Giskard

Tool manual · Kali & common usage

AI Security · Intermediate · AI Security lane

IntermediateAI Security

Authorized usage only. Capture and inspect traffic only on systems and networks you own or have written permission to analyze.

What is Giskard?

Giskard tests ML/LLM systems for performance and security issues.

Scan models for bias/leakage-style issues in lab notebooks.

Official website: Giskard · Documentation

When do you use it?

You need ML/LLM testing for performance and security issues.
You are following a CYNARKS lab or authorized engagement that calls for Giskard.
You already tried simpler checks and need this tool’s deeper capability.

Who uses it?

Security practitioners
Students in authorized labs
Engineers validating their own systems

How do you use it? (typical flow)

Install Giskard using the steps below (prefer Kali package or official installer).
Confirm you have authorization for the target (lab VM, own system, or written scope).
Run --help / man (or the Help section) to see current flags for your version.
Start with a safe example from Basic commands against localhost or an authorized lab target.
Record what you ran, what you observed, and any follow-up (filter, report, remediation).

Help & manual (like man / --help)

Every serious tool has a built-in way to look up flags. Learn these first so you are not stuck memorizing every option.

1. Docs
```
https://docs.giskard.ai/
```

Kali Linux

pip install giskard

1. Installation

OS	Installation
`Kali Linux`	pip install giskard
`pip`	pip install giskard

2. Basic commands

1. Find bias/leakage issues
```
scan model wrapper in notebook
```
Find bias/leakage issues
2. Show help
```
scan --help
```
List flags for your installed version (same habit as man/--help).
3. Short help
```
scan -h
```
Alternate help flag when supported.

5. Useful features

Scan
Reports

6. Practical examples

Example 1: Find bias/leakage issues
```
scan model wrapper in notebook
```
Find bias/leakage issues
Example 2: Show help
```
scan --help
```
List flags for your installed version (same habit as man/--help).
Example 3: Short help
```
scan -h
```
Alternate help flag when supported.

7. Important notes

Extend to LLM agents with care.
Authorized targets only — labs, systems you own, or written permission.
Prefer reading --help / man / official docs for your installed version; flags change over time.

Related course: ai security · web application security · Commands: /commands