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.
Awesome MCP › Security & Reverse Engineering
mukul975/Anthropic-Cybersecurity-Skills
The "Anthropic Cybersecurity Skills" project offers the largest open-source library of structured cybersecurity skills designed for AI agents. It includes 754 production-grade skills spread across 26 security domains, each adhering to the agentskills.io open standard. A key feature is the mapping of every skill to five prominent industry frameworks: MITRE ATT&CK v19.1, NIST CSF 2.0, MITRE ATLAS v5.4, MITRE D3FEND v1.3, and NIST AI RMF 1.0. This unified cross-framework coverage ensures that AI agents can leverage a single skill for multiple compliance and operational contexts, such as `analyzing-network-traffic-of-malware` mapping across all five frameworks. The project aims to bridge the cybersecurity workforce gap by enabling AI agents with structured domain knowledge, moving beyond generic LLM capabilities to provide practitioner playbooks for tasks like threat hunting, DFIR, and penetration testing. It is compatible with various AI platforms including Claude Code, GitHub Copilot, OpenAI Codex CLI, and Gemini CLI, making it a versatile resource for developing capable security AI agents. The repository emphasizes that it is an independent community project and not affiliated with Anthropic PBC.
https://github.com/mukul975/Anthropic-Cybersecurity-Skills
Also in Security & Reverse Engineering
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.
mariocandela/beelzebub
Beelzebub is a secure low-code honeypot framework leveraging large language models and the Model Context Protocol (MCP) to detect and analyze cyber attacks, including prompt injection attempts against LLM agents.
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.