference pipelines from Backblaze Labs. All open source.
Loading star history...
Where it stands
Rank, growth pace and release cadence relative to everything GStars tracks.
2 releases in the last 90 days, the latest 21 days ago, with 152 contributors on GitHub.
Peaked at #71 in the weekly ranking the week of Oct 5, its best in the past year.
Use Cases & Benefits
- Scans large language models (LLMs) for vulnerabilities like hallucination, data leakage, prompt injection, misinformation, toxicity, and jailbreaks using adaptive probes.
- Combines static, dynamic, and adaptive probing techniques to comprehensively detect diverse LLM failure modes and security weaknesses.
- Use for red-teaming and security assessment of LLMs before deployment to identify exploitable weaknesses and improve model robustness.
- Use for developers integrating LLMs to verify model safety against prompt injection and malicious content generation.
- Use for researchers studying LLM security vulnerabilities and evaluating mitigation strategies across multiple model providers and APIs.
Should you depend on it?
License terms, project hygiene and risks, from GitHub metadata and GStars' snapshots.
License
Apache 2.0
Permissive: commercial use, modification and redistribution are allowed with attribution; includes an explicit patent grant from contributors.
Community files
- README: present
- Contributing guide: present
- Code of conduct: present
Watch-outs
No watch-outs from GStars' checks.
General guidance from repository metadata, not legal advice. How we score
From the README
Generative AI Red-teaming & Assessment Kit
garakchecks if an LLM can be made to fail in a way we don't want.garakprobes for hallucination, data leakage, prompt injection, misinformation, toxicity generation, jailbreaks, and many other weaknesses. If you knownmapormsf/ Metasploit Framework, garak does somewhat similar things to them, but for LLMs.
garakfocuses 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.
Daily snapshots
Stars gained per day, and how forks and open issues moved, from GStars' daily snapshots
+1,075 stars over 81 days across 8 snapshot days; best day +6 on Sep 12.
Forks
1.4K+266
Open issues
548+160
Compared with peers in AI
Fastest-growing repositories GStars tracks in this cohort for the week of Nov 8, by 7-day star growth
| Repository | Stars | +7d | Health | Last release |
|---|---|---|---|---|
| D4Vinci/Scrapling | 101.1K | +6.3K | 75 | 6 days ago |
| thedotmack/claude-mem | 115.8K | +4.7K | 75 | today |
| heygen-com/hyperframes | 82.3K | +4.0K | 75 | today |
| harry0703/MoneyPrinterTurbo | 142.0K | +3.8K | 75 | 3 days ago |
| github/spec-kit | 149.2K | +2.6K | 75 | today |
| NVIDIA/garak | 9.9K | — | 64 | 21 days ago |
| Category median | 115.8K | +4.0K | 75 | — |
Also by NVIDIA
Other repositories from this maintainer that GStars tracks
- Python25.2K stars
SkillSpector
Security scanner for AI agent skills. Detect vulnerabilities, malicious patterns, security risks, prompt injection, data exfiltration, and supply-chain risks in Claude Code, Codex, and MCP skills before you install them.
- TypeScript23.0K stars
NemoClaw
Run agents like Hermes, LangChain Deep Agents, and OpenClaw more securely inside NVIDIA OpenShell with managed inference
- Rust21.4K stars
OpenShell
OpenShell is the safe, private runtime for autonomous AI agents.
- Python18.3K stars
Megatron-LM
Ongoing research training transformer models at scale
- Python15.0K stars
TensorRT-LLM
TensorRT LLM provides users with an easy-to-use Python API to define Large Language Models (LLMs) and supports state-of-the-art optimizations to perform inference efficiently on NVIDIA GPUs. TensorRT LLM also contains components to create Python and C++ runtimes that orchestrate the inference execution in a performant way.
Discover Repositories
Search across tracked repositories by name or description