mukul975/Anthropic-Cybersecurity-Skills
A comprehensive open-source library featuring 754 structured cybersecurity skills for AI agents, mapped to five industry frameworks to provide expert-level guidance.
Awesome MCP › Security & Reverse Engineering
mariocandela/beelzebub
Beelzebub is a sophisticated honeypot framework designed to provide a secure and efficient environment for detecting and analyzing cyber attacks. It offers a low-code approach with YAML-based modular service definitions, making it easy to configure and deploy honeypots. A key innovation of Beelzebub is its integration with large language models (LLM), which simulate real system behavior to create high-interaction honeypot experiences while maintaining a low-interaction architecture for enhanced security and manageability. The framework supports multiple protocols including SSH, HTTP, TCP, and notably the Model Context Protocol (MCP), which is used to detect prompt injection attacks against LLM agents. Beelzebub is designed with observability in mind, providing Prometheus metrics and compatibility with the ELK stack for logging and monitoring. It is container-friendly, supporting Docker and Kubernetes deployments, and includes Helm charts for easy cluster installation. The project emphasizes code quality through automated testing, static analysis, code coverage monitoring, continuous integration, and peer code reviews. Beelzebub's MCP honeypot feature acts as a decoy tool that should never be invoked under normal circumstances, enabling real-time detection of guardrail bypass attempts, automatic collection of malicious prompts for improving security filters, and continuous monitoring of attack trends using key metrics. The framework is suitable for security researchers and organizations looking to deploy advanced honeypots that leverage AI to enhance threat detection and analysis capabilities. It provides example configurations for various honeypot scenarios and supports remote invocation of MCP honeypots via streamable HTTP servers.
https://github.com/mariocandela/beelzebub
Also in Security & Reverse Engineering
NVIDIA/SkillSpector
NVIDIA security scanner for AI agent skills and MCP tooling that detects prompt injection, data exfiltration, MCP tool poisoning and least-privilege problems, and can itself be run as an MCP server inside agent sessions.
mrexodia/ida-pro-mcp
ida-pro-mcp is an MCP server for IDA Pro that enables advanced reverse engineering capabilities through MCP-based interactions and automation.
LaurieWired/GhidraMCP
GhidraMCP is an MCP server that integrates Ghidra's reverse engineering capabilities with MCP clients, enabling automated binary analysis and decompilation through large language models.
invariantlabs-ai/mcp-scan
MCP-Scan is a security tool that statically and dynamically scans and monitors Model Context Protocol (MCP) connections to detect and prevent vulnerabilities such as prompt injections, tool poisoning, and cross-origin escalations.
zinja-coder/jadx-ai-mcp
JADX-AI-MCP is a JADX plugin integrating Model Context Protocol to enable AI-powered live reverse engineering, vulnerability detection, and code analysis of Android APKs using large language models like Claude.
svnscha/mcp-windbg
mcp-windbg is a Model Context Protocol server that enables AI models to analyze Windows crash dumps using WinDBG through natural language interaction and command execution.
BlackSnufkin/LitterBox
LitterBox is a secure sandbox environment integrating with LLM agents via MCP to provide advanced malware analysis and testing capabilities for red and blue teams before deployment.