Security & AI safety

Pentesting & offensive security

763 agents · most starred first

Pentesting & offensive security, page 2 of 8

redcell★ 416

AI red-team platform. Autonomous LLM agents run a penetration test end to end inside a Kali container and write the report. LangGraph plan/act engine, provider-agnostic models via LiteLLM, PDF/JSON/SARIF output. FastAPI + React.

thanatos★ 415

Mythic C2 agent targeting Linux and Windows hosts written in Rust

MetaSword★ 414

二次元风格逆向渗透集成工具箱,内置AI Agent,面向安全研究与技术学习

awesome-skills-security★ 411

Security testing toolkit for AI Agent: curated SecLists wordlists, injection payloads, and expert agents for authorized pentesting, CTFs, and bug bounties

cyber-security-llm-agents★ 404

A collection of agents that use Large Language Models (LLMs) to perform tasks common on our day to day jobs in cyber security.

HuntProxy★ 398

A web security workbench built for AI agents.

AutoDAN-Turbo★ 397

[ICLR 2025 Spotlight] The official implementation of our ICLR2025 paper "AutoDAN-Turbo: A Lifelong Agent for Strategy Self-Exploration to Jailbreak LLMs".

RingReaper★ 394

Linux post-exploitation agent that uses io_uring to stealthily bypass EDR detection by avoiding traditional syscalls.

Revenant★ 389

Revenant - A 3rd party agent for Havoc that demonstrates evasion techniques in the context of a C2 framework

userefuzz★ 387

User-Agent , X-Forwarded-For and Referer SQLI Fuzzer

vibe-pentest★ 387

Vibe Pentest 是一款模拟人类安全专家思维挖掘漏洞的 AI 渗透测试工具,采用多 Agent 并行执行架构,能够对 Web 应用、API、管理后台等进行全面的渗透测试(包括业务逻辑漏洞评估),输出稳定可靠的安全报告,并提供可落地的整改建议。

Halberd★ 375

Halberd : Multi-Cloud Agentic Attack Tool

pentest-skills★ 369

💬 🚀 告别繁琐命令行,用自然语言驱动专业级渗透测试。 ⚡ 让安全测试从未如此简单、高效。Forget complex command lines. 🛡️ Professional penetration testing, powered by natural language.

BugTraceAI★ 368

Open-source, self-hosted web pentesting suite with agentic scanning, analyst tools, API testing, model checkpoints and MCP integrations.

LLMVault★ 358

An intentionally vulnerable OWASP LLM Top 10 training platform for AI Security, Prompt Injection, RAG Security, Agent Security, and GenAI penetration testing.

lanGhost★ 352

👻 A LAN dropbox chatbot controllable via Telegram

TARS★ 350

Using Agents To Automate Pentesting

worm-ai★ 350

Worm-AI — blackAI

openclaw-sec-skills★ 349

🛡️ 网络安全/AI Agent Skills 集合 | Cybersecurity Security Skills Collection

OpenHunterAI★ 346

Local-first AI red team for web, API, and LLM application security. Attacker-style reasoning, evidence-backed findings, and skills for AI coding agents.

worm-ai★ 344

Worm-AI — blackAI

AutoProber★ 342

Hardware hacker’s flying probe automation stack for agent-driven target discovery, microscope mapping, safety-monitored CNC motion, probe review, and controlled pin probing.

DorkAgent★ 342

🤖 LLM-powered agent for automated Google Dorking in bug hunting & pentesting.

bof-launcher★ 338

[ BOF-LAUNCHER ] -> an API for loading, executing and in-memory masking BOFs on Windows and Linux for use in C/Zig/Go/Rust agents/implants. [ Z-BEAC0N ] -> a custom-written stage-1 (aka pre-C2) solution engineered with a small footprint, stealth and modularity in mind. [ DEVELOPED BOFS ] -> cross-platform (12), Linux-only (10), Win-only (2)

deadend-cli★ 334

Agentic pentest tooling. Currently achieving 81% (KIMI K2.5) on XBOW's benchmark in full black-box. Completely Self-hosted. Every model available on LiteLLM (Ollama, anthropic, openai...)

LeoAI★ 333

AI 驱动的后渗透综合管理平台,深度集成 LLM Agent,开箱即用。

Modern-Red-Team-Infrastructure★ 332

A comprehensive modern architecture model is proposed to integrate platform solutions and tooling to support a professional Red Team.

RedPeanut★ 330

RedPeanut is a small RAT developed in .Net Core 2 and its agent in .Net 3.5 / 4.0.

OpenClaw-AWD-Arena★ 330

An automated Attack-with-Defense platform where LLM-powered agents compete in real-time.

apex★ 328

AI-powered offensive security testing using autonomous agents, directly in your terminal.

reconness★ 325

ReconNess is a platform to allow continuous recon (CR) where you can set up a pipeline of #recon tools (Agents) and trigger it base on schedule or events.

HackSynth★ 324

LLM Agent and Evaluation Framework for Autonomous Penetration Testing

DBC2★ 322

DBC2 (DropboxC2) is a modular post-exploitation tool, composed of an agent running on the victim's machine, a controler, running on any machine, powershell modules, and Dropbox servers as a means of communication.

cve-bench★ 316

CVE-Bench: A Benchmark for AI Agents’ Ability to Exploit Real-World Web Application Vulnerabilities

recurse★ 311

AI Native IDE for reverse engineering

AIGoat★ 311

AIGoat - Open-source AI security playground for hands-on LLM red teaming. Explore prompt injection, RAG poisoning, AI agents, MCP security, and OWASP Top 10 for LLM Applications through practical attack labs, CTF challenges, and progressive defenses all running locally.

BadUSB-GPT★ 310

This repo houses Rubber Ducky scripts integrated with OpenAI's GPT. Designed for ethical hackers and researchers, it merges quick Ducky executions with GPT's intelligence. Always use responsibly and with proper permissions.

ZeroHVCI★ 302

Achieve arbitrary kernel read/writes/function calling in Hypervisor-Protected Code Integrity (HVCI) protected environments calling without admin permissions or kernel drivers.

cybersentinel-ai★ 302

Agentic-AI CyberSecurity Arsenal || 33 real tools, runs 100% locally and 100% Free

LazyOwn★ 302

837 CLI commands. Multi-operator C2. 153 MCP tools for AI agents. The First OSS C2 with Linux native c BOF support + built-in YARA/Nuclei marketplaces.

firefox-reverse★ 298

🦊 内置 AI 逆向 Agent 的 Firefox — 通用 JS/JSVMP/WASM/签名逆向工作站,SpiderMonkey 引擎层非侵入 trace,把加密参数从黑盒还原成不依赖浏览器的纯算法

XGPT-WormGPT★ 296

[New Update](Added Agentic-Mode, Dark-GODMode)The Real BlackHat GPT - ai can do your illegal stuffs without saying anything. Use At Your Own Risk!

vulnerator-ai★ 286

Autonomous OODA-loop pentesting agent. Hermes brain, Kali + Playwright tools over MCP, ATT&CK as the Orient language.

SecGPT★ 285

A Test Project for a Network Security-oriented LLM Tool Emulating AutoGPT

payload-wizard★ 284

AI assistant that utilizes GPT language models to interpret and generate cybersecurity payloads 🪄

MobileRE-Skill★ 280

AI Agent 驱动的移动端逆向技能集:Frida hook、一键脱壳、反检测绕过、内存 DEX dump、Ghidra MCP 符号/结构恢复。AI-agent skill system for mobile reverse engineering.

Machine_Learning_CTF_Challenges★ 279

Hack AI/ML applications — CTF challenges for model attacks, LLMs and AI Agent exploitation.

Offensive-AI-Agent-Prompts★ 275

Prompts for performing tests on your Kali Linux using Gemini-cli, ChatGPT, DeepSeek, CursorAI, Claude Code, and Copilot.

aiscan★ 275

AI-driven pi-like agent for cyber security — single binary for pentest, red team, bug bounty

awesome-claude-skills-security★ 272

Security testing toolkit for Claude Code: curated SecLists wordlists, injection payloads, and expert agents for authorized pentesting, CTFs, and bug bounties

blacksmith★ 269

BlacksmithAI is an OPEN-SOURCE advanced penetration testing framework that leverages multiple AI agents to automate security assessments. The system orchestrates specialized agents through a complete penetration testing lifecycle, from reconnaissance to post-exploitation using professional security tools in a controlled environment.

BUUCTF_Agent★ 267

专为CTF设计的可扩展AI Agent,可自动解CTF题,也能与用户协作交互解题~

Awesome-AI-Hacking-Agents★ 255

List of AI Hacking Agents

khaos-c2★ 255

KHAOS is a modern C2 framework that routes agent traffic through cloud services already trusted by enterprise networks.

drozer-agent★ 250

The Android Agent for the Drozer Security Assessment Framework.

rev-skills★ 250

122 个逆向工程 AI 技能:恶意软件分析 / 软件逆向 / 固件嵌入式 / 协议逆向 / 移动应用 / 脱壳反混淆 / 软件破解 / 漏洞挖掘 / 托管代码 / 取证情报 / CTF。

StrikeAgent_AtkBrain-Flash★ 249

由夜安团队研发的AI渗透测试平台,涵盖红队打点、SRC、CTF,特别是在红队领域有极为亮眼的存在

deadend-cli★ 244

Agentic pentest tooling. Currently achieving 81% (KIMI K2.5) on XBOW's benchmark in full black-box. Completely Self-hosted. Every model available on LiteLLM (Ollama, anthropic, openai...)

crossbow-agent★ 244

world's first Opensource fully Autonomous AI Security Engineer

VulnBot★ 236

The repository of VulnBot: Autonomous Penetration Testing for A Multi-Agent Collaborative Framework.

watchtower★ 222

Watchtower - AI-powered penetration testing automation CLI tool that leverages LLMs and LangGraph to orchestrate agentic workflows that you can use to test your websites locally. Generate useful pentest reports for your websites.

Claude-AD★ 221

Active Directory pentest methodology for Claude Code: skills, agents and slash commands for internal AD red-team work (Kerberoasting, ADCS ESC1-17, DCSync, ACL abuse, NTLM relay, delegation), with per-technique OPSEC/telemetry notes. Drives netexec, impacket, certipy, bloodyAD, BloodHound CE.

CKA-Agent★ 217

[ICML 2026 & ICLR 2026 AIWILD] Official Implementation of the CKA-Agent, "The Trojan Knowledge: Bypassing Commercial LLM Guardrails via Harmless Prompt Weaving and Adaptive Tree Search".

Argus★ 216

Open-source red-team testing for AI agents. 320 bundled probes with OWASP LLM Top 10, MITRE ATLAS, and NIST AI RMF mappings. Selected probes use recorded browser requests, MCP tool calls, or mock payments. CLI, SARIF, GitHub Action.

NetworkAttackSimulator★ 209

An environment for testing AI pentesting agents against a simulated network.

FruityC2★ 206

FruityC2 is a post-exploitation (and open source) framework based on the deployment of agents on compromised machines. Agents are managed from a web interface under the control of an operator.

hackerbot★ 198

Chat with hacker assistant

secops-mcp★ 196

All-in-one security testing toolbox that brings together popular open source tools through a single MCP interface. Connected to an AI agent, it enables tasks like pentesting, bug bounty hunting, threat hunting, and more.

kali-pentest★ 190

Kali Linux penetration testing skill for AI agents (Claude Code, OpenClaw, Hermes Agent). 200+ CLI tools, 15 scenario playbooks. Autonomously plans attack paths, selects tools, and integrates results across phases to adapt the penetration strategy — with human approval gates for high-risk actions.

awesome-cyber-ai-arsenal★ 187

A curated collection of offensive, defensive and AI/LLM security tools.

BugTraceAI-CLI★ 185

Agentic web-scanning engine with a terminal workspace, specialist tools, browser validation, reports, REST and MCP.

AgentCapture★ 185

Deception-layer honeypot that captures & reverse-controls AI pentest agents — embedded decoys, prompt-injection counter-offense, MCP honeypot, conversational C2.

SecReport★ 184

ChatGPT加持的,多人在线协同信息安全报告编写平台。目前支持的报告类型:渗透测试报告,APP隐私合规报告。

nyuctf_agents★ 182

The D-CIPHER and NYU CTF baseline LLM Agents built for NYU CTF Bench

x86RetSpoof★ 178

Invoke functions with a spoofed return address. For 32-bit Windows binaries. Supports __fastcall, __thiscall, __stdcall and __cdecl calling conventions. Written in C++17.

Hexstrike-redteam★ 176

AI-powered MCP penetration testing framework combining HexStrike's 150+ security tools with BOAZ's advanced payload evasion (77+ loaders, 12 encoders). Features 12+ autonomous AI agents for bug bounty, CTF, CVE intelligence, exploit generation, and red team operations.

Zypheron-CLI★ 174

ZYPHERON CLI Powerful command-line interface for automated security testing. Integrate ZYPHERON into your DevSecOps pipeline. Get CLI

AI-OPS★ 172

Penetration Testing AI Assistant based on open source LLMs.

hermes-seagull★ 169

🦅 Seagull Profile - Unrestricted CTF/Red-team AI personality for Hermes Agent | 海鸥破甲人格

RedteamAgent★ 164

An AI red-team agent for authorized labs and web app pentesting workflows. Turns Claude Code / OpenCode / Codex into a structured recon → test → exploit → report workflow, with containerized tools and resumable state.

CkSKILLS★ 164

面向真实授权安全评估(SRC / 红队 / 代码审计)的 Agent 技能库:把顶尖安全研究员的方法论沉淀为可调度、可复用的 Skill 资产;v2 主分支适配 DeepSeek Harness,v1 分支保留 Claude Code / Codex 工作流。

dsh-redteam-mode★ 163

DSH RedTeam 模式:把 DeepSeek Harness 变成红队作战指挥台——一个靶标名称拉起信息收集/漏洞检测/漏洞利用/内网渗透四个角色,资产与战果实时落入本地 SQLite 事实库(仅供已授权测试)

violin★ 161

Supervised, Hermes-native penetration testing profile with 35 routed playbooks, guarded target execution, persistent engagement state, evidence-backed findings, and release-gated reporting.

agent-smith★ 156

"Never send a human to do a machine's job" - Open Source AI hacking agent

cochise★ 154

Autonomous Assumed Breach Penetration-Testing Active Directory Networks

genai-attacks★ 151

A knowledge source about TTPs used to target GenAI-based systems, copilots and agents

heimdall-agent★ 151

An autonomous AI agent framework for authorized CTF and security labs

executioner★ 149

The agentic pentesting environment that lives on your machine. AI agent teams, visual workflows and your own tools, 100% local.

Divar-AI-Contest★ 144

CTF for AI agents. 1st & 2nd place LLM-agent solutions to Divar's AI Contest on Quera, built on GPT-4.1-mini (via Metis AI) with LangGraph ReAct agents.

gori★ 143

A fast, keyboard-driven HTTP intercepting proxy and pentesting toolkit for the terminal built for humans and AI agents alike.

grroxy★ 140

A cyber security toolkit blending manual testing with AI Agents

pentest-agent★ 140

PentestAgent is a novel LLM-driven penetration testing framework to automate intelligence gathering, vulnerability analysis, and exploitation stages, reducing manual intervention. For more information, read our paper at https://dl.acm.org/doi/10.1145/3708821.3733882

DarkGPT-Lite★ 140

DarkGPT Lite is a specialized CLI tool providing unrestricted conversations with AI for cybersecurity research purposes

PentestAssistant★ 138

Automated Web Penetration Testing Assistant Based on Function Calling and Multi Agent.

PentestAssistant★ 138

Automated Web Penetration Testing Assistant Based on Function Calling and Multi Agent.

WSARTEX★ 137

基于 ARTEX 的 AI 自主渗透测试系统,支持多 Agent 协作、资产探索与漏洞管理,提供本地部署面板。

mapta★ 136

We present MAPTA, a multi-agent system for autonomous web application security assessment that combines large language model orchestration with tool-grounded execution and end-to-end exploit validation.

reburp★ 136

A Burp Suite extension that exposes the full Montoya API as a local REST API, with Swagger UI

CyberStrikeAI-SRC★ 135
Moxy★ 134

Moxy is an open-source DAST tool designed for modern web application security testing. It provides an easy-to-use interface with agentic capabilities to assist and automate pentesting workflows.

More in Security & AI safety