← All tools

Garak

AI Security · Intermediate

LLM vulnerability probing framework.

Knowledge reference only. Prefer in-browser Labs first. Use this tool only on systems you own or have written authorization to test.

What to learn

  • Probes
  • Reports

Legitimate use

Red-team LLMs you control.

Official docs →

Example commands (lab VMs only)

  • garak --model_type openai --model_name gpt-4o-mini
    Test your own LLM app endpoint