🔌 pluginActiveCuratedmedium

Anthropic-Cybersecurity-Skills

by mukul975

734+ structured cybersecurity skills for AI agents · MITRE ATT&CK mapped · agentskills.io open standard · Works with Claude Code, GitHub Copilot, OpenAI Codex CLI, Cursor, Gemini CLI & 20+ platforms · Penetration testing, DFIR, threat intel, cloud security & more · Apache 2.0

Stars

15.4k

Skill Type

📖 Library & API Reference

Quality Score

124/200

License

Apache-2.0

Forks

1.8k

Last Updated

Jun 11, 2026

Discovered

Mar 27, 2026

Validation

Passed

github.com/mukul975/Anthropic-Cybersecurity-Skills

Quality Breakdown

124/ 200

Content Signals

Gotchas/Edge Cases+40
Progressive Disclosure+30
Trigger Description+20
Verification/Safety+20
Code Examples+15
Composability+15

Repo Health

Recent Activity+15
Scripts/Automation+10
Real Usage (Issues)+10
Single Responsibility+10
Config/Persistence+10
Install Instructions+5

Multi-platform bonus: +5 pts if tool supports 2+ platforms. Score derived from 12 structural signals — not stars or popularity.

Trust & Verification

medium

Requires extended permissions (shell access, subagents). Review before use.

Active

Updated within the last 90 days. Actively maintained.

Unverified skill. Always review source code before installing any skill from an unknown author.

Risk Assessment

  • Repository contains 750+ cybersecurity skills including penetration testing, malware analysis, and offensive security techniques (rootkit analysis, APT group analysis, Active Directory exploitation)
  • Multiple agent.py scripts across skills directory suggest autonomous code execution capability without explicit approval gates documented
  • Skills cover sensitive domains: DFIR, threat intelligence, malware analysis, privilege escalation, and exploitation techniques that could be misused
  • GitHub Actions workflows (validate-skills.yml, update-index.yml, sync-marketplace-version.yml) enable automated CI/CD execution of skill-related code
  • Repository is designed for multi-platform AI agent integration (Claude Code, GitHub Copilot, OpenAI, Cursor, Gemini, 20+ platforms) increasing distribution surface
  • MITRE ATT&CK mapping indicates comprehensive offensive security coverage, not defensive-only