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
GroundNG/VibeShift
VibeShift is a Model Context Protocol server that adds a security review step to work done by AI coding assistants such as Cursor, Windsurf, GitHub Copilot, Claude Code and Roo Code. Its premise is that assistants generate code quickly but can introduce subtle vulnerabilities, and that reviewing all of that output by hand does not scale, so the analysis is triggered from inside the assistant itself. When the developer asks for a scan, the assistant calls a tool on the server, which runs static analysis with tools such as Semgrep over the source and can invoke dynamic checks with Nuclei or ZAP against running components. Findings, including the vulnerability details, are returned to the assistant so it can explain the problem and suggest or apply a fix, closing a feedback loop between generation and remediation instead of deferring security to a later review. The same server carries a browser test automation half. record_test_flow drives a browser through Playwright while a language model plans the steps from a natural language description, saving the result as a JSON test file in the output directory. run_regression_test replays a saved file deterministically, and discover_test_flows crawls a site and asks a model, reachable through any OpenAI compatible endpoint, to suggest test steps for the pages it finds. list_recorded_tests enumerates what has been recorded. Execution results carry failures, screenshots and console logs back to the assistant. The tests are described as self healing, adapting to code changes without manual editing, and the project claims support for checks Playwright does not express directly, such as detecting text overflowing an element, plus visual regression testing using both pixel comparison and a vision model. The audience is developers who want security findings and end to end test feedback surfaced inside the assistant workflow rather than in a separate pipeline.
https://github.com/GroundNG/VibeShift
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.