Anthropic-Cybersecurity-Skills is a free, open source threat detection & response project written in Python and released under Apache-2.0. It has 32,960 GitHub stars, 3,985 forks and 48 open issues, and was last pushed 19 days ago. On this registry it ranks #2 of 12 tracked projects in Threat Detection & Response, with 5 head-to-head comparisons available.

What is Anthropic-Cybersecurity-Skills?

Anthropic Cybersecurity Skills is an Apache-2.0 Python library of 817 structured cybersecurity skills that gives AI agents the working knowledge of a senior security analyst, aimed at security teams, DevSecOps engineers, and red or blue teams that already run agents such as Claude Code, GitHub Copilot, Codex CLI, Cursor, or Gemini CLI.

What it is

The project is an open-source skills library for AI agents registered under Security & Privacy / Threat Detection & Response. Each of the 817 skills follows the agentskills.io open standard and spans 29 security domains, from incident response and malware analysis to cloud security, ethical hacking, and DevSecOps. Every skill is mapped to the frameworks that fit its subject across six standards: MITRE ATT&CK, NIST CSF 2.0, MITRE ATLAS, MITRE D3FEND, NIST AI RMF, and the MITRE Fight Fraud Framework (F3) v1.1, with ATT&CK and NIST CSF applying near-universally and ATLAS, AI RMF, D3FEND, and F3 applied where relevant.

The problem it solves is procedural knowledge. A junior analyst knows which Volatility3 plugin to run on a suspicious memory dump, which Sigma rules catch Kerberoasting, and how to scope a cloud breach across three providers. An AI agent does not, unless it is handed that expertise in a structured form. This library replaces the ad-hoc practice of pasting security knowledge into prompts or hand-writing per-platform agent instructions: clone the repository, point the agent at it, and the investigation gets expert-level guidance without per-platform rework.

Key capabilities

  • 817 structured cybersecurity skills across 29 security domains, each written to the agentskills.io open standard.
  • Six framework mappings in one library: MITRE ATT&CK, NIST CSF 2.0, MITRE ATLAS, MITRE D3FEND, NIST AI RMF, and MITRE F3 v1.1.
  • Per-skill framework selection, so a forensics skill carries ATT&CK plus CSF while an AI-security skill adds ATLAS and AI RMF.
  • Compatibility with Claude Code, GitHub Copilot, Codex CLI, Cursor, Gemini CLI, Hermes Agent, and more than 20 further platforms.
  • Domain coverage that includes incident response, malware analysis, cloud security, threat detection, ethical hacking, and DevSecOps.
  • Offensive and dual-use skills such as red-team command and control, phishing simulation, and exploitation for authorized testing.
  • Repository governance files including LICENSE, SECURITY.md, CODE_OF_CONDUCT.md, and CONTRIBUTING.md.

Who uses it and how

  • Incident responders and SOC analysts triaging memory dumps, where the agent needs to select the correct Volatility3 plugin rather than guess.
  • Detection engineers authoring Sigma rules for Kerberoasting and similar identity attacks, using framework mappings to justify rule coverage.
  • Cloud security teams scoping a breach that crosses three providers, using the skill library to structure the investigation.
  • DevSecOps teams embedding the skills into agent workflows on Claude Code, GitHub Copilot, Cursor, or Codex CLI.
  • Red teams running authorized penetration tests, C2 exercises, and phishing simulations under written rules of engagement.

Getting started

Clone the repository and point an agent at it. A hosted playground is listed at Casky.ai with a waitlist, and the project homepage is mahipal.engineer/Anthropic-Cybersecurity-Skills/.

How it compares

No list of paid products replaced by this project appears in the supplied facts, and no comparable tools are named. It stands alone in this registry on that basis.

When to use it — and when not to

A self-hoster operates only an AI agent platform, since the library ships as skills rather than as a server, database, or mail service, but the user carries full responsibility for lawful and authorized use of the offensive and dual-use techniques. Anyone without written permission to test a target should not adopt it, and teams wanting a fully audited, enterprise-vetted knowledge base should weigh that this is an independent community project not affiliated with Anthropic PBC. The counts also drift between sources: the registry listing states 817 skills and 29 domains, while the repository README shows 818 skills and 34 domains.

project readme (upstream, from github) — read inline

Anthropic Cybersecurity Skills

The largest open-source cybersecurity skills library for AI agents

GARS-2026 Survey License Skills Frameworks MITRE F3 Domains Platforms GitHub stars GitHub forks Last Commit agentskills.io PRs Welcome Playground Hermes Agent

818 production-grade cybersecurity skills · 34 security domains · 6 framework mappings · 26+ AI platforms

Get Started · What's Inside · Frameworks · Platforms · Contributing


⚠️ Community Project — This is an independent, community-created project. Not affiliated with Anthropic PBC.

🔐 Authorized & lawful use only. This library includes offensive and dual-use techniques (e.g. red-team C2, phishing simulation, exploitation) intended for authorized penetration testing, security research, defense, and education. Only use them against systems you own or have explicit written permission to test, and comply with all applicable laws and rules of engagement. You are solely responsible for how you use these skills. See SECURITY.md and CODE_OF_CONDUCT.md.

Give any AI agent the security skills of a senior analyst

A junior analyst knows which Volatility3 plugin to run on a suspicious memory dump, which Sigma rules catch Kerberoasting, and how to scope a cloud breach across three providers. Your AI agent doesn't — unless you give it these skills.

This repo contains 818 structured cybersecurity skills spanning 34 security domains, each following the agentskills.io open standard. The library maps across six industry frameworks — MITRE ATT&CK, NIST CSF 2.0, MITRE ATLAS, MITRE D3FEND, NIST AI RMF, and the MITRE Fight Fraud Framework (F3) — with each skill mapped to the frameworks relevant to its type (a forensics skill carries ATT&CK + CSF; an AI-security skill adds ATLAS and AI RMF). Clone it, point your agent at it, and your next security investigation gets expert-level guidance in seconds.

Six frameworks, one skill library

Each skill maps to the frameworks that fit its subject — ATT&CK and NIST CSF are near-universal, while ATLAS, AI RMF, D3FEND, and F3 apply where they're relevant. Framework coverage across the 817 skills: MITRE ATT&CK 805 · NIST CSF 2.0 804 · MITRE D3FEND 139 · NIST AI RMF 97 · MITRE F3 94 · MITRE ATLAS 93.

Framework Version Framework scope What it maps
MITRE ATT&CK v19.1 15 tactics · Enterprise/Mobile/ICS Adversary behaviors and TTPs
NIST CSF 2.0 2.0 6 functions · 22 categories · 106 subcategories Organizational security posture
MITRE ATLAS 2026.07 101 techniques · 77 sub-techniques AI/ML adversarial threats
MITRE D3FEND v1.4.0 270 techniques Defensive countermeasures
NIST AI RMF 1.0 4 functions (Govern/Map/Measure/Manage) AI risk management
MITRE F3 (Fight Fraud Framework) v1.1 (2026-04-09) 8 tactics · 123 techniques · 94 fraud-relevant skills Cyber-enabled financial fraud TTPs

Example — each skill maps only to the frameworks relevant to it (one may hit all six, another just a couple):

Skill ATT&CK NIST CSF ATLAS D3FEND AI RMF F3
analyzing-network-traffic-of-malware T1071 DE.CM AML.T0047 D3-NTA MEASURE-2.6
detecting-business-email-compromise T1566 DE.AE F1005.006 · monetization

🆕 MITRE Fight Fraud Framework (F3) — 94 fraud-relevant skills

MITRE F3

The MITRE Fight Fraud Framework (F3) was released April 9, 2026 by MITRE's Center for Threat-Informed Defense (CTID), co-developed with JPMorganChase, Citigroup, Lloyds Banking Group, Standard Chartered, CrowdStrike, Verizon Business, FS-ISAC, and others. It is an ATT&CK-compatible TTP catalog for cyber-enabled financial fraud — filling the gap ATT&CK leaves after initial compromise.

F3 v1.1 adds two fraud-specific tactics that ATT&CK does not enumerate:

  • Positioning (FA0001) — actions taken after access to collect/manipulate data and prepare the fraud (synthetic-identity seeding, account warming, beneficiary setup, SIM-swap pre-positioning, banking-session hijack).
  • Monetization (FA0002) — converting stolen assets into usable funds (money-mule layering, APP fraud, crypto off-ramping, card cash-out, refund/chargeback abuse).

Fraud-specific techniques use F1XXX IDs (e.g. F1005.003 Add Beneficiary, F1025.003 Wire Transfer, F1007 Adversary-in-the-Browser); reused ATT&CK techniques keep their T1XXX IDs. Mappings live in each skill's mitre_f3: frontmatter block — all 123 F3 v1.1 technique IDs were verified against the upstream STIX bundle. See docs/mitre-f3-mapping.md for the schema.

MITRE ATT&CK v19.1 — 805/817 skills mapped

Every skill carries a mitre_attack frontmatter list validated against MITRE ATT&CK v19.1 (the latest release) using the official mitreattack-python library — 290 distinct techniques and sub-techniques (146 base + 144 sub) across Enterprise, ICS, and Mobile. Zero revoked or deprecated IDs. v19.1's restructured Defense Evasion (now split into Stealth and Defense Impairment) is reflected below.

Tactic ID Skills
Reconnaissance TA0043 103
Resource Development TA0042 22
Initial Access TA0001 467
Execution TA0002 350
Persistence TA0003 444
Privilege Escalation TA0004 464
Stealth TA0005 442
Defense Impairment TA0112 92
Credential Access TA0006 202
Discovery TA0007 237
Lateral Movement TA0008 68
Collection TA0009 172
Command and Control TA0011 123
Exfiltration TA0010 82
Impact TA0040 50

Quick start

# Option 1: npx (recommended)
npx skills add mukul975/Anthropic-Cybersecurity-Skills

# Option 2: Git clone
git clone https://github.com/mukul975/Anthropic-Cybersecurity-Skills.git
cd Anthropic-Cybersecurity-Skills

Works immediately with Claude Code, GitHub Copilot, OpenAI Codex CLI, Cursor, Gemini CLI, and any agentskills.io-compatible platform.

🌍 GARS-2026 — Global Agentic AI Readiness Survey

I'm running a global academic study measuring how ready security professionals, developers, and enterprise teams actually are for agentic AI — MCP servers, tool calling, governance, and human-in-the-loop workflows.

**If you use this repo, your response would be a genuinely valuable data

readme truncated — read the full docs on github

Frequently asked questions

Is Anthropic-Cybersecurity-Skills free to use?

Anthropic-Cybersecurity-Skills is open source under the Apache-2.0 licence. There is no licence fee and no seat count — you can self-host it or, where the project offers one, pay a vendor for a managed version instead.

What does Anthropic-Cybersecurity-Skills do?

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

What is Anthropic-Cybersecurity-Skills written in?

Anthropic-Cybersecurity-Skills is primarily written in Python. Its source is publicly available at https://github.com/mukul975/Anthropic-Cybersecurity-Skills, and it has 32,960 GitHub stars.