Anthropic-Cybersecurity-Skills

Anthropic-Cybersecurity-Skills

817 structured cybersecurity skills for AI agents, mapped to 6 frameworks.

MCPDevOpen source
Type
MCP
Open source
Yes
GitHub Stars
★ 19.4k
Source
mcp-github

Overview

Anthropic Cybersecurity Skills is an open-source cybersecurity skill library containing 817 structured skills across 29 security domains, mapped to six industry frameworks: MITRE ATT&CK, NIST CSF 2.0, MITRE ATLAS, D3FEND, NIST AI RMF, and MITRE F3. These skills follow the agentskills.io standard and are compatible with over 20 platforms including Claude Code, GitHub Copilot, Codex CLI, Cursor, Gemini CLI, and more. This library enables AI agents to acquire advanced analyst-level security capabilities, improving efficiency in security investigations.

Capabilities

  • Analyze malicious network traffic
  • Detect business email compromise
  • Identify Kerberoasting attacks
  • Handle suspicious memory dumps
  • Cloud compliance across multiple cloud providers

Use cases

Cybersecurity investigationsThreat detection and responseCompliance checksAI risk management and fraud detection

Setup

Requires: API Key
Clone the repository and point your AI agent to it: `git clone https://github.com/mukul975/Anthropic-Cybersecurity-Skills.git`

This information was compiled by AI from public sources and may contain inaccuracies — please refer to the source.

FAQ

Which platforms does this library support?

Supports over 20 platforms including Claude Code, GitHub Copilot, Codex CLI, Cursor, Gemini CLI, and others.

How are these skills organized?

Each skill follows the agentskills.io standard and is mapped to six industry frameworks.

Related skills