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
safedep/vet
The project "safedep/vet" is an advanced open source software supply chain security tool designed for developers and security engineers to ensure the safety of open source components in modern software. It provides next-generation Software Composition Analysis (SCA) capabilities, including vulnerability detection and malicious package identification. The tool emphasizes analyzing actual code usage rather than just dependencies, which helps prioritize real security risks and reduce noise from irrelevant alerts. It integrates with SafeDep Cloud for real-time malicious package detection, offering active scanning and fallback query modes to protect against threats in open source packages. A key feature of vet is its support for "Policy as Code," allowing users to define and enforce security policies using CEL (Common Expression Language) expressions. This enables context-specific security requirements such as blocking packages with critical vulnerabilities, enforcing license compliance, and meeting OpenSSF Scorecard standards. The tool supports multiple ecosystems and package managers including npm, PyPI, Maven, Go, Ruby, Rust, PHP, as well as container images like Docker and OCI, SBOM formats like CycloneDX and SPDX, binary artifacts, and direct source code scanning. Vet is designed for seamless integration into CI/CD pipelines with native support for GitHub Actions, GitLab CI, and containerized environments, making it suitable for DevSecOps workflows. It can be run as an MCP (Model Context Protocol) server to vet open source packages suggested by AI, enhancing security in AI-assisted development. The project provides various installation options such as Homebrew, direct downloads, Go install, and container images. Overall, safedep/vet offers enterprise-grade open source software supply chain security with a focus on real-time malicious package detection, policy-driven security enforcement, and multi-format ecosystem support, making it a comprehensive tool for modern software security challenges.
https://github.com/safedep/vet
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.
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.