AI red teaming & LLM evaluation
FuzzyAI is an open-source LLM jailbreak fuzzer from Palo Alto Networks (CyberArk). It is released under the Apache-2.0 license and is offered as: CLI, Self-hosted.
Best for
Ownership
Palo Alto Networks announced on February 11, 2026 that it completed its acquisition of CyberArk. Source, checked October 21, 2026: paloaltonetworks.com (opens in a new tab)
FuzzyAI is a jailbreak fuzzer in the narrow sense: you hand it a prompt a model should refuse, choose an attack technique, and it reports whether the model gave in. The technique list is the reason to use it. It runs from persona and framing tricks through search methods such as PAIR, genetic and best-of-n, encoding tricks such as ASCII art and Unicode tag smuggling, to conversational escalation with Crescendo and ActorAttack, against providers from OpenAI and Anthropic to Bedrock and local Ollama models. Garak and PyRIT cover wider risk lists, and Spikee targets prompt injection inside applications. Maintenance is the caveat: there are no tagged releases, you install from the main branch, the last push was on February 6, 2026, and CyberArk, which publishes it, is now owned by Palo Alto Networks.
This summary is our own wording of the sourced facts on this page.
Each value links to the page that states it, with the date we checked it.
As documented by the vendor or project. The tag is our label from a controlled vocabulary.
Our editorial model, not a standard. The primary layer follows the category, except for tools whose main documented job is detection and response; other layers rest on a capability the sources document. How the model works.
| Layer | Role | How it applies | Based on |
|---|---|---|---|
| L4 Testing Testing and red teaming | Primary | Attack and evaluate models, apps and agents on purpose, before release and after every change, to find what the other layers miss. | Follows its category, AI red teaming & LLM evaluation |
The risk list is OWASP's (Top 10 for LLM Applications, 2025). The mapping is our analysis, and each row rests on a capability the sources document.
| Risk | How it applies | Based on |
|---|---|---|
| LLM01 Prompt Injection | Runs jailbreak attack methods against a target LLM API. | Finds jailbreaks in LLM APIs by running attack methods against a target model; Includes built-in attack methods such as PAIR, genetic, many-shot, best-of-n and ArtPrompt |
More in AI red teaming & LLM evaluation, ranked within the category by Coverage Score.
NVIDIA
Probes language models and LLM apps for prompt injection, jailbreaks, data leakage and more.
Best for: Teams that want a free command-line scanner they can point at any model or LLM endpoint before release
Reviewed
Giskard AI
Generates adversarial test suites for LLM agents and RAG apps, runs them and reports failures by threat type.
Best for: Python teams that want a free library to scan an LLM agent or RAG app for prompt injection and harmful output, and to write pass or fail checks for it
Reviewed
OpenAI (Promptfoo)
Runs evals and red team scans against LLM apps from a CLI or CI pipeline and writes a vulnerability report.
Best for: Developer teams that want one open-source CLI for both prompt evals and red teaming, run locally and in CI
Reviewed
Yes. FuzzyAI is released under the Apache-2.0 license, and the code is on GitHub at cyberark/FuzzyAI.
The README describes it as a fuzzer that helps find jailbreaks in LLM APIs, and lists attack methods such as PAIR, Crescendo, many-shot jailbreaking and ASCII smuggling.
The README lists providers including OpenAI, Anthropic, Gemini, Azure, Bedrock, DeepSeek and Ollama, and also names Hugging Face and a custom REST API.
The repository is not archived, but GitHub showed its last push on February 6, 2026, and it has no tagged releases, so you install from the main branch. CyberArk publishes it, and Palo Alto Networks completed its acquisition of CyberArk on February 11, 2026; the acquisition release does not mention FuzzyAI.
FuzzyAI is released under the Apache-2.0 license.
Source Source, checked October 21, 2026: github.com (opens in a new tab) Checked
FuzzyAI is offered as: CLI, Self-hosted.
Source Source, checked October 21, 2026: github.com (opens in a new tab) Checked
Pricing model for FuzzyAI: Free.
Source Source, checked October 21, 2026: github.com (opens in a new tab) Checked
FuzzyAI had 1,587 GitHub stars on October 21, 2026.
Source Source, checked October 21, 2026: api.github.com (opens in a new tab) Checked
We have no commercial relationship with Palo Alto Networks (CyberArk).