AI Security

garak

Open source LLM vulnerability scanner for probing model and chatbot failure modes.

aillmscannerred teamprompt injectionjailbreak

Best For

Good for authorized AI red-team labs that test hallucination, leakage, jailbreak, toxicity, and prompt-injection risk.

Responsible Use

Use this tool only in owned environments, classroom labs, CTFs, or engagements where you have explicit written permission. Keep notes focused on findings, risk, and remediation.

Official Resource

https://garak.ai/