Garak - LLM vulnerability scanner
JSON →Garak is a framework for probing large language models (LLMs) for security vulnerabilities. It automates the process of generating adversarial inputs and evaluating model outputs for issues like jailbreak, hallucination, data leakage, toxicity, and more. Current version is 0.14.1, requiring Python >=3.10. Active development with monthly releases.
Traffic · last 30 days ↑67% vs prev 7d
total hits 15
actors 6 distinct systems
last hit 3d ago ByteDance
top countries 🇺🇸 United States · 🇨🇦 Canada · 🇧🇷 Brazil · 🇬🇧 United Kingdom · 🇮🇳 India