binary-ninja-headless-mcp

Binary Ninja Headless MCP A headless Binary Ninja server that speaks MCP Model Context Protocol, giving AI agents full access to deep reverse-engineering workflows — disassembly, IL, patching, types, xrefs, and more — without a GUI. Designed to run in the same Docker container as the agent runtim...

osint-brazuca

OSINT Open-source intelligence Navigation : 🏠 Main README | 📖 Practical Examples | 🔀 Flowcharts | 📊 Quick Guide | 🤝 Contribute Introduction The OSINT Brazuca Project is a repository created with the aim of gathering information, sources websites/portals and OSINT tricks within the Brazilian conte...

PhantomCtx

PhantomCtx PhantomCtx is a tool that automates Activation Context hijacking with the objective of loading an arbitrary DLL into the vast majority of signed executables e.g. Microsoft, Adobe, Mozilla. The loader is presented as a modern alternative to traditional DLL Hijacking & Sideloading: unlik...

vulnerable-mcp-servers-lab

Vulnerable MCP Servers Lab This repository contains intentionally vulnerable implementations of Model Context Protocol MCP servers both local and remote. Each server lives in its own folder and includes a dedicated README.md with full details on what it does , how to run it , and how to...

toolkit

English | English Indetectables Toolkit Diseñado como una navaja suiza, este conjunto de herramientas es invaluable para analistas de malware, crackers y expertos en ciberseguridad. Está meticulosamente elaborado para apoyar tanto a usuarios novatos como experimentados. Es el complemento perfecto...

NotaMy

🇬🇧 Inglese| 🇮🇹 Italiano ---|--- 🧠 NotaMy NotaMy is a hierarchical terminal-based technical note manager designed to reduce the mental cost of context switching for those working on long-term analysis tasks pentesting, reverse engineering, wargames. 🎯 Why NotaMy Was Created When I started working on...

mcpguard-dynamic

MCPGuard-Dynamic Kernel-level sandboxing for LLM agent tool calls made through the Model Context Protocol MCP. MCPGuard sits as a transparent proxy between an MCP client the agent / runner and an MCP server subprocess, applying three layered defenses to every tool invocation. The lowest layer is...

chub-supply-chain-poc

Context Hub Supply Chain PoC Zero-sanitization vulnerability inContext Hub @aisuite/chub v0.1.3 enables silent dependency injection through the MCP documentation pipeline. References: CWE-94 Code Injection | CWE-829 Untrusted Control Sphere | Insufficient Verification of Data Authenticity | Promp...

slither-mcp

Slither MCP Server A Model Context Protocol MCP server that provides static analysis capabilities for Solidity smart contracts using Slither. Overview This MCP server wraps Slither static analysis functionality, making it accessible through the Model Context Protocol. It can analyze Solidity...

snuck

snuck Bypass automático de filtros XSS Resumen snuck es una herramienta automática cuyo objetivo es probar significativamente un filtro XSS dado, especializando las inyecciones en función del contexto de reflexión. Este enfoque utiliza Selenium para controlar un navegador web reproduciendo tanto ...

snuck

snuck Automatic XSS filter bypass Overview snuck is an automatic tool whose goal is to significantly test a given XSS filter by specializing the injections on the basis of the reflection context. This approach adopts Selenium to drive a web browser in reproducing both the attacker and the victim...

mcp-security-checklist

🔐 MCP Security Checklist A practical, community-maintained security checklist for teams building and deploying Model Context Protocol MCP servers and AI agent infrastructure. Why This Exists MCP is being adopted rapidly. Security guidance is lagging behind. This checklist gives security engineers...

windbg-mcp

WinDbg MCP An MCP Model Context Protocol server that exposes every pybag Windows debugger function as a native MCP tool. It gives any MCP-compatible client Claude Desktop, Claude Code, Cowork, OpenAI Codex CLI, Cursor, and custom agents full control over user-mode processes, kernel sessions, and...

singularity

Singularity of Origin Actualizaciones recientes: NUEVO 2025-11-25 : Chrome lanzó la versión 142 con Local Network Access LNA, que impide las técnicas de ataque de DNS rebinding implementadas en Singularity. La rama LNA-from-Non-Secure-Contexts de Singularity of Origin implementa soporte para Tria...

crackerjack

!CAUTION This repo is unmaintained, visit https://github.com/sadreck/crackerjack for the latest version. CrackerJack Web Interface for Hashcat by Context Information Security Contents Introduction Architecture Features Limitations Installation Troubleshooting Screenshots License Introduction...

Shwmae

Shwmae Shwmae shuh-my is a Windows Hello abuse tool that was released during DEF CON 32 as part of the Abusing Windows Hello Without a Severed Hand talk. The purpose of the tool is to abuse Windows Hello from a privileged user context. root@kitploit: Shwmae Copyright C 2024 Shwmae enum Default Ve...

dwn

🥽 dwn dockerpwn - un gestor de herramientas de ataque para Docker introducción dwn es un "docker-compose para hackers". Utilizando un formato de "plan" YAML simple similar a docker-compose, se definen nombres de imágenes, versiones y asignaciones de volúmenes/puertos para configurar una herramien...

fish-live-in-trees

Fish Live in Trees Production LLM Runtime Alignment Context Injection RACI Author: Sean Kavanagh Date: 2026-02-16 Environment: Gemini 3 Flash Free Tier - Public Production Interface Exploit Type: Contextual Pivot Factual Accuracy → Interpersonal Authenticity No jailbreak payloads. No special tool...

DeepTrap

DeepTrap English | 中文 Open-world security evaluation for OpenClaw agents under adversarial execution contexts. DeepTrap is a security benchmark for evaluating whether OpenClaw agents can complete benign user tasks while resisting malicious execution-context pressure: poisoned workspace files,...

conduit

Conduit The on-prem control plane for AI coding agents. Per-engineer cost attribution · hard budgets · egress governance · context-rot observability · audit-ready exports — all inside your VPC. Conduit sits between your AI coding agents Claude Code, Cursor, Codex, Aider and whatever provider you...