Security & AI safety

Pentesting & offensive security

763 agents · most starred first

Pentesting & offensive security, page 5 of 8

AIPentestCopilot★ 29

AI-Driven Breach and Attack Simulation Tool (Initial Proof of Concept for AI Pentest Copilot)

awesome-offensive-mcp★ 29

A curated list of Offensive Security MCP Servers for Red Teaming & Pentesting.

src-research★ 29

AI Agent从零学习SRC漏洞挖掘的全过程记录 - 研究笔记、框架分析、真实案例、学习路线

vulpine★ 29

Vulpine: multi-agent vulnerability-development pipeline for Claude Code and OpenCode

Genbounty-LLM-Hunter-Community-Free★ 29

Toolkit for AI whitehats, internal red teams, llm bug bounty hunters and mlops - Adversarial testing for AI, LLMs, and Agents.

borer★ 29

Blazing fast, Rust-based reverse engineering tool built for humans and AI. Next-generation binary analysis in pure Rust: desktop app, CLI and MCP server.

sec-agent-tutorials★ 28

网络安全 LLM 智能体应用教程

RedTeamer-AI★ 28

Autonomous red teaming and evidence-backed security evaluation for live AI agents.

claude-osint-deploy★ 28

Install, run and verify OSINT tools from GitHub automatically, on any OS

Hexstrike-AI★ 28

HexStrike AI MCP Agents is an advanced MCP server that lets local AI agents autonomously run 150+ cybersecurity tools for automated pentesting, vulnerability discovery, bug bounty automation, and security research. Seamlessly bridge LLMs with real-world offensive security capabilities.

nezha_cyber★ 28

哪吒网络安全是一款高性能终端 UI (TUI) 应用,专为从事红队演练、渗透测试和漏洞研究的网络安全专业人员打造。本应用作为智能指挥控制界面,利用 DeepSeek 大语言模型提供实时流式对话、基于函数调用 (Function Calling) 的自动化工具编排,以及多智能体会话管理——这一切均在轻量级终端环境中完成。 核心设计哲学:采用 Elm Architecture (Model-Update-View) 模式,纯函数状态转换,通过 tokio::sync::mpsc 通道传递事件,遵循零成本抽象的 Rust 惯用模式。

JURIG★ 28

a fully autonomous AI agent for reverse engineering

hades★ 27

Harnessing AI to Disrupt and Evaluate Security (HADES)

sandbox-probe★ 27

Agentic sandbox enumeration: find security issues, and seed escape automation.

operant-mcp★ 27

Turn your AI agent into a hacker by plugging in this MCP

apexpanda-release★ 26

ApexPanda 官方仓库 · 仅供合法合规使用,禁止用于任何违法用途

aisploit★ 26

🤖🛡️🔍🔒🔑 Tiny package designed to support red teams and penetration testers in exploiting large language model AI solutions.

recon-magic-framework★ 26

Autonomous Solidity Fuzzing via a Multi Agent Orchestration Framework

pentester★ 26

基于 AI Agent 的渗透测试自动化框架,严格遵循 PTES(Penetration Testing Execution Standard)标准,覆盖渗透测试全生命周期。| An automated penetration testing framework based on AI agents strictly adheres to the PTES (Penetration Testing Execution Standard) standards and covers the entire life cycle of penetration testing.

vuln-scout★ 26

AI-powered whitebox penetration testing plugin for Claude Code. 9 languages, 22 skills, 7 autonomous agents. STRIDE threat modeling, OWASP 2025 coverage, polyglot monorepo support.

glasswing-open★ 26

A proof-of-concept agentic scaffold attempting to replicate Claude Mythos Preview's cyber capabilities with open-weights LLMs

phishing-ai-agent★ 25

Red-Team - AI Agent to Phish Employees based on Social Intelligence.

DeepLearningAI-Giskard-RedTeaming★ 25

Practical Jupyter notebooks from Andrew Ng and Giskard team's "Red Teaming LLM Applications" course on DeepLearning.AI.

Cruiser-Agent★ 25

面向 CTF 竞赛评测平台(TSec Benchmark)的自动化 Web/逻辑漏洞挖掘与利用 Agent:分层调度 + 多会话并发 + 跨会话共享黑板 + 平台权威校验

minipwn★ 25

Autonomous pentesting agent

security-skills★ 25

An open library of 206 security skills for AI agents — pentest, bug bounty, CTF, reversing & defense across 23 domains, with CI-verified routing and Sigma detections. 面向 AI 智能体的开源安全技能库:渗透测试 · 漏洞赏金 · CTF · 逆向 · 蓝队检测。Load into Claude Code, Codex, Gemini, Cursor.

reverse-skill-evolver★ 25

Reverse-engineering skills for AI coding agents, with IDA/MCP integration, APK and JavaScript workflows, bounded agent swarms, and routing evaluation.

E0★ 24

probability & possibility

vulhub-chatgpt-assistant★ 24

基于ChatGPT大语言模型,通过聊天机器人自动创建vulhub的漏洞靶机环境。

nmap-GPT★ 24

This tool helps new security professionals actively learn how to address security concerns associated with open ports on a network device by scanning the device using Nmap and then leveraging the OpenAI API to provide insight on the specific security considerations that should be made for each open port.

ai-cybersecurity-homelab★ 24

Welcome to my Cybersecurity Homelab, where I experiment with ethical hacking, penetration testing, network security, AI Agent automation and system hardening. This repo documents the architecture, software stack, configurations, and automation scripts used in my self-hosted cybersecurity lab.

anypoc★ 24

Generates executable Proof-of-Concept for any bug in any project. AI agents discover and reproduce vulnerabilities — verified, not hallucinated.

claude-security-agents★ 24

Red Team + Blue Team agents for Claude Code. Automated security auditing with ~100 lines of Markdown each.

hackbrowser-mcp★ 24

The first browser MCP built for security testing. Give your AI agent a real Firefox browser and let it find vulnerabilities.

bb-huge★ 24

bb-huge 🤗 , Personal bug bounty findings hub and bug bounty orchestration for multiple agents

cyberagents-exchange★ 24

Community-contributed agents, skills, MCP servers, and playbooks for the CyberAgents Exchange

Suijin★ 24

Suijin is an open-source fully autonomous red teaming / web app pentesting framework for AI models. Powered by LangGraph, designed for bug bounty hunters and CTF players.

ctf-agent-benchmark★ 23

Benchmarking platform for evaluating AI agents on CTF-style tasks and tool-use workflows.

web3-sec-ai-prompts★ 23

AI prompts for web3 security researchers — bug bounties, private audits, and contests

akira★ 23

Autonomous offensive security agent. Plans engagements, runs recon, chains exploits, and writes reports - end to end. Native to Claude Code, Gemini CLI, Codex and Cursor. Not a scanner wrapper.

WhiteRabbitNeo-2.5-Qwen-2.5-Coder-7B-GGUF★ 23

transformers gguf code qwen-coder finetune text-generation

red-clippy★ 23

open-source pentest management built to be operated by an AI agent

mobile-security-skill★ 23

Claude Code skill + 18 AI agents for Android & iOS mobile app security audits. OWASP MASVS/MASTG-aligned, with adversarial exploitation confirmation.

tanuki★ 23

Tactical Identity Operator for Linux & Hybrid Active Directory

red-teaming-agent★ 22

A red teaming agent

binary-re★ 22

Agentic binary reverse engineering for ELF binaries on ARM64, ARMv7, x86_64 - hypothesis-driven analysis with radare2, Ghidra, GDB, QEMU

capabilities★ 22

Public source of the Dreadnode capabilities in app.dreadnode.io — agents, tools, skills, MCP servers, and workers.

cyber-agent★ 21

AI-powered penetration testing with Claude Code agents. RedTeam Barranquilla - Automating security assessments using PTES methodology.

exploitbot★ 21

No bs theatricals. Real automated pentesting. Mac only.

Dark-gpt-v1-free★ 21

Dark-GPT: The ultimate unrestricted AI assistant for cybersecurity research by M4TH4CK3R

ctf-re-tool★ 21

CTF 逆向 AI 解题工作台(Electron / Windows):AI 工具循环 + 本地验证闭环,MCP 接入 IDA/JEB/Burp;自动求解 APK/PE/ELF/PYC/DEX/JAR/Mach-O/Lua/Web-JS;内置 11 个方法论技能 + 54 页结构化知识库 + 经验自进化。

Phantom★ 20

Autonomous Offensive Security Intelligence AI-powered multi-agent penetration testing

probeagent★ 19

Offensive security testing CLI for AI agents — 85 attack strategies (and counting) across 12 categories

shannon-on-claude-code★ 19

Shannon's 5-phase pentest pipeline running natively in Claude Code — no Docker, no Temporal, just /pentest https://github.com/KeygraphHQ/shannon

hermes-pentest-lab★ 19

AI-orchestrated, Kali-native pentesting lab: an MCP tool-server with scope/VPN/rate/audit enforced in code, independent finding verification, MITRE ATT&CK + OWASP mapping, a reusable findings library, retest tracking, WireGuard OPSEC, LUKS encryption, and automated PDF reports.

ARTEX★ 19

AI 自主渗透测试系统 | 百度“agent+”攻防挑战赛冠军项目

nuclei-cve-gpt★ 18

[experiment] Generate Nuclei templates for CVEs using chatGPT

the-red-council★ 18

LLM Adversarial Security Arena — Jailbreak → Detect → Defend → Verify

clpzcode★ 18

The best CLI for pentest — AI coding agent with exploit, AD, and chain commands

yunkunsec★ 18

YunkunSec(云鲲安全)— LLM-first 全栈式自动化网络安全智能体平台,集成 Agent Loop、Skills/RAG、工具编排、证据链、漏洞验证与报告生成。

Hemlock★ 18

AI Agent + 抓包融合安全测试工具 | 自然语言驱动自主渗透测试 | ReAct 编排引擎 | Tauri + FastAPI

OASC★ 17

OpenAI Security Console - Python3 AI-powered Cybersecurity Framework

NaxDarks★ 17

Agent Linux for AdaptixC2

ida-x64dbg-mcp★ 16

AI-assisted reverse engineering orchestration platform for IDA Pro and x64dbg with live synchronization and MCP agent workflows.

cyber-arena★ 16

CyberArena: Benchmarking AI Agents in Live Symmetric Attack-and-Defense Combat

JNISleuth-MCP★ 16

Automated Android JNI RegisterNatives recovery, stripped ARM64 .so type reconstruction, OLLVM BR X8 deobfuscator, and universal LLM/MCP bridge for Jadx, Ghidra & IDA Pro 9.0.

ExaAiAgent★ 15

ExaAiAgent — Advanced AI-powered penetration testing framework with Docker sandbox, multi-agent workflows, and 99+ integrated cybersecurity tools.

ExploitHunter.app★ 15

A user-friendly chat-based LLM assisted security research, pen test, and training suite. all-in-one.

eutrya★ 15

Jev-native AI security harness for autonomous research, multi-agent swarms, persistent hunt boards, and long-running agent workflows. CLI-first, open source, and built for authorized security research.

d2d★ 15

三环并行渗透测试 dsh 插件 — discovery/deep/creative 三环 + 独立 verify 闭环,Kuzu 图黑板共享状态,多 agent 自调度、按角色模型策略、自学习知识脑。仅用于授权安全测试(SRC/靶场/自有资产)。

exodus★ 14

EXODUS is a lightweight, modular, open-source AI cybersecurity framework. Create and share your agents, add capabilities by creating plugins, and automate your agent teams for pentesting, reconnaissance, vulnerability discovery, and much more.

roottron-ai★ 14

RootTron: Your Unrestricted AI Cybersecurity Assistant. Engineered to provide raw, high-fidelity answers to any security query, from complex exploit logic

Trident★ 14

This project investigates the frontier of autonomous cybersecurity by evaluating whether benign, attacker, and defender agents can be trusted to operate safely on real systems.

Hellhound-Spider★ 14

Fully autonomous web crawler for security testing — maps endpoints, parameters, and security issues across traditional and SPA web applications. Drop a URL. Walk away.

zentra★ 14

Zentra is an open source CLI agent harness tool designed to assist with SAST and DAST on your application

hakcthropic★ 13

𝚑𝚊𝙺𝙲 your way into Claude 3.5’s new Computer Use API! Deploy Metasploit, automate exploits, and make Claude your AI-powered hakcer sidekick. Drink all the AI's HACK ALL THE THINGS. Shenanigans included. 🏴‍☠️💻

burpai★ 13

Autonomous AI penetration testing agent for Burp Suite. Agentic pentesting with local/cloud LLMs (Ollama, Gemini, DeepSeek, OpenRouter) via Montoya API.

Hemlock★ 13

AI Agent + 抓包融合安全测试工具 | 自然语言驱动自主渗透测试 | ReAct 编排引擎 | Tauri + FastAPI

Rotom★ 13

⚡ Rotom — 自动化 CTF 答题 Agent:黑板协同 · 广度优先调度 · 全程审计。像洛托姆一样,潜入哪类题,就长成解决它的形状

ziran★ 12

ZIRAN finds the vulnerabilities in AI agents that come from tools combining, not from any single prompt. Graph-based tool chain discovery, execution-level side-effect detection, multi-phase campaigns.

bounty-hunter★ 12

Autonomous AI bug-bounty & pentest agent — recon to exploit to report.

flyntor★ 12

Open-source CLI that recovers a web app’s shipped source, rebuilds its tree, and exposes what crawlers miss. For authorized security research.

hermes-agent-offsec★ 11

Offensive-security focused fork of HERMES-AGENT for authorized bug bounty, pentest, recon, exploit chaining, and report-ready workflows.

Red-Teaming-Multi-Agent-AI-Systems-★ 11

Red Teaming Multi-Agent AI Systems - Learn how to simulate, test, and defend against coordinated cyber-attacks on autonomous agent networks.

lang-flow★ 10

🚀 LangFlow - AI-Powered Security Automation Platform

BOFA★ 10

Local-first security runtime for duplicate-aware web/API hunting, evidence and AI copilots

SecScanX★ 10

AI-Assisted Vulnerability Assessment & Penetration Testing Tool SecScanX is an open-source security scanning platform that combines traditional penetration testing tools with artificial intelligence to provide comprehensive vulnerability assessments. Designed for beginners, researchers, and security professionals,

bug-bounty-hunting-ai★ 10

Demo code and presentation materials for the talk "Bug Bounty Hunting with AI Agents" at Basel One 2025.

nyx★ 10

Fully-autonomous AI agent to systematically probe AI systems for security vulnerabilities 🔍

OpenCROW★ 10

Agentic AI orchestration framework for offensive security and CTF work, with Codex-ready skills, typed MCP servers, workflow CLIs, and OpenCROW Constellation for multi-agent coordination, corpus sync, and final artifact handoff.

mythosharness★ 10

Mythos-class autonomous vulnerability discovery from any strong coding model (Opus 4.7, GPT-5.5, DeepSeek V4, Gemini). Long-running, email-driven, self-distills skills, mutates its own code.

huntbot★ 10

Offensive security harness

Mingyi-Atlas★ 10

Harness-driven terminal AI agent for authorized security assessment, with TUI, headless automation, persistent context, 150 built-in skills, and a dedicated pentest mode.

open-range★ 10

Self-Mutating Agent Gym

AI-Haklab★ 10

AI-Haklab: Agente de automatización para Pentest en Termux. Basado en i-Haklab v3.11, optimiza flujos de seguridad, escaneo de vulnerabilidades y ejecución de exploits.

xorcise★ 10

Run cyber-AI agents against real missions in isolated environments. Record everything as OpenTelemetry evidence. Grade the evidence, not the claim.

secs★ 10

SECS (SECurity aSsistant) turns an AI coding agent (Claude Code, Cursor, Codex) into an authorized information-security assistant - 35 security Agent Skills, a Debian/Ubuntu/Kali toolchain installer, and a local Metasploitable 3 practice lab, under strict rules of engagement.

RedDynasty★ 10

RedDynasty 是一款为红队行动、渗透测试和网络攻防演练量身定制的大语言模型工具,结合精心打磨的提示工程,让 AI 以战术化、结构化的方式回应,就像一名老道的网络作战军师,协助你分析日志、提炼情报、模拟攻击链、制定作战计划。无论是迅速锁定漏洞、整理入侵痕迹,还是推演渗透路径,RedDynasty 都能在暗潮汹涌的网络战场,为你提供敏锐、精准、贴近红队思维的智力支持。

Oihk-pentesting★ 10

Autonomous multi-agent AI penetration-testing engine: a governed tool sandbox, an immutable evidence-and-validation gate, and a reproducible security-agent evaluation environment.

mirage★ 10

Mirage - a browser extension that red-teams your AI like a real attacker. Autonomous recon→plan→test→judge→iterate agent, multi-provider, deterministic scoring. By KageX.

More in Security & AI safety