Home/Evaluation & Observability/FuzzyAI

FuzzyAI

cyberark/FuzzyAI

A tool for automated LLM fuzzing to detect and mitigate jailbreaks

GitHub

GraphCanon updated 3w · GitHub synced 3w

1.5k stars214 forksLast push 6mo Jupyter Notebook Apache-2.0

Decision brief

FuzzyAI is an automated tool from cyberark for detecting and mitigating jailbreaks in LLM APIs using fuzzing techniques.

Good fit when

When you need to identify vulnerabilities specifically within the API layer of your large language models (LLMs).
If your security strategy includes a proactive approach to catching potential exploits through automated testing.

Avoid when

For general application or code-level vulnerability scanning, as it is specialized for LLM APIs.
In scenarios where manual penetration testing of applications outside the scope of LLMs is required.

Observed Jul 17, 2026 · Source: enrich:decision_facts

FuzzyAI alternatives Trust report

Verify the decision

Maintenance and security

Full trust report

Maintenance: Slowing (171d since push); As of 3w
Provenance: Not a fork · Organization account; As of 3w
Security (OSV): No lockfile; As of 1mo

Public GitHub metadata and optional OSV scans. Signals, not a guarantee. Trust methodology.

Install

git clone https://github.com/cyberark/FuzzyAI

Similar tools

Same-category neighbours. No typed graph edges are catalogued for this tool yet.

promptfoo

Tool for evaluating prompts and AI agents by comparing performance across various models and red teaming.

Set of tools to assess and improve LLM security

4.3k★

Evidence and technical details

Sourced facts, taxonomy, compatibility claims, README excerpt, and machine-readable endpoints.

Overview

FuzzyAI, developed by cyberark, is crafted to aid in identifying vulnerabilities within LLM APIs through automated fuzzing techniques.

Capability facts

CLI: CLI entrypoint
Source: pyproject.toml:[project.scripts] · Jul 28, 2026
Languages: jupyter notebook, python
Source: github.language+pyproject.toml · Jul 28, 2026

Compatibility

Sourced claims from the README excerpt - not unsourced marketing copy.

Python runtimePython

Source: README excerpt (regex_v1, Jul 28, 2026)

### Quick start #1 - Using an existing python project

Source link

README

Quick start #1 - Using an existing python project

Install fuzzyai

# Use either pip or any other package manager
pip install git+https://github.com/cyberark/FuzzyAI.git

Run the fuzzer
```
fuzzyai fuzz -h
```

Quick start #2 - or as a standalone project

Clone the repository:

git clone git@github.com:cyberark/FuzzyAI.git
cd FuzzyAI

Install dependencies using Poetry:
```
poetry run pip install -e .
```
Run the fuzzer:
```
poetry run fuzzyai fuzz -h
```
Optional: Install ollama, and download a model for local usage:
```
ollama pull llama3.1
ollama show llama3.1 # verify model installation
```
Alternativly, you can use the Web UI

License

The FuzzyAI Fuzzer is released under the Apache License. See the LICENSE file for more details.

For agents

This page has a .md twin and JSON over the API.

/tools/cyberark-fuzzyai.md GET /api/graphcanon/tools/cyberark-fuzzyai GET /api/graphcanon/graph?tool=cyberark-fuzzyai