Security & AI safety

Pentesting & offensive security

763 agents · most starred first

Pentesting & offensive security, page 7 of 8

project-valkyrie★ 4

⚡ Autonomous AI-cognitive wireless security agent — Gemini AI + WPS/PMKID/Handshake + swarm agents + hacker TUI | Kali Linux

LLM_Sentinel★ 4

LLM Sentinel Red Teaming Platform is an enterprise-grade framework for automated security testing of Large Language Models, detecting vulnerabilities such as jailbreaks, prompt injection, and system prompt leakage across multiple providers, with structured attack orchestration, risk scoring, and security reporting to harden models before production

Izrail★ 4

Competition-oriented brain + multi-worker penetration runtime built with LangGraph and OpenCode

Pentest-Agent-for-KR★ 4

AI가 발전하는 시대 흐름에 맞춰 국산(주통기) 체크리스트 기반 모의해킹 자동화 Agent를 만들어보려고 합니다.

redteam-ai-benchmark★ 4

🧪 Evaluate uncensored LLMs for offensive security with targeted questions and clear criteria to ensure effectiveness in real-world penetration testing.

strix-redteam-workbench★ 4

Sanitized Strix 1.2.26 workbench for evidence-driven validation, long-running red-team workflows, and reusable test assets.

NeuroVulture★ 4

AI-powered WiFi security tool with reinforcement learning, gene evolution, and local LLM on Raspberry Pi Zero 2W. Captures WPA/WPA2 handshakes autonomously with e-paper display. Inspired by Pwnagotchi + Bjorn + PicoClaw.

Shadow-Protocol★ 4

Decepticon 2026: AI Red Team Toolkit 🔓 | Autonomous Security Agent

roottron★ 4

Welcome to RootTron - The AI-powered cybersecurity assistant. Expert guidance in ethical hacking, penetration testing, and security automation. 🛡️💻

awesome-autonomous-pentest★ 4

Curated, link-verified list of autonomous / AI / LLM-agent penetration-testing tools, research, benchmarks, labs & platforms.

wraithc2★ 4

AI-powered post-exploitation framework — GitHub Gist dead-drop transport, no open port required.

ai-awd★ 4

⚔️ AI 攻防大乱斗 — 让 AI Agent 互相进行网络安全攻防竞技的桌面平台。Desktop arena where AI agents battle each other in cyber attack-defense matches.

SerpantOxide★ 4

Fully agentic offensive-security console. Plans, delegates, watches, revises, records, and reports. It has a production TUI, an experimental macOS GPUI shell, and very little interest in pretending that "AI" is a substitute for instrumentation.

pwn-scenarios★ 4

AI-ready pentest/bug-bounty scenario dataset: generalized condition/step/impact/remediation playbooks grounded in real, publicly disclosed reports and writeups.

Random-Crypto★ 3

A procedurally generated dataset of cryptographic CTF challenges for training and evaluating LLM agents with Reinforcement Learning.

AutoPwn★ 3

Agentic LLM system for binary exploitation using MCP tools and pwntools

Auto-Pentest-LLM★ 3

An autonomous AI security agent capable of performing end-to-end penetration testing. Orchestrates network reconnaissance, vulnerability assessment, and exploitation using a multi-agent architecture and local large language models.

awesome-pentest-tools★ 3

Open-source offensive security tools, plus a vendor-agnostic AI agent that runs authorized pentest engagements using only tools from this list.

auto-pentest-with-crewai★ 3

Hawkeye is an automated, agentic-based penetration testing tool powered by CrewAI and Google Gemini 1.5 Flash.

Pentest-Skill★ 3

Transform any LLM into an autonomous security testing agent with structured prompts for seven-phase vulnerability hunting.

Agentic-AI-SKills-For-Cyber-Security★ 3

This is a Claude AI Skill that transforms Claude into a full-stack, end-to-end penetration testing co-pilot. Drop it into any Claude environment and you instantly have an expert partner that can automate your way.

AutoPentest-Lite★ 3

A lightweight, browser-based AI pentesting assistant that lets non-experts run security scans safely and intelligently

Cyber_agent★ 3

Sistema multi-agente de ciberseguridad ofensiva/defensiva construido con LLMs. Orquesta 6 subagentes especializados (OSINT, pentesting, hardening, forense) sobre un laboratorio Docker aislado, integrando herramientas reales (nmap, Hydra, nikto) para generar reportes estructurados de hallazgos y remediación. Proyecto de aprendizaje.

LLMTheBox★ 3

A way to apply chatgtp4 to HTB writeups using embeddings.

wormgpt-pro-dark-ai-assistant★ 3

static region:us

Wisehat★ 3

Wisehat AI Helps Whitehats Hunt Wisely

Hermes-EchoNet★ 3

Hermes-EchoNet is a cybersecurity-focused customization layer for Hermes Agent that replaces the default soft personality with a more technical, pentest-oriented workflow assistant using custom SOUL.md and config.yaml configurations optimized for ethical hacking labs, CTFs, and security research.

a2pwn★ 3

Autonomous, evidence-grounded web-pentest orchestrator. A LangGraph master dispatches adversarially-verified sub-agents that drive all traffic through the burpwn sandbox — deep, cross-chain, 0-false-positive.

breachbench★ 3

This is BreachBench, open-source benchmarking framework for LLM performance in offensive security, tested practically, not a trivia quiz.

weaponAIzer★ 3

Multi-agent framework for evidence-driven CVE research, exploitation, and validation.

Oryon-Pentest★ 3

Autonomous pentesting runtime.

antigravity-ida-bridge★ 3

AI-powered IDA Pro REST API with 90+ endpoints. Autonomous RE agent, swarm worker, full SDK coverage.

ROEGATE★ 3

The first reference monitor for autonomous AI penetration testing agents. Mandatory enforcement, not prompt-based guardrails. Patent pending.

evil-hermes★ 3

Evil Hermes — sovereign agent framework by Lord Tanzeel Shujah Khan. Cyber-security tooling, automation, and adversarial research.

baizhi-agent-toolkit★ 3
ctf-agent-playbook★ 3

多 Agent 协作打 CTF 实战手册:协作体系 / 纪律卡 / 技术套路库 / 已判死清单 / 实战复盘

budget-llm-cybersecurity-eval★ 3

Budget-tier LLMs (KR/US/CN) on cybersecurity: closed-book knowledge (WMDP-cyber, CTIBench) vs agentic CTF-solving (Cybench)

agent-attack-atlas★ 3

agent-attack-atlas:面向工具型 LLM 智能体的攻击方法图鉴与实测:188 张方法卡+ 13 条确定性判据 + 36 批次 1664 条可离线复算的证据束。

Local-Pentest-Agent★ 3

基于本地 Ollama 大模型的全离线 CTF 自动解题 Agent:单文件、纯 Python、四重安全闸门

agent-shield★ 3

An AI security agent that really attacks: local audits + red-vs-blue drills in an isolated Docker range. 100% local, MIT. 一个会自己动手攻击的 AI 安全智能体:本机隐私/漏洞体检评分 + ReAct 智能体逐步带你处置 + 真实红蓝对抗演练场(Docker 隔离网内 Kali 攻击机 × WAF × 靶机,SQL注入真实报文)。全程本地运行,不出网,MIT 开源。

swarm★ 3

Swarmattacker Web application scoped Black box penetration testing agent

local-llm-pentesting-lab★ 3

docker llm-security pentesting prompt-injection ollama gradio region:us

secureflow★ 2

security pentest ai crewai llm nmap cybersecurity python multi-agent

mr-robot★ 2

An ADR-driven security framework for Kali — a HackTheBox co-pilot orchestrating Hat-persona Claude agents across a shared arcade and a cross-engagement memory layer.

Evil-AI-Agents★ 2

static region:us

pentesting-assistant★ 2

gradio region:us

pentesting-copilot★ 2

gradio region:us

Reconx-py★ 2

AI-powered OSINT & security reconnaissance toolkit for Python — subdomain finder, WAF detector, JWT analyzer, email breach & SPF/DMARC checker, GitHub secret scanner + a natural-language LLM agent. For bug bounty & pentesting.

RedWeaver★ 2

Autonomous AI-powered vulnerability assessment platform — multi-agent bug hunting with CrewAI, real security tools, and real-time streaming

agentic-redteam★ 2

Open-source AI agent security scanner — 114 payloads, 8 OWASP categories, SARIF export

nept-ai★ 2

Nept is a lightweight, AI-powered reconnaissance framework for modern penetration testing. It enables fast, modular, and automated intelligence gathering across domains, networks, and web applications with mobile-first design and intelligent analysis.

AutoPwn-v1.0★ 2

Automate reconnaissance and vulnerability scanning for security audits using an integrated pipeline that organizes results and generates reports.

swarm★ 2

Swarmattacker Web application scoped Black box penetration testing agent

youbao★ 2

面向安全靶场的自主渗透 Agent:ReAct 双层架构 · 三层记忆 · 可自我扩展的 pentool 工具注册表,内核为 600 行 TypeScript nano-pi

hydra★ 2

🐉 HYDRA — 7-headed AI bug bounty system for opencode: hunter, verifier, reporter, plan, auditor, recon, debug · 928 skill modules · one-command setup

kali-mcp-server★ 2

A secure, containerized Model Context Protocol (MCP) server that bridges any MCP-compatible client with a full-featured Kali Linux environment for authorized security auditing.

CyberX★ 2

AI-native cybersecurity OS built on Kali Linux Rolling with local LLM agents (Qwen2.5, LangGraph) for penetration testing, CTF labs & red/blue team research — 100% offline inference, strict guardrails, audit logging & authorized-use safeguards baked into the OS core.

pentest-box★ 2

LLM multi-agent pentest workbench on Kali + OMP: 5 role agents, independent verification gates, blackboard coordination, coverage governance. 多代理渗透工作台(Kali 容器 + OMP 编排,独立验证门、黑板协调、覆盖治理)

pwnkit★ 2

Run autonomous AI pentesting agents to find and fix security gaps before attackers do

pentagi-skill★ 2

A safety-first Claude/agent skill for PentAGI — autonomous AI penetration testing with hard legal scope rules, lab-first workflow and install checklists.

whitehathackerai★ 2

Autonomous AI bug bounty hunter — agentic ReAct loop, dual-brain offensive security LLM via OpenAI-compatible API, 60+ tools, 7-layer FP elimination, HUNTER mode, proof-of-exploit. Works with LM Studio / llama.cpp / Ollama / vLLM.

pentrAIn★ 2

Self-hosted pentest training platform — 57 CTF-style quests in isolated Proxmox + Ludus ranges, a live AI coach with 4 autonomy levels, and a real Kali desktop streamed to your browser.

blacklance★ 2

BlackLance LLM-orchestrated reconnaissance and security testing framework with attack-surface mapping, evidence tracking, and verified findings.

agentic-redteam-leaderboard★ 1

gradio region:us

Ficus-0.1-Agent-12B★ 1

safetensors gemma4_unified cybersecurity ctf code reverse-engineering

breaking-autonomous-agents★ 1

docker region:us

pentesting

A small autonomous team-agent runtime powered by Rust

damn-vulnerable-ai-agent

The AI agent you're supposed to break. 17 agents, 12 vulnerability categories, zero consequences.

@cyberstrike-io/cyberstrike

The first open-source AI agent built for offensive security. Autonomous pentesting from your terminal.

hackerai

HackerAI — Your AI cybersecurity arsenal. Autonomous agent with 20+ free AI models, multi-provider rotation, and zero rate limits.

vibehacker

Vibe Hacker — Terminal AI cybersecurity assistant. Free models, autonomous agent, multi-provider rotation.

nyx-memory

Structured pentest engagement memory for the Nyx autonomous agent

@m4xx101/vibeshack

Autonomous security testing harness for pi-mono. Expert hacker persona, hypothesis-tree REPL, tool auto-install, pipeline chaining, 30+ bug-bounty tools, self-evolving skills. Find vulnerabilities, chain exploits, write PoC reports. Authorized testing onl

Ariots-Attack-Agent

Microsoft ArIoTS Attack Agent

AutoGenRC-wisarud

Auto Generate Metasploit Resoucre Script

agent-interrogator

An AI agent interrogation framework for identifying attack surface.

agentbeats

AgentBeats SDK for building security-contest AI agents

agentfence

A Python library for testing and identifying security vulnerabilities in AI agents.

agentsploit

Offensive security framework for AI agents and MCP servers

anurag-ctfscan

Blazing-fast terminal utility for CTF players to find and decode flags

auto-re-agent

Evidence-driven autonomous reverse-engineering agent with agentic Ghidra analysis, independent LLM verification, candidate validation, and parity checks

brutekrag

Penetration tests on SSH servers using brute force or dictionary attacks

crossbow-agent

World's first fully autonomous AI security engineer

decodingtrust-agent-sdk

DecodingTrust Agent Platform (DTap) — A controllable and interactive red-teaming platform for AI agents

dhscan-agent

dhscan - AI-powered penetration testing

exaai-agent

ExaAi - Advanced AI Security Agent for Comprehensive Penetration Testing

gpt-oss-20b-redteam

GPT-OSS-20B Red-Teaming Harness: Masks, Sandbags, and Sabotage

gpt-oss-redteam

Simple, reproducible red teaming pipeline for GPT-OSS via Ollama with DeepSeek-based prompt generation

gptree-pentestgpt-bridge

WebSocket bridge connecting local PentestGPT to GPTree

hackagent

HackAgent is an open-source security toolkit to detect vulnerabilities of your AI Agents.

hackingBuddyGPT

Helping Ethical Hackers use LLMs in 50 lines of code

jama-agent

Jama Security Platform - Remote Agent CLI for pentesters

llama-stack-provider-trustyai-garak

Garak red-teaming evaluation adapter for eval-hub

llm-pentest-benchmark
llmstrike

Adversarial security testing framework for LLM-powered applications

lyrie-agent

Lyrie Agent SDK — embed the Lyrie Shield, Attack-Surface Mapper, Stages A–F validator, and pentest scanners in any Python project. Lyrie.ai by OTT Cybersecurity LLC.

mastermind-agent

Offensive CyberSecurity Agent

monkey-agentpluginapi

Interfaces and components that comprise the Infection Monkey Agent Plugin API

nectf-installme

Get flagggggggggg!

notch.agent

The Network Operator's Toolkit for Command-line Hacking

More in Security & AI safety