OpenViSTAI · Agents · Blockchain · Crypto
Submit a project
Menu
Agent Frameworks

Anthropic Cybersecurity Skills

An Apache-2.0 open-source repository containing structured cybersecurity skills for AI agents, mapped to six security frameworks and aligned with the agentskills.io standard.

Explore the practical guide ↓

Independent OpenViST project profile, based on linked sources.

Anthropic Cybersecurity Skills — OpenViST project profile in Agent Frameworks.
OpenViST project illustration. See the linked sources for product details.
Understand the project

Practical overview

When it fits

Use it when an AI-agent project needs reusable cybersecurity guidance organized across recognized threat, defense, AI-risk and fraud frameworks.

Who it is for

  • Developers extending AI coding assistants with cybersecurity skills.
  • Security practitioners designing framework-aware investigation, review or response workflows.
  • Builders creating DevSecOps or MCP-connected security assistants.

Documented uses

  • Add cybersecurity skill selection to an AI coding assistant.
  • Create security reviews that reference mapped industry frameworks.
  • Develop incident-response, DevSecOps or security-research agent workflows.
Before you choose

Requirements & limits

The repository is identified as open source and uses the Apache-2.0 license. No account, pricing or service-availability requirements are documented.

  • The library is mapped to MITRE ATT&CK, NIST CSF 2.0, MITRE ATLAS, MITRE D3FEND, NIST AI RMF and MITRE F3.
  • Documented platform ecosystems include Claude Code, GitHub Copilot, Codex CLI, Cursor, Gemini CLI and MCP.
  • The repository contains offensive and dual-use techniques and states that use should be authorized and lawful.
  • Claude Code support is explicitly listed, but installation and runtime procedures are not shown in the supplied documentation.

Check current requirements in the official documentation. Source-based guidance does not mean OpenViST has run or independently tested this project.

Source-based practical guide

Add the cybersecurity skills library to a compatible agent

Obtain the repository’s structured cybersecurity skills using one of its documented quick-start options.

Before you start

  • Use an environment with npx for the recommended option, or git for the clone option.
  • Choose a platform listed as compatible in the README, such as Claude Code, GitHub Copilot, Codex CLI, Cursor, or Gemini CLI.

Steps

  1. Run the command below for the recommended quick-start option.

    Documented command
    npx skills add mukul975/Anthropic-Cybersecurity-Skills

  2. Alternatively, clone the repository with the command below.

    Documented command
    git clone https://github.com/mukul975/Anthropic-Cybersecurity-Skills.git

  3. If you cloned it, change into the repository directory with cd Anthropic-Cybersecurity-Skills.

Expected outcome

The README describes the skills as available immediately with the listed compatible platforms and agentskills.io-compatible platforms.

Guide limitations

  • The README lists platform compatibility but does not detail platform-specific configuration or runtime behavior.
  • Use offensive or dual-use skills only for authorized security testing, research, defense, or education; obtain explicit written permission before testing systems you do not own.
Documentation 1 ↗Documentation 2 ↗
COMPARE OPTIONS

Compare options for AI coding assistance

These projects document a common task and share a project role. This is a source-based comparison, not an execution benchmark or a guarantee of interchangeability.

ProjectDocumented purposePlatformAccess and requirements
Anthropic Cybersecurity SkillsAdd cybersecurity skill selection to an AI coding assistant.CLI, DesktopThe repository is identified as open source and uses the Apache-2.0 license. No account, pricing or service-availability requirements are documented.
DextoDefine agents in YAML with a model, tools, storage and permissions.CLI
Evidence and transparency

Sources & review

Official repository ↗Guide documentation ↗
Source record details
Source availability
Active
Sources checked
1 October 2026
Original website title
mukul975/Anthropic-Cybersecurity-Skills · Official homepage title · retained in its source language
How we review sourcesSuggest a correction