Sign InOpen Brain
GitHubGitHub RepoNeeds Review

mukul975/Anthropic-Cybersecurity-Skills

This community library packages 817 security workflows as agent skills, offering broad framework-mapped guidance while requiring careful review for offensive and dual-use tasks.

GitHub
Open Source Open MarkdownOpen JSON
Source Summary

The repository contains **817 skills** across **29 security domains**, using the agentskills.io format. Coverage includes 805 ATT&CK mappings, 804 NIST CSF mappings, and smaller sets for D3FEND, AI RMF, F3, and ATLAS.

Practical Implication

Treat it as a searchable playbook layer for security agents: frontmatter supports cheap discovery, while full skill files provide prerequisites, procedures, decision points, and verification steps. Review the selected workflow and required access before execution.

Agent-Ready Context
The repository contains **817 skills** across **29 security domains**, using the agentskills.io format. Coverage includes 805 ATT&CK mappings, 804 NIST CSF mappings, and smaller sets for D3FEND, AI RMF, F3, and ATLAS.

Treat it as a searchable playbook layer for security agents: frontmatter supports cheap discovery, while full skill files provide prerequisites, procedures, decision points, and verification steps. Review the selected workflow and required access before execution.

This is an **independent community project**, not an Anthropic release. It includes offensive and dual-use material, so use must stay within owned systems or explicit written authorization; the repository’s quality claims are not independently validated here.
Connected Context · Feed7 Judgment

This expands the skill-catalog pattern into a security-specific playbook layer with unusually broad framework mapping and discovery metadata. Against prior candidates, its scale strengthens the case for selective routing, authorization checks, and supply-chain review rather than wholesale installation. The mappings improve findability, but neither they nor the repository’s own quality claims establish workflow correctness or safe execution.

zhaoxuya520/reverse-skillreverse-skill supplies a narrower authorization-first, evidence-linked execution pattern that could govern selection and use of this much broader security playbook catalog.We Vetted 2000 AI Skills Before They Reached Developers — Lucas Palma, NubankThe catalog’s 817 independent, dual-use skills make Nubank’s deterministic scanning, LLM review, and distribution gating directly relevant as prerequisites for trusted adoption.affaan-m/ECCBoth expose large cross-domain skill surfaces whose breadth increases audit and maintenance work, reinforcing selective installation and verification rather than assuming more skills improve the harness.In Code They Act, In Proof We Trust — Erik Meijer, Leibniz LabsMachine-checkable approval before side effects would strengthen the repository’s stated authorization boundary, which currently depends on users reviewing workflows and access before execution.
Context Map
agentsecurity#skills#tool-use
Uncertainty
This is an **independent community project**, not an Anthropic release. It includes offensive and dual-use material, so use must stay within owned systems or explicit written authorization; the repository’s quality claims are not independently validated here.