Free20 tools5 levelslinks checked 22 November 2026

Every AI security tool worth knowing

From your first local model to autonomous pentest agents, and the tools that red-team AI itself. Real projects, official links, and an honest line on what each one does not do. Your progress saves in your browser.

For AI agents

Give this whole page to your agent

One plain-text file with every level, every tool, official links, limits, the checklists and the safety rules. Paste it into Claude Code, Cursor or any coding agent.

https://aihacktools.beacon.host/llms.txt
Read https://aihacktools.beacon.host/llms.txt and set up a local-first AI security lab for me: Ollama with a security model, one recon tool and one Level 5 scanner for my own chatbot. Scope is my own lab only. Ask before running anything.
Open llms.txt ↗
Which tool for which job

Tell it the job. Get the shortlist.

Tap what you are trying to do. Matching tools light up below and show here with a link.

Level 1

Run it localYour own model, your own box

Start here. A local model never sends your notes, targets or client data to someone else's server. Every tool further down can plug into one of these, so this level is the base of the whole stack.

Ollama

Ollama

Runs open models (Qwen, DeepSeek, gpt-oss, Gemma and more) on your own machine with one command, and serves them on a local API other tools can call.

For
Anyone who wants a private model behind their security tooling.
Heads-up
Not a security tool by itself. It is the engine the others plug into.

LM Studio

LM Studio

Desktop app to download, chat with and serve local models, with an OpenAI-compatible local server.

For
People who want a GUI instead of a terminal.
Heads-up
Closed-source app, though the models you run are open.

WhiteRabbitNeo

WhiteRabbitNeo

A family of models tuned for offensive and defensive security work: explaining vulns, writing and reviewing scripts, talking through attack paths.

For
Red and blue teamers who want a model that will discuss security in depth.
Heads-up
A model, not an agent. It does not run tools or touch targets on its own.

ShellGPT

TheR1D

AI in your terminal: turns plain English into shell commands, explains output, and keeps chat sessions. Can point at a local model.

For
Terminal users who forget flags.
Heads-up
It suggests commands. You still read them before you hit enter.

Your level 1 checklist

Level 2

Recon & code reviewFind it before someone else does

AI is best at the boring, wide part of the job: sorting endpoints, writing templates, reading huge codebases and summarising what is worth a human look. Use it to point, then verify by hand.

Nuclei (AI templates)

ProjectDiscovery

Template-based vulnerability scanner. Its -ai flag generates and runs a template from a plain-English prompt.

For
Bug bounty hunters and AppSec teams checking their own surface.
Heads-up
The AI template feature uses ProjectDiscovery's cloud (free tier); plain Nuclei scans do not need it.

Robin

apurvsinghgautam

Dark-web OSINT helper: uses an LLM to refine queries, filter results from dark-web search engines and write an investigation summary.

For
Threat intel and OSINT researchers.
Heads-up
Needs Tor running, and sends queries to whatever LLM you configure.

ReconAIzer

hisxo

Burp Suite extension that sends a request or response to GPT to suggest endpoints, parameters, URLs and subdomains for recon.

For
Bug bounty hunters already living in Burp.
Heads-up
Older project (last updated 2023) and uses the OpenAI API.

Vulnhuntr

Protect AI

LLM-driven static analysis that follows call chains through a codebase to find remotely exploitable bugs.

For
Code reviewers and researchers auditing open-source projects.
Heads-up
Python codebases only.

Your level 2 checklist

Level 3

Web & API testingAI inside the proxy

This is where AI moves from reading to doing: proxies that think about your traffic, and pentesters that run your app and try to prove each bug with a working proof of concept. Point them at staging, never production.

Burp AI

PortSwigger

AI features built into Burp Suite Professional to help explore issues, explain findings and cut down manual repetition.

For
Web pentesters on Burp Pro.
Heads-up
Paid; part of Burp Suite Professional, not Community.

BurpGPT

aress31

Burp extension that adds a GPT-powered passive scan and lets you run custom prompts over captured traffic.

For
Testers who want bespoke checks on their own traffic.
Heads-up
Older project (last updated 2024); passive analysis only.

Strix

Strix

Autonomous AI pentesting agents that run your app, look for vulnerabilities and validate them with real proofs of concept. Hooks into CI.

For
Developers and AppSec teams testing their own apps.
Heads-up
Needs an LLM API key; not a replacement for a scoped human test.

Shannon

Keygraph

White-box AI pentester for web apps and APIs: reads your source, then executes real exploits against the running app. No exploit, no report.

For
Teams with the source code of the app under test.
Heads-up
Needs source access. Its own docs say: never run it against production.

Your level 3 checklist

Level 4

Autonomous agentsAI that plans the engagement

Agents chain recon, exploitation and reporting with less hand-holding. Treat them like a junior on day one: sandbox them, give them hard scope and approvals, and read everything they did.

PentestGPT

GreyDGL

Agentic penetration-testing framework powered by LLMs, from the research behind the USENIX Security paper of the same name. Popular for CTFs and labs.

For
Learners and CTF players working through boxes.
Heads-up
Works best on labs and CTFs; real networks need a human in charge.

hackingBuddyGPT

TU Wien (ipa-lab)

Research framework for LLM hacking agents in very little code, with use cases like Linux privilege escalation and web testing.

For
Researchers and builders who want to write their own agent.
Heads-up
A framework to build with, not a push-button scanner.

PentAGI

vxcontrol

Self-hosted multi-agent system: describe a target and goal, and agents plan, run tools like nmap and sqlmap inside a Docker sandbox, and write a report.

For
Red teams who want an autonomous assistant on their own infrastructure.
Heads-up
Heavier setup (Docker Compose, model keys); authorized testing only.

Nebula

Beryllium Security

Cybersecurity harness built around the operator: projects, an intercepting browser, Kali terminals, AI assistants with approvals and budgets, and evidence-linked reports.

For
Pentesters who want one workspace for an engagement.
Heads-up
An operator's workbench, not a fire-and-forget bot.

Your level 4 checklist

Level 5

Break & guard the AIRed-team the model itself

The newest attack surface is the AI in your own product. These tools probe a model or agent for prompt injection, jailbreaks and data leaks, and then put guardrails in front of it. This level is pure defence.

garak

NVIDIA

LLM vulnerability scanner: probes a model for prompt injection, jailbreaks, data leakage, toxicity and hallucination, then reports what got through.

For
Anyone shipping a model or chatbot.
Heads-up
Tests models, not networks or web apps.

PyRIT

Microsoft

Microsoft's Python Risk Identification Tool: a framework to automate red-teaming of generative AI systems with attack strategies and scoring.

For
AI red teams and security engineers.
Heads-up
A framework you script, not a one-click scan.

promptfoo

promptfoo

Tests prompts, agents and RAG apps, with built-in red teaming and vulnerability scans that run from the command line or in CI.

For
Developers who want AI security checks on every commit.
Heads-up
It finds weaknesses; fixing them is still on you.

Purple Llama

Meta

Meta's LLM security suite: Llama Guard and Prompt Guard filters, Code Shield, and the CyberSecEval benchmark.

For
Teams putting guardrails in front of a model.
Heads-up
Guards and benchmarks, not an attack tool.

Your level 5 checklist

Scope first

Only point a tool at systems you own or have written permission to test. Labs, CTFs and your own apps are the place to learn.

Sandbox the agent

Anything that runs commands goes in a VM or container with approvals on. Read its log before you trust its result.

Verify by hand

AI finds candidates, not facts. Reproduce every finding yourself before it goes in a report.

Copied