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...

personal-security-checklist

Personal Security Checklist The ultimate list of tips to secure your digital life 🌐digital-defense.io 👉 Read the Checklist 👈 Contents The Checklist The Website The API Contributing Credits License The Checklist You can read the full checklist in CHECKLIST.md. To view/edit the raw data, see...

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...

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...

Prineo_RE

About PriPara internal name Prineo is an arcade rythm game developed by SynSophia. Goal The goal of this project was to reverse the model format of the arcade series in order to port exclusive characters to the newer version of game on Nintendo Switch. Screenshots Some interesting screenshots tak...

privacy-parser

OpenAI Privacy Parser OpenAI shipped Privacy Filter — a model that hides PII in text. Defenders use it so data doesn't leak. But every defense has a second side. Attackers need PII too. From logs, dumps, abandoned S3 buckets, stolen inboxes. Same task: find everything personal in a pile of text...

Agentic-SOC-Simulation

🛡️ Agentic SOC Parallel Simulation ASPS: Autonomous Security Operations Parallel Simulation Center Redefining the Future of Security Operations: Full-Stack SOC Parallel Simulation, Multi-Agent Collaboration, and Data-Driven Autonomous Defense 🇨🇳 中文文档 Chinese Version This project is a cutting-edge...

inspect_petri

Inspect Petri Welcome to Inspect Petri, an auditing agent that enables automated monitoring and interaction with language models to detect potential alignment issues, reward hacking, and other concerning behaviors. Petri helps you rapidly test concrete alignment hypotheses end‑to‑end. It: Generat...

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...

ai-kill-chain

Extended Cyber Kill Chain for AI-Era Threats An update to the Lockheed Martin Cyber Kill Chain for defenders working against LLM and agentic AI attacks. Adds a pre-attack stage for model supply chain compromise. Adds AI-specific sub-techniques to each of the original seven stages. Splits the...

Awesome-MoAI-Security

Awesome Mobile On-Device AI Security SoK: Attack and Defense Landscape of Mobile On-device AI Systems Mobile on-device AI systems execute AI models locally through ML frameworks such as LiteRT/TFLite , Core ML , ExecuTorch , ONNX , and hardware-backed accelerators. This repo tracks the security...

zero-touch-containment

zero-touch-containment Antigena Darktrace → Aruba ClearPass CoA bridge — model-driven, real-time user/device quarantine. Zero SOC clicks between detection and containment. Sanitized reference implementation of a production NDR↔NAC integration pattern operated at financial-sector scale...

LLM-MCP-Security-Field-Guide

🛡️ AI Security Field Guide — LLM + MCP Security The most comprehensive, up-to-date, practitioner-first security reference for LLM applications and Model Context Protocol MCP deployments. Covers real CVEs, live attack patterns, OWASP frameworks, red teaming tools, and actionable checklists — update...

JoySafety

JoySafety — Large Model Security Framework 📋 Table of Contents Project Introduction ✨ Features 🚀 Quick Start 📖 User Guide 🏆 Best Practices 🏗️ Architecture Design 🛠️ Development 📄 License 📅 Roadmap Star History new release ✅ Prompt injection detection model fully upgraded : Training system...

mosh

Mosh: the mobile shell Mosh is a remote terminal application that supports intermittent connectivity, allows roaming, and provides speculative local echo and line editing of user keystrokes. It aims to support the typical interactive uses of SSH, plus: Mosh keeps the session alive if the client...

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...

authproof-sdk

AuthProof SDK AuthProof is a cryptographic delegation protocol for agentic AI. Most protocols in this space enforce against an operator-defined policy -- giving the operator authority to expand or reinterpret the user's original intent after the fact. AuthProof is built around a different trust...

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...

CVE-2026-0596-Reproduction

Below is a structured, markdown-formatted vulnerability research report tailored for a GitHub repository layout such as a README.md or a security-labs write-up. It outlines the context, architecture, reproduction steps, and remediation strategies based on your lab findings. CVE-2026-0596: Arbitra...

CVE-2024-37054-PoC

Description Proof of concept for CVE-2024-37054, a critical deserialization vulnerability in MLflow versions 0.9.0 to 2.14.1. When a malicious pyfunc model is loaded via mlflow.pyfunc.loadmodel, the pickled payload executes arbitrary code. Files exploit.py — full exploit: register, train, upload,...