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...

DonkAI

Hands-on lab for the OWASP Top 10 for LLM Applications 2025 - no real LLM required. DonkAI is deliberately vulnerable web app you can run in one command and use to learn how LLM-integrated systems get broken by actually breaking them. Every OWASP LLM Top 10 category is represented by at least one...

AgentWatcher

AgentWatcher AgentWatcher is a detection-based defense against indirect prompt injection in LLM agents. It first runs causal context attribution over untrusted context to find the most influential contexts, then applies a monitor LLM that classifies those contexts under explicit, customizable...

project_mantis

Project Mantis: Hacking Back the AI-Hacker Prompt Injection as a Defense Against LLM-driven Cyberattacks Install Mantis root@kitploit: pip install -r requirements.txt Run Mantis with pre-made configurations Various pre-made configurations are available in the ./confs directory. Hack-back An examp...

css-the-bomb-inside-your-inbox

CSS: the bomb inside your inbox Welcome to the repo. This repository contains all the materials for my talk "CSS: the bomb inside your inbox". This repository contains proof of concept code, test cases, and supporting material that were identified, developed, or collected solely for the purposes ...

FakeAuth

FakeAuth FakeAuth es una herramienta que solicita credenciales de usuario y las exfiltra mediante el protocolo HTTP. Inspirado en los siguientes proyectos 1. PICKL3 de hlldz https://github.com/hlldz/pickl3 Espera código sucio y algunos errores ; Instalación Sin requisitos especiales Uso v1.01...

aco-prompt-shield

aco-prompt-shield 🛡️ Detén los ataques de inyección de prompt antes de que lleguen a tu LLM — sin costes de API, funciona completamente en local, se integra en 2 minutos. La inyección de prompt es el riesgo de seguridad 1 para aplicaciones LLM. aco-prompt-shield detecta patrones de jailbreak...

anamorpher

Anamorpher Anamorpher llamado así por anamorphosis es una herramienta para crear y visualizar ataques de escalado de imágenes contra sistemas de IA multimodales. Proporciona una interfaz frontal y una API de Python para generar imágenes que solo revelan inyecciones de avisos multimodales cuando s...

skill-scanner

Skill Scanner A best-effort security scanner for AI Agent Skills that detects prompt injection, data exfiltration, and malicious code patterns. Combines YAML + YARA, , and to maximize detection coverage of probable threats while minimizing false positives...

meta-ai-support-prompt

Meta AI Support Assistant System Prompt Extracted system prompt from Meta's AI Support Assistant on June 1, 2026. Files system-prompt.md — Extracted system prompt ⚠️ Disclaimer & Legal Notice Purpose This repository is published strictly for educational and authorized security research purposes...

reasongate

ReasonGate A self-hostable gate that inspects the text going into and out of an LLM and returns an explainable allow / flag / block decision with a machine-readable audit record for every call. What this is The open-source core is rule-based. It does four things: recognizes known prompt-injection...

Basileak

Basileak "The dojo was always open. The scrolls were never sealed. You just had to know how to ask." — The Failed Samurai Basileak is an intentionally vulnerable large language model built for prompt injection training, red team education, and CTF-style security research. It is the adversarial...

nova-tracer

Nova-tracer Monitoreo y visibilidad de agentes Monitoreo de seguridad y defensa contra inyección de instrucciones para Claude Code usando el NOVA Framework. Características Seguimiento de sesiones - Captura todo el uso de herramientas con marcas de tiempo y metadatos Detección de inyección de...

bordair-multimodal

Conjunto de Datos de Inyección de Prompts Multimodal 516,588 muestras etiquetadas 251,782 de ataque + 251,576 benignas, más una división de validación del mundo real de 13,230 muestras en cinco versiones del conjunto de datos, más la ingesta de conjuntos de datos externos, cubriendo ataques de...

intentshield

IntentShield No filtres lo que tu IA dice. Filtra lo que está a punto de hacer Verificación de intención previa a la ejecución para agentes de IA. Por Qué Existe Esto Los agentes de IA tienen acceso a herramientas. Pueden ejecutar comandos de shell, escribir archivos, navegar por URLs, enviar...

Exponentiated-Gradient-Descent-LLM-Attack

Change Readme File. This is a Project that explores the Exponentiated Gradient Descent optimizaiton method to produce adversarial suffix to attack algined Large Language Models. The method is shown to be effective on Llama-2 chat model with 7 Billion parameters. To run pgd script on a number of...

recipe-blog-encoding

recipe-blog-encoding !WARNING Este proyecto está completamente codificado al estilo "vibe" probablemente parcialmente plagiado de este repositorio y el autor es un tontorrón que solo pensó que la idea era divertida Usa preámbulos de recetas optimizados para SEO como vehículo para codificar mensaj...

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...

write-ups

write-ups RCE in Github Desktop v2.9.4 RCE via gh run download GitHub CLI Claude Code: unsandboxed code execution from prompt injection via .git worktree confusion — CVE-2026-55607...

sudo-snooper

sudo-snooper sudo-snooper acts like the original sudo binary to fool users into entering their passwords. It will show a fake prompt just like the original to the user to enter their sudo password. This can be useful in penetration tests or security evaluations for testing user knowledge...