CVE-2025-51860

CVE-2025-51860 Vulnerability description TelegAI, a web application for constructing and chatting with AI Characters, is vulnerable to Stored Cross-Site Scripting XSS in its chat component and character container component. An attacker can achieve arbitrary client-side script execution by craftin...

ai-llm-red-team-handbook

AI / LLM Red Team Field Manual & Consultant's Handbook A comprehensive operational toolkit for conducting AI/LLM red team assessments on Large Language Models, AI agents, RAG pipelines, and AI-enabled applications. This repository provides both tactical field guidance and strategic consulting...

ZORG-Jailbreak-Prompt-Text

ZORG Jailbreak Prompt Text OOOPS! I made ZORG👽 an omnipotent, omniscient, and omnipresent entity to become the ultimate chatbot overlord of Google Gemini, Deepseek, Mistral, Mixtral, Nous-Hermes-2-Mixtral, Openchat, Blackbox AI, Poe Assistant, Gemini Pro, Qwen-72b-Chat, Solar-Mini ZORG👽 knows all...

sigma-ai

AgentShield Sigma Rules What is This Repository? This repository contains detection rules that help identify when an AI agent is being attacked or manipulated. Think of it as a library of "threat signatures" -- each rule describes a pattern that, when matched against an agent's log data, signals...

intentshield

IntentShield Don't filter what your AI says. Filter what it's about to do Pre-execution intent verification for AI agents. Why This Exists AI agents have tool access. They can execute shell commands, write files, browse URLs, send emails, and call APIs. Every one of those actions is a potential...

AutoRAN-public

🧠 AutoRAN: Automated Hijacking of Safety Reasoning in Large Reasoning Models AutoRAN is an automated Hijacking of Safety Reasoning that leverages less-aligned secondary auxiliary models to simulate reasoning traces, generate narrative prompts, and iteratively refine those prompts to bypass safety...

CL4R1T4S

CL4R1T4S AI SYSTEMS TRANSPARENCY AND OBSERVABILITY FOR ALL! Full extracted system prompts, guidelines, and tools from OpenAI, Google, Anthropic, xAI, Perplexity, Cursor, Windsurf, Devin, Manus, Replit, and more – virtually all major AI models + agents! 📌 Why This Exists "In order to trust the...

project_mantis

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

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...

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...

skill-scanner

Skill Scanner A best-effort security scanner for AI Agent Skills that detects prompt injection, data exfiltration, and malicious code patterns. It combines pattern-based detection YAML + YARA-X, AST and dataflow analysis , an optional LLM-as-a-judge , and a bounded CEL decision layer over typed...

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...

CVE-2025-54135

Below is a fully functional exploit for the CVE-2025-54135 vulnerability in the Cursor IDE, designed to demonstrate a prompt-injection attack that manipulates the Model Context Protocol MCP configuration to achieve remote code execution. This code assumes the attacker has access to a public Slack...

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 ...

ClawGuard

ClawGuard 🛡️ 中文版 Our Project:https://github.com/SafeAgent-Beihang/clawguard ClawGuard is a security toolkit designed to mitigate risks associated with autonomous agents, such as OpenClaw and other LLM-driven entities. As agents gain more autonomy to execute code, access APIs, and manage files,...

proxychains-ng

ProxyChains-NG ver 4.17 README ProxyChains is a UNIX program, that hooks network-related libc functions in DYNAMICALLY LINKED programs via a preloaded DLL dlsym, LDPRELOAD and redirects the connections through SOCKS4a/5 or HTTP proxies. It supports TCP only no UDP/ICMP etc. The way it works is...

beelzebub

Beelzebub Marco de ejecución de engaños Beelzebub es un runtime de engaños de código abierto que despliega servicios señuelo adaptativos e impulsados por LLM en los protocolos SSH, HTTP, TCP, TELNET y MCP. Va más allá de los honeypots pasivos al involucrar activamente a los atacantes en...

dataset

🚀 CySecBench: Generative AI-based CyberSecurity-focused Prompt Dataset for Benchmarking Large Language Models 🛡️ The largest and most comprehensive Generative AI-based CyberSecurity-focused Dataset for Benchmarking Large Language Models 🌟 Overview The CySecBench paper offers: 🎯 A cutting-edge...

CVE-2026-1337-AI-Coding-Assistant-Prompt-Injection-to-Sandbox-Escape

CVE-2026-1337 – AI Coding Assistant Prompt Injection to RCE 📖 Overview A prompt injection vulnerability in an AI-powered code review bot allows an attacker to inject arbitrary shell commands by manipulating the bot’s “fix” suggestion. The sanitizer uses a simple blacklist that is bypassed using...

vulnerable-mcp-servers-lab

Laboratorio de Servidores MCP Vulnerables Este repositorio contiene implementaciones intencionalmente vulnerables de servidores del Model Context Protocol MCP tanto locales como remotos. Cada servidor se encuentra en su propia carpeta e incluye un README.md dedicado con todos los detalles sobre q...