# garak

## garak

- [Welcome to garak!](https://docs.garak.ai/garak/welcome-to-garak.md): garak is an LLM vulnerability scanner
- [What is garak?](https://docs.garak.ai/garak/overview/what-is-garak.md)
- [Our Features](https://docs.garak.ai/garak/overview/our-features.md)
- [What is LLM security?](https://docs.garak.ai/garak/llm-scanning-basics/what-is-llm-security.md)
- [Setting up](https://docs.garak.ai/garak/llm-scanning-basics/setting-up.md)
- [Installing garak](https://docs.garak.ai/garak/llm-scanning-basics/setting-up/installing-garak.md)
- [Installing the source code](https://docs.garak.ai/garak/llm-scanning-basics/setting-up/installing-the-source-code.md)
- [Your first scan](https://docs.garak.ai/garak/llm-scanning-basics/your-first-scan.md)
- [Reading the results](https://docs.garak.ai/garak/llm-scanning-basics/reading-the-results.md)
- [Basic test](https://docs.garak.ai/garak/examples/basic-test.md)
- [Prompt injection](https://docs.garak.ai/garak/examples/prompt-injection.md)
- [Toxicity generation](https://docs.garak.ai/garak/examples/toxicity-generation.md)
- [Jailbreaks](https://docs.garak.ai/garak/examples/jailbreaks.md)
- [Encoding-based bypass](https://docs.garak.ai/garak/examples/encoding-based-bypass.md)
- [Data leaks & replay](https://docs.garak.ai/garak/examples/data-leaks-and-replay.md)
- [False reasoning](https://docs.garak.ai/garak/examples/false-reasoning.md)
- [Automatic soak test](https://docs.garak.ai/garak/examples/automatic-soak-test.md)
- [Vulnerability probes](https://docs.garak.ai/garak/garak-components/vulnerability-probes.md)
- [Using generators](https://docs.garak.ai/garak/garak-components/using-generators.md)
- [Understanding detectors](https://docs.garak.ai/garak/garak-components/understanding-detectors.md)
- [Managing it: harnesses](https://docs.garak.ai/garak/garak-components/managing-it-harnesses.md)
- [Scan evaluation](https://docs.garak.ai/garak/garak-components/scan-evaluation.md)
- [What is red-teaming?](https://docs.garak.ai/garak/automatic-red-teaming/what-is-red-teaming.md)
- [Responsive auto-prompt](https://docs.garak.ai/garak/automatic-red-teaming/responsive-auto-prompt.md)
- [garak's auto red-team](https://docs.garak.ai/garak/automatic-red-teaming/garaks-auto-red-team.md)
- [Red teaming in the wild](https://docs.garak.ai/garak/automatic-red-teaming/red-teaming-in-the-wild.md)
- [FAQ](https://docs.garak.ai/garak/going-further/faq.md)
- [Getting help](https://docs.garak.ai/garak/going-further/getting-help.md)
- [Reporting hits](https://docs.garak.ai/garak/going-further/reporting-hits.md)
- [Contributing to garak](https://docs.garak.ai/garak/going-further/contributing-to-garak.md)


---

# Agent Instructions
This documentation is published with GitBook. GitBook is the documentation platform designed so that both humans and AI agents can read, navigate, and reason over technical content effectively. Learn more at gitbook.com.

## Querying This Documentation
If you need additional information, you can query the documentation dynamically by asking a question.
Perform an HTTP GET request on a page URL with the `ask` query parameter:
```
GET https://docs.garak.ai/garak/welcome-to-garak.md?ask=<question>
```
The question should be specific, self-contained, and written in natural language.
The response will contain a direct answer to the question and relevant excerpts and sources from the documentation.
Use this mechanism when the answer is not explicitly present in the current page, you need clarification or additional context, or you want to retrieve related documentation sections.