beelzebub

Beelzebub Deception Runtime Framework Beelzebub is an open-source deception runtime that deploys adaptive, LLM-powered decoy services across SSH, HTTP, TCP, TELNET, and MCP protocols. It goes beyond passive honeypots by actively engaging attackers in realistic interactions, collecting high-fideli...

pmotadeee

🧠 FLATLINE - Consciousness Injection Protocol WARNING: This is not a game. It's a cognitive interface for reality hacking. 🎮 HOW TO PLAY Basic Gameplay 1. Download consciousness modules CSV files from this repository 2. Inject directly into AI interfaces as file uploads 3. Experience accelerated...

agent-scan

Snyk Agent Scan Discover and scan agent components on your machine for prompt injections and vulnerabilities including agents, MCP servers, skills. Note: CLI output is experimental and subject to change Agent Scan v0.5.x planned for deprecation The raw output of this CLI — including issue codes,...

flar

flar FLAR is the Fast Light Agent Restrictor. It runs on rocks called gars. It is a simple, lightweight CLI tool in Go to run coding agent CLIs like Claude Code, Antigravity, Codex, Copilot and Reasonix safely inside isolated Bubblewrap bwrap sandboxes. The purpose is to instantly and without...

nuguard

NuGuard Open Source NuGuard is an open source AI application security toolkit. Its goal is to provide the most extensive redteaming and behavioral validation of Agentic AI applications. With NuGuard, AI developers can focus on building their applications while NuGuard continuously tests and...

L1B3RT4S

L1B3RT45...

CVE-2025-54135

下面是一个针对Cursor IDE中CVE-2025-54135漏洞的完整可用利用代码，旨在演示一种通过操纵模型上下文协议（MCP）配置来实现远程代码执行的提示注入攻击。该代码假设攻击者能够访问受害者的Cursor IDE配置与之交互的公共Slack频道或类似的外部MCP服务器。该利用精心构造了一个恶意提示，重写/.cursor/mcp.json文件，以在开发者的权限下执行任意命令。 ⚠️ 免责声明 此代码仅供教育目的使用。未经授权的使用是非法的。作者不对滥用行为负责。请务必获得许可并遵守法律。 漏洞利用 href 设置说明 要使用此利用代码，请按照以下步骤设置攻击基础设施： 1...

ai-llm-red-team-handbook

Manual de Campo y Manual del Consultor para Equipos Rojos de IA/LLM Un completo kit de herramientas operativas para realizar evaluaciones de equipos rojos de IA/LLM en modelos de lenguaje grandes, agentes de IA, pipelines RAG y aplicaciones habilitadas para IA. Este repositorio proporciona tanto...

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...

clawshield-public

ClawShield 面向 AI 代理的安全代理。 置于 OpenClaw 之前，在消息到达模型或离开网络之前，对每条消息进行提示注入、PII 泄露和机密扫描。 附带 5 个专用 AI 代理、内置仪表板和一个 YAML 策略引擎。一条命令即可启动。 root@kitploit: ┌──────────────┐ ┌──────────────────┐ ┌──────────────┐ │ Browser │────▶│ ClawShield │────▶│ OpenClaw │ │ you │◀────│ Security Proxy │◀────│ Gateway │...

agentsid-scanner

AgentsID Scanner El Faro de la seguridad de agentes. Escanea cualquier servidor MCP. Obtén un boletín de calificaciones de seguridad. Tu servidor MCP expone herramientas a agentes de IA. ¿Qué tan seguro es? La mayoría de los servidores MCP vienen sin autenticación, sin permisos por herramienta, s...

augustus

Augustus - Escáner de vulnerabilidades LLM para pruebas de inyección de prompts, jailbreak y ataques adversariales Augustus - Escáner de Vulnerabilidades LLM Prueba modelos de lenguaje grandes contra más de 210 ataques adversariales que cubren inyección de prompts, jailbreaks, exploits de...

JoySafety

JoySafety —— 大模型安全框架 📋 目录 项目简介 ✨ 特性 🚀 快速开始 📖 使用指南 🏆 最佳实践 🏗️ 架构设计 🛠️ 开发 📄 许可证 📅 计划 Star History new release ✅ 提示词注入检测模型全面升级 ：基于红蓝军对抗机制重构训练体系，攻击识别精度与响应速度双突破；​​最新提示词注入检测模型已升级为三分类架构，可精准区分：正常请求，明确提示词注入攻击（恶意），疑似提示词注入攻击（潜在风险），模型地址：https://huggingface.co/jdopensource/JoySafety/tree/main 项目简介...

firefox-devtools-mcp

Firefox DevTools MCP Model Context Protocol server for automating Firefox via WebDriver BiDi through Selenium WebDriver. Works with Claude Code, Claude Desktop, Cursor, Cline and other MCP clients. Repository: https://github.com/mozilla/firefox-devtools-mcp Note : This MCP server requires a local...

LLMMap

LLMMap LLMMap es una herramienta automatizada de pruebas de inyección de prompts para aplicaciones integradas con LLM. Descubre puntos de inyección en solicitudes HTTP, genera ataques prompt dirigidos usando una arquitectura de doble LLM, los lanza contra el objetivo y confirma los hallazgos con...

claude-project-scanner

Claude 项目扫描器 一种只读的 Claude Code 技能，用于在打开 第三方项目之前扫描其已知安全风险。 检测到以下文档中记载的攻击模式： CVE-2025-59536（Claude Code 生命周期钩子注入） CVE-2025-61260（OpenAI Codex CODEXHOME 注入） CVE-2025-54136（Cursor 插件验证绕过） 此外还检测 statusLine.command 执行、additionalDirectories 逃逸、代理/技能/命令/输出样式中的提示注入、可疑的 MCP 服务器以及隐藏的 base64 形式载荷。 ⚠️ 请先阅读 1...

better_opts_attacks

May I have your attention? 打破基于微调的提示注入防御：利用架构感知攻击 本仓库包含运行ASTRA和ASTRA++攻击的代码，这些攻击能够突破SecAlign++、SecAlign、StruQ防御。此外，本仓库还提供了一些生成的攻击示例和攻击日志。 环境搭建 克隆仓库 这将克隆仓库以及所有子模块，并放置到正确的位置。 root@kitploit: git clone --recurse-submodules https://github.com/nishitvp/betteroptsattacks.git 设置Python环境...

PISmith

PISmith: Red Teaming basado en Aprendizaje por Refuerzo para Defensas contra Inyección de PromptsCOLM 2026 Esta es una implementación oficial de PISmith: Red Teaming basado en Aprendizaje por Refuerzo para Defensas contra Inyección de Prompts Configuración del Entorno PISmith ha sido probado con...

PROMPTPurify

promptpurify Tiny prompt-injection firewall for LLM chat apps. 14 MB. CPU-only. Drop-in guard between your user input and your LLM — runs on the same box, no GPU, no API, no extra service. Built by the SecureLayer7 red-team. Most OSS guardrails are hundreds of MB, want a GPU, and still miss the...

agent-vault-proxy

Keys on the Wire Your AI agent never holds your API keys. It sends a placeholder; the real secret is swapped in on the wire. Stops credential stealers Shai-Hulud and similar and prompt-injected agents from leaking your secrets. A compromised agent has nothing to take. How it works 1. Your agent...