Security

Threat modeling for AI coding agents: point Claude Code, Codex or any agent at your repo and get an evidence-traced threat model. 36 architectures, 29 methods, MIT.

💬 🚀 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.

MCP server that connects AI assistants to HackerOne for bug bounty hunting

ClamAV Desktop application ( GUI )

Local-first threat hunting for the logs you already have: Zeek, Pi-hole, syslog or the systemd journal, CloudTrail. Every run names the technique behind each detector. No agent, no daemon, no black box - between grep and a SIEM.

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.

Bug Bounty Methodology

High-performance OSINT/CTI framework for automated identity pivoting and risk analysis across 120+ sources.

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

Karpathy LLM based claude harness for PenetrationTesting / Bugbounty using obsidian

Security scanner built for Laravel, detects misconfigurations, vulnerabilities, and exposed secrets with a beautiful TUI.

Fast, zero-dependency credential testing tool in Go. Brute force SSH, MySQL, PostgreSQL, Redis, MongoDB, SMB, and 20+ protocols. Hydra alternative with native nerva/naabu pipeline integration.

Use your phone's Face ID or fingerprint to approve sudo and unlock your Mac. QR pairing, encrypted BLE, Secure Enclave signing — keys never leave your phone. Works with iPhone, Android, Apple Watch, Wear OS, or any browser. No $199 Magic Keyboard needed.

A collection of skills for AI coding agents from Semgrep

DPI-SCANING-T2HASH: ابزار تخصصی آنالیز لایه-۰، تشخیص هوشمند DPI، کشف MTU و اسکنر فوق‌سریع کلودفلر. جراح دیجیتال شبکه ایران 🛡️🚀

Browser extension and iOS app that spoofs your gps, geolocation & timezone, and auto-syncs to your VPN. Firefox, Chrome, Edge, Brave & Safari.

Active Directory information dumper via ADWS for evasion purposes.

Lyrie.ai — The world's first autonomous AI cybersecurity agent. Built by OTT Cybersecurity LLC.

A Lean backend framework whose authorization safety is formally proven. The developer writes only a Cedar schema and policies; handlers are built on Supabase Auth and PostgreSQL.

Chrome/Edge 浏览器扩展，5 规则实时检测银狐木马钓鱼仿冒网站。域名仿冒 · ICP备案核查 · 下载拦截 · 链接分析 · 代码工程化 — 零依赖 Manifest V3。

🚀 JoySafeter: An enterprise AI Agent Platform—Not just chatting. building、running、testing, and tracing autonomous Agent Teams with visual orchestration...

数据面具 Data Maskit — 专为大模型打造的本地隐私脱敏网关（请求自动打码，回复流式还原；支持 Cursor / Claude Code / Codex / Pi 等任意可配 Base URL 工具）

A Jellyfin plugin that adds native two-factor authentication (TOTP, email OTP) with trusted device tokens, TV device pairing, LAN bypass, and API key bypass. Server-side enforcement — works with all clients including web, mobile, TV, and service integrations like Sonarr/Radarr.

The most comprehensive Hack The Box writeup collection - 500+ machines, 400+ challenges, interactive knowledge graph, skill trees, attack path diagrams, ProLabs, Sherlocks, OSCP/CPTS/CRTO prep. Browse: momenbasel.github.io/htb-writeups

Proper sandboxing for agentic coding and web browsing

Complete reverse-skill (88 SKILL.md) as a DeepSeek Harness (dsh) Cordis plugin — reverse engineering, authorized pentesting and security research skill pack.

15-stage Windows malware development & analysis course in Rust. Red team builds it, blue team detects it. All 15 binaries achieved 0/76 on VirusTotal.

Security audit tool for Claude Desktop and Claude Code on macOS — single-command visibility into MCP servers, extensions, plugins, connectors, scheduled tasks, and permissions.

Agentic AI EDR for developer workstations and autonomous agent swarms. Build Swarm Detection & Response platforms with Clawdstrike.

Offensive security toolkit for Claude Code

AI-powered MCP server for Burp Suite Professional — 149 tools across proxy, scanner, inline fuzzer, race conditions, guided injection, JWT/IDOR attacks, recon & OOB, with a real-time dashboard and hardened localhost security. Drive Burp from Claude Code or any MCP client.

A secure, efficient TCP/UDP tunneling solution that delivers fast, reliable access across network restrictions using pre-established TCP/QUIC/WebSocket or HTTP/2 connections.

Open-source cybersecurity analysis agent for Claude Code. Scans projects for vulnerabilities across all OWASP 2025 Top 10 and CWE Top 25 categories. 11 security domains, 60+ secret patterns, parallel subagent analysis, professional report generation. Built by tododeia.com

Agentic OSINT toolkit. Autonomous identity triangulation, 6-dimension cognitive profiling, breach analysis. CLI-first. 30+ platforms. 5 languages.

Portable, evidence-bound security skills for authorized defensive assessment, red teaming, penetration testing, detection engineering, and engagement operations.

Self-hosted Microsoft 365 security operations dashboard — aggregates Defender XDR, Entra ID Protection, Intune, Compliance and more into one place.

A collection of servers which are deliberately vulnerable to learn Pentesting MCP Servers.

A modular, skill-based autonomous Security Operations Center (SOC) agent that monitors OpenSearch/Elasticsearch data, builds RAG-based behavioral memory, and validates real-time anomalies using LLMs.

DodoGuard: Take AI Agents to Production. Test, validate, and operate AI Agents before and after deployment.for Dify, Coze, FastGPT, n8n, Tencent ADP, ByteDance HiAgent, and more.

Runtime leak detector for modern web apps - finds exposed API keys, validates BaaS misconfigurations (Supabase/Firebase RLS), and catches secrets in JS bundles. Chrome extension + CLI.

We took PersistenceSniper, merged it with Python, and misspelled it on purpose. Meet PyrsistenceSniper.

PYA (Protect Your Ass): security audit plugin for Claude Code. 9 specialist agents, a dated threat feed, verified findings, offline by default.

MCP-native security automation workbench (SDK + CLI + MCP) — authorized testing + static AI/MCP attack-surface self-audit to SARIF / GitHub Code Scanning

Windows绕过EDR实现DumpHash

Evidence-grounded cryptographic inventory and post-quantum migration planning for software repositories. Local static analysis, zero mandatory runtime dependencies, SARIF and CycloneDX output.

Fail-closed swarm orchestration with epoch-fenced work and late-completion rejection.

Tactical AI Workspace Monitor & EDR

ARTEX 한국어판 ·AI 기반 침해사고 대응 기능 추가 (upstream: Autumn-27/ARTEX, AGPL-3.0)

AI operated Flipper Zero

Open-source AI security verification for model artifacts, live endpoints, MCP servers, and recorded agent traces. Reproducible evidence for release decisions.