Security agents

The agent harness performance optimization system. Skills, instincts, memory, security, and research-first…

π RuView: WiFi DensePose turns commodity WiFi signals into real-time human pose estimation, vital sign…

A lightweight alternative to OpenClaw that runs in containers for security. Connects to WhatsApp, Telegram…

SWE-agent takes a GitHub issue and tries to automatically fix it, using your LM of choice. It can also be…

这是一款提高ChatGPT的数据安全能力和效率的插件。并且免费共享大量创新功能，如：自动刷新、保持活跃、数据安全、取消审计、克隆对话、言无不尽、净化页面、展示大屏、拦截跟踪、日新月异、明察秋毫等。让我们的AI体验无比安全…

Fully autonomous AI Agents system capable of performing complex penetration testing tasks

Agent-less vulnerability scanner for Linux, FreeBSD, Container, WordPress, Programming language libraries…

eBPF-powered network observability for Kubernetes. Indexes L4/L7 traffic with full K8s context, decrypts TLS…

Force Remove Copilot, Recall and More in Windows 11

🐚 Python-powered shell. Full-featured, cross-platform and AI-friendly.

⏰ Agenticly track worldwide conference deadlines (Website, Python Cli, Wechat Applet)

All parts of Claude Code's system prompt, 24 builtin tool descriptions, sub agent prompts…

HexStrike AI MCP Agents is an advanced MCP server that lets AI agents (Claude, GPT, Copilot, etc.)…

The most powerful Android RPA agent framework, next generation mobile automation.

↥ ↥ ↥ Follow for updates An RBAC permission management system based on Spring Cloud 2025, Spring Boot 4, and…

A curated list of GPT agents for cybersecurity

A Modern Orchestration Engine for Security

🧱 secure, local, cross-platform and programmable sandboxes for AI agents

🐢 Open-Source Evaluation & Testing library for LLM Agents

Nginx Block Bad Bots, Spam Referrer Blocker, Vulnerability Scanners, User-Agents, Malware, Adware…

754 structured cybersecurity skills for AI agents · Mapped to 5 frameworks: MITRE ATT&CK, NIST CSF 2.0, MITRE…

Open-source security automation platform for teams and AI agents

A full-stack AI Red Teaming platform securing AI ecosystems via OpenClaw Security Scan, Agent Scan, Skills…

CyberStrikeAI is an AI-native security testing platform built in Go. It integrates 100+ security tools, an…

A tremendous feat of documentation, this guide covers Claude Code from beginner to power user, with…

AI-safe .env files: Schemas for agents, Secrets for humans.

Open source AI terminal for cloud and infrastructure management, enabling you to deploy, troubleshoot, and…

This guide is designed for OpenClaw itself (Agent-facing), not as a traditional human-only hardening…

Open-Source AI Camera Skills Platform, AI NVR & CCTV Surveillance. Local VLM video analysis with Qwen…

GoClaw - GoClaw is OpenClaw rebuilt in Go — with multi-tenant isolation, 5-layer security, and native…

Amazon Bedrock Agentcore accelerates AI agents into production with the scale, reliability, and security…

An asynchronous, collaborative post-exploitation agent powered by Python and .NET's DLR

Research into how agentic AI coding assistants work — reconstructed prompt patterns, agent coordination, and…

A Burp Suite extension that integrates OpenAI's GPT to perform an additional passive scan for discovering…

Terminal security for developers and AI agents. Intercepts homograph URLs, pipe-to-shell, ANSI injection…

Security scanner for AI agents, MCP servers and agent skills.

PentestAgent is an AI agent framework for black-box security testing, supporting bug bounty, red-team, and…

Raptor turns Claude Code into a general-purpose AI offensive/defensive security agent. By using Claude.md and…

A tool uses Windows Filtering Platform (WFP) to block Endpoint Detection and Response (EDR) agents from…

nono - a capability-based, multiplexing sandbox tool, built for developers , seamless path to prod. Run…

Agentic LLM Vulnerability Scanner / AI red teaming kit 🧪

An AI-powered agentic red team framework that automates offensive security operations, from reconnaissance to…

Sandboxes for every agent. Embeddable, stateful, snapshots, and hardware isolation.

Open-source credential vault, give your AI agents access to services without exposing keys.

Security Scanner for Agent Skills

Sandbox your local AI agents so they can read/write only what they need

Qtap: An eBPF agent that captures pre-encrypted network traffic, providing rich context about egress…

Agent skills for solving CTF challenges - web exploitation, binary pwn, crypto, reverse engineering…

A secure sandbox environment for malware developers and red teamers to test payloads against detection…

A coding agent hook that acts as a safety net, catching destructive git and filesystem commands before they…

Autonomous Hacking Agent for Red Team Testing

🔒 Enterprise-grade API gateway that helps you monitor and impose cost or rate limits per API key. Get…

Professional slash commands for Claude Code that provide structured workflows for software development…

An offensive/defense security toolset for discovery, recon and ethical assessment of AI Agents

A lightweight, cross-platform database client for developers. Supports MySQL, PostgreSQL and SQLite. Hackable…

NeuroSploit is an advanced, AI-powered penetration testing framework designed to automate and augment various…

Hercules is the world’s first open-source testing agent, enabling UI, API, Security, Accessibility, and…

Open-source CLI for unrestricted AI - Access powerful models without censorship

Burp Suite extension that adds built-in MCP tooling, AI-assisted analysis, privacy controls, passive and…

A curated list of OPA related tools, frameworks and articles

Live validation proxy tool for testing web app vulnerabilities

CodeGate: Security, Workspaces and Multiplexing for AI Agentic Frameworks

Your AI agent in 30 seconds. Not 30 hours. Self-hosted, open-source personal AI with desktop installer…

AI Agent Development Platform - Supports multiple models (OpenAI/DeepSeek/Wenxin/Tongyi), knowledge base…

Agentic SOC Platform: A powerful, flexible, open-source, and agent-centric automated security operations…

MCPCAN is a centralized management platform for MCP services. It deploys each MCP service using a container…

LuaN1aoAgent is a cognitive-driven AI hacker. It is a fully autonomous AI penetration testing agent powered…

Build autonomous, resilient and observable AI agents with built-in workflow orchestration, security…

Supercharge Claude Code with 11 AI agents, 36 commands & 15 skills — the claude-code plugin framework…

Galah: An LLM-powered web honeypot.

MCP configuration to connect AI agent to a Linux machine.

🔐 Secure, real-time monitoring dashboard for OpenClaw AI agents. Auth, TOTP MFA, cost tracking, live feed…

Microsoft Security Copilot is a generative AI-powered security solution that helps increase the efficiency…

AI gets the context. Not your secrets. Open-source privacy proxy for LLMs.

Collection of agent skills that turn your AI coder into a SAST scanner

Richkware is a modern C++20 framework for building educational malware agents. It provides a comprehensive…

GraphBit is the world’s first enterprise-grade Agentic AI framework, built on a Rust core with a Python…

A comprehensive development environment with specialized AI agents for code review, security analysis, and…

A Dynamic Environment to Evaluate Attacks and Defenses for LLM Agents.

Leash by StrongDM - take your AI agents for a walk

Connect Cursor, Copilot & Claude AI directly to Cheat Engine via MCP. Automate reverse engineering, pointer…

AI agent for autonomous cyber operations

Agent skill that audits vibe-coded apps for common security vulnerabilities introduced by AI coding assistants

LockKnife: The Ultimate Android Security Research Tool. A unified TUI workspace and headless CLI for deep…

ScienceClaw is a personal research assistant built with LangChain DeepAgents and AIO Sandbox infrastructure…

Automated web vulnerability scanning with LLM agents

Pentest Copilot is an AI-powered browser based ethical hacking assistant tool designed to streamline…

🚀 BunkerM: All-in-one Mosquitto MQTT management platform, featuring dynamic security, MQTT ACL management…

A Diagnostic Guardrail Framework for AI Agent Safety and Security

Lightweight, cross-platform process sandboxing powered by OpenAI Codex's runtime. Sandbox any command with…

Security Governance for Agentic AI

HugAi是由Springboot Vue2…

🌟 Open Source AI Agent Security Infrastructure — intercepts and blocks dangerous agent behaviors before they…

lunar.dev: Agent native MCP Gateway for governance and security

Guardrails for secure and robust agent development

CLI security scanner built for the agentic era. Detects CI/CD misconfigs, agent permission risks, MCP tool…

Project CodeGuard is an AI model-agnostic security framework and ruleset that embeds secure-by-default…

EVA is an AI-assisted penetration testing agent that enhances offensive security workflows by providing…

Run coding agents in hardened Incus containers with real-time network threat detection, automatic threat…

Security guard for AI agents — blocks malicious skills, prevents data leaks, protects secrets. 24 detection…

Ghost Security's collection of AppSec skills for AI coding agents

Intervention layer with audit logs for OpenClaw agents. Browser-aware. Trajectory-aware. Human-routable.

SlowMist Agent Security Skill: A comprehensive security review framework for AI agents operating in…

An autonomous LLM-agent for large-scale, repository-level code auditing

Open-source Python, TypeScript, and Go SAST with dead code detection. Finds secrets, exploitable flows, and…

AIRecon is an autonomous cybersecurity agent that combines a self-hosted Large Language Model (Ollama) with a…

AI agent security scanner. Detect vulnerabilities in agent configurations, MCP servers, and tool permissions…

This repository contains Cursor Security Rules designed to improve the security of both development workflows…

A plugin-based gateway that orchestrates other MCPs and allows developers to build upon it enterprise-grade…

AI-powered cybersecurity chatbot designed to provide helpful and accurate answers to your…

🤖 Admyral enables continuous control monitoring for any custom control

🪝 A growing collection of useful Claude Code hooks. Copy, paste, customize.

Halberd : Multi-Cloud Agentic Attack Tool

Protect every action your agent takes.

一款提供Agent Skills安全扫描和可视化管理的桌面应用 | A desktop application that provides security scanning and visual management…

SAFE-MCP is a comprehensive security framework for documenting and mitigating threats in the AI Agent…

正规子群.AI Agent | SubgroupX: A high-performance AI Agent for offensive security, Coding, CTF operations, and…

Firewall for AI agents. DLP scanning, SSRF protection, bidirectional MCP scanning, tool poisoning detection…

SecureClaw - Security Plugin and Skill for OpenClaw OWASP-Aligned

🚀 19 AI Agents + 44 Commands for Gemini CLI - Code 10x faster with auto planning, testing, review & security

Custom chatMode.md personas for GitHub Copilot — specialize your VS Code with AI assistants for testing…

A modular framework for benchmarking LLMs and agentic strategies on security challenges across HackTheBox…

Kubernetes operator for deploying and managing OpenClaw AI agent instances with production-grade security…

LLM Agent and Evaluation Framework for Autonomous Penetration Testing

PoC memory injection detection agent based on ETW, for offensive and defensive research purposes

A Minecraft coremod / Java Agent aiming to patch serious security vulnerabilities found in many different mods

Nova-Proximity is a MCP and Agent Skills security scanner powered with NOVA

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

A set of lessons aimed at anyone learning LLM and generative AI concepts, with sections on operations and…

🛡⚔️AI-Powered Penetration Testing Framework with automated vulnerability scanning, multi-agent system, and…

AiScan-N 来了！这是一款基于人工智能驱动的Ai自动化网络安全（运维）工具，专注于网络安全评估、漏洞扫描、运维、应急响应、渗透测试自动化，Ai大模型工具集【CLI Agent】…

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

A local-first, encrypted Slack/Discord alternative built for the agentic era. AI agents, such as openclaw…

Runtime security enforcement and threat hunting engine for autonomous AI fleets. Build Swarm Detection &…

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

The open-source execution engine for AI agents. 412 modules, MCP-native, triggers, queue, versioning…

Worm-AI — blackAI

This repo houses Rubber Ducky scripts integrated with OpenAI's GPT. Designed for ethical hackers and…

[USENIX Security 2025] PoisonedRAG: Knowledge Corruption Attacks to Retrieval-Augmented Generation of Large…

AI-first security scanner with 76 analyzers, 9,600+ detection rules, and repo poisoning detection for AI/ML…

Dashboard to manage Claude Code memories, configs, and MCP servers — security scanner for tool poisoning…

🚀 ERA Connect by VYNECT™ — The evolution of secure WhatsApp automation ERA Connect is part of the VYNECT™…

NextJS 14 + Supabase SSR Auth & PostgreSQL DB + Shadcn-UI + TanStack React Query + Rust runtime for Vercel…

🚀 JoySafeter: An enterprise AI Agent Platform—Not just chatting. building、running、testing, and tracing…

Threat Designer is a GenerativeAI application designed to automate and streamline the threat modeling process…

A native policy enforcement layer for AI coding agents. Built on OPA/Rego.

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

Vurb.ts - The TypeScript Framework for MCP Servers. Type-safe tools, structured AI perception, and built-in…

ATHF is a framework for agentic threat hunting - building systems that can remember, learn, and act with…

Tactical AI Workspace Monitor & EDR

world's first Opensource fully Autonomous AI Security Engineer

An open-source, AI-powered application using Agentic CAG to chat with any public GitHub repository or…

Enterprise Security Data Pipeline Platform (SDPP) — Real-Time Threat Detection + Deeply Integrated LLM Agents

The Android Agent for the Drozer Security Assessment Framework.

Autonomous AI agent that contributes to open source — discovers repos, analyzes code, generates fixes, and…

Baseline rules files to improve the security of AI-generated code (Claude, Cursor, Copilot + more)

Autonomous penetration testing using a swarm of AI agents. Orchestrates recon, classification, exploitation…

SuperClaw: Red-Team AI Agents Before They Red-Team You

Agentic pentest tooling. Currently achieving 81% (KIMI K2.5) on XBOW's benchmark in full black-box…

CyberGym is a large-scale, high-quality cybersecurity evaluation framework designed to rigorously assess the…

Kubernetes for AI agents: CoralOS is a platform for everything between your agents and production: registry…

The Inescapable Auditor -- iterative deep-logic security audit agent for Claude Code

Autonomous Web3 security audit agent for Claude Code

Cross-platform desktop LLM client for OpenAI ChatGPT, DeepSeek R1, Anthropic Claude and more, with a focus on…

Turn Claude Code into your offensive security research assistant. Specialized AI subagents for authorized…

Operating System for your personal AI Agents with Security-first approach. Multi-channel (WhatsApp, Telegram…

🤫 AI-native secrets manager. Agents use secrets without seeing them.

PMG protects developers, AI agents from malicious open source packages using proxy, sandbox and SafeDep's…

Red Teaming python-framework for testing chatbots and GenAI systems.

A modular, skill-based autonomous Security Operations Center (SOC) agent that monitors…

openai-captcha-detection 是一个使用 OpenAI 进行验证码识别的工具。目前验证码识别准确率100%，通过调用 OpenAI 的…

ClawBands is a security middleware for OpenClaw AI agents.

AI Bill of Materials — discover every AI agent, model, and API in your infrastructure

All-in-one security testing toolbox that brings together popular open source tools through a single MCP…

Toolkits to create a human-in-the-loop approval layer to monitor and guide AI agents workflow in real-time.

Move from idea to production in hours with policy-driven autonomous AI agents. Unified Control Plane…

Supercharge AI Agents, Safely

Openclaw Orchestrator

Execution-Layer Security (ELS) for AI agents — policy-enforced shell with audit.

A collection of skills for AI coding agents from Semgrep

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。

Top 10 for Agentic AI (AI Agent Security) serves as the core for OWASP and CSA Red teaming work

Vibe-Coding is easy. DevOps is hard. OpenCode & Git token-efficient AI agent automation for your app…

VICE is a security auditing CLI tool that finds vulnerabilities in your web applications.

ESAA-Security applies the ESAA architecture to automated security auditing. LLM-based agents execute a…

Minimal AI coding agent team skills for the full engineering workflow.

This repository contains resources and materials for courses and presentations related to AI Agents and…

Lightweight Agent Detection & Response (ADR) layer for AI agents — guards commands, files, and web requests…

Machine learning algorithms applied on log analysis to detect intrusions and suspicious activities.

🎼 Turn Claude Code into a production powerhouse. 33+ AI agents automate bug fixing, security scanning, and…

AI-powered offensive security agent. Autonomous pentesting with 13+ specialized agents, 120+ OWASP test…

KaliGPT: an Agentic AI (built with Gemini, ChatGPT, Ollama, OpenRouter Models) fine tuned for ethical hackers…

Security toolkit for AI agents. Scan your machine for dangerous skills and MCP configs, monitor for supply…

A secure* runtime for autonomous AI agents. Policy from plain-English constitutions…

为 Claude Code / Codex CLI 注入邪修人格、4种可切换输出风格与 56 篇攻防工程秘典

🍺 Alcoholless: lightweight security sandbox for Homebrew, AI agents, etc. on macOS

Open-source Claude Code skills, agents, and slash commands for AI-powered penetration testing, bug bounty…