ENNAENNA

garak vs Semgrep

GitHub Stats

7.7k
Stars
14.9k
903
Forks
923
325
Issues
877
today
Updated
today
Apache-2.0
License
LGPL-2.1
Python
Language
OCaml

About garak

garak is a vulnerability scanner specifically designed for Large Language Models, developed by NVIDIA. It probes LLMs for weaknesses including prompt injection, jailbreaking, training data leakage, hallucination, toxic generation, and other failure modes. garak ships with dozens of probe modules targeting specific vulnerability classes and supports custom probe development. It works with OpenAI, Hugging Face, local models, and any API-compatible endpoint. Results include detailed reports on which attacks succeeded, confidence scores, and categorization by risk type. Essential for red-teaming AI systems before deployment and validating safety guardrails.

About Semgrep

Semgrep is a lightweight static analysis engine that helps find bugs and enforce code standards across over 30 programming languages. It uses custom rules to perform code scanning, offering flexibility in detecting vulnerabilities and ensuring best practices. Semgrep's ability to integrate into development environments allows developers to catch issues early in the coding process. Its focus on customizable rules and language support makes it a powerful tool for secure software development.

Platform Support

๐Ÿงlinux๐ŸŽmacos๐ŸชŸwindows
๐Ÿงlinux๐ŸŽmacos๐ŸชŸwindows

Tags

garak only

llm-securityai-red-teamprompt-injectionjailbreakml-security

Semgrep only

saststatic-analysiscode-scanningcustom-rules