# mukul975/Anthropic-Cybersecurity-Skills

817 structured cybersecurity skills for AI agents · Mapped to 6 frameworks: MITRE ATT&CK, NIST CSF 2.0, MITRE ATLAS, D3FEND, NIST AI RMF & MITRE F3 (Fight Fraud) · agentskills.io standard · Works with Claude Code, GitHub Copilot, Codex CLI, Cursor, Gemini CLI & 20+ platforms · 29 security domains · Apache 2.0

Repository: https://github.com/mukul975/Anthropic-Cybersecurity-Skills
Canonical: https://ross.abutalabs.com/products/anthropic-cybersecurity-skills
Homepage: https://mahipal.engineer/Anthropic-Cybersecurity-Skills/
Language: Python
License: Apache-2.0
License Family: permissive
Topics: ai-agents, claude-code, cybersecurity, incident-response, mitre-attack, penetration-testing, red-team, security, cloud-security, malware-analysis, devsecops, ethical-hacking, infosec, llm, mcp, osint, security-automation, threat-intelligence, nist-csf, threat-hunting
Last push: 2026-08-24T11:12:27+00:00

## Health v2 (maintenance only)
Score: 78/100 (v2, computed 2026-09-02T17:46:02.011165+00:00)
- activity 99, release rhythm 89, longevity 13
- inputs: {"age_days": 189, "days_push": 9, "days_rel": 72, "gap_med": 15, "n_releases_24m": 4}
- flags: none
- formula: round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10)

## Adoption (not part of the score)
Stars 31259, forks 3726 (observed 2026-08-28T04:11:56.622144+00:00)

## What it is
A large open-source library of structured cybersecurity skills (Markdown files with YAML frontmatter) for AI coding agents, mapped to frameworks like MITRE ATT&CK, NIST CSF 2.0, MITRE ATLAS, D3FEND, NIST AI RMF, and MITRE F3. Skills install into Claude Code, GitHub Copilot, Cursor, Codex CLI, Gemini CLI, and 20+ other agent platforms following the agentskills.io standard.

## Use cases
- give my AI coding agent cybersecurity skills
- run red team exercises with Claude Code
- map security workflows to MITRE ATT&CK
- automate incident response playbooks for AI agents
- audit AWS S3 bucket security configurations
- perform memory forensics with Volatility3 guidance
- build a threat hunting assistant
- learn penetration testing workflows with an LLM

## When to choose
- you use Claude Code, Copilot, Cursor, or another compatible AI agent and want structured security workflows
- you need skills aligned to MITRE ATT&CK, NIST CSF, ATLAS, D3FEND, or AI RMF frameworks
- you want a broad, regularly updated catalog covering many security domains
- you prefer a permissive Apache-2.0 license for security tooling

## When to avoid
- you need a standalone security scanner rather than skills loaded into an AI agent
- you lack authorization to test systems, since the library includes offensive techniques
- you require vendor-supported, certified security tooling for compliance purposes
- you want a small, curated set of skills rather than a large community-driven collection

## Facets
- artifact type: library
- maturity: active
- function: security, penetration-testing, osint, mcp, agent-framework, prompt-engineering, developer-tools
- domain: security, penetration-testing, osint, developer-tools, cloud-computing
- platform: cli, cross-platform, python
- tags: cybersecurity-skills, mitre-attack, nist-csf, red-team, threat-intelligence, incident-response, claude-code, agentskills, skill-library, devsecops, threat-hunting, malware-analysis, ai-agents, automation, nodejs

## Member repositories
- mukul975/Anthropic-Cybersecurity-Skills (main) score 78

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:11:56.622144+00:00.
- Health v2: computed from the inputs above; adoption is never an input.
- Inferred fields (summary, facets, guidance): AI-extracted, prompt v1, taxonomy v1, on 2026-08-29T16:52:18.660628+00:00, confidence not recorded.
  - readme: https://github.com/mukul975/Anthropic-Cybersecurity-Skills (fetched 2026-08-28T04:11:56.622144+00:00, sha 0a9b22902567)
  - homepage: https://mahipal.engineer/Anthropic-Cybersecurity-Skills/ (fetched 2026-08-29T07:49:29.286586+00:00, sha 5748c98ebd92)
- Data as of 2026-08-30T08:39:29.467469+00:00.