Open-Source Cybersecurity Skills Collection for AI Coding Agents

X postCorey HainesResource

Bri Russell has released a major update to her open-source cybersecurity-skills repository. The collection provides security playbooks and automated workflows for AI coding agents like Claude Code, Cursor, and Codex, helping teams without dedicated security personnel run formal audits.

Key points

  1. Authored in canonical SKILL.md format for Claude Code, with adapters for Cursor and Codex.
  2. Available via 'npx skills' or through the Claude Code plugin marketplace.
  3. Covers code reviews (OWASP, API, dependencies), cloud infrastructure, and container audits.
  4. Offensive modules like recon and web pentesting enforce explicit target authorisation checks.
  5. Includes workflows for incident triage, compliance checks (GDPR, SOC 2, HIPAA), and log monitoring.

Why it matters

Developers and smaller organisations can equip AI coding agents with specialised playbooks to conduct thorough security reviews without hiring an expensive CISO.

Analysis

The open-source repository cybersecurity-skills, maintained by Bri Russell, packages domain-specific security checklists and inspection routines into modular skills for AI agents. The project aims to bridge the gap between formal compliance frameworks and day-to-day engineering sprints.

Structure and Integration

Skills are structured using the SKILL.md format designed for Claude Code, complemented by dedicated adapters for platforms such as Cursor and Codex. Installation can be handled via npx skills or the plugin marketplace. The prompts guide agents through deterministic grep patterns, aligned with OWASP, NIST, and MITRE ATT&CK standards.

Supported Use Cases

The collection spans several operational stages:

  • Codebase & Dependencies: Modules like owasp-audit, api-audit, and dependency-audit allow automated sweeps of application code and third-party libraries.
  • Infrastructure: Includes audits for AWS, GCP, Azure misconfigurations, IAM roles, and Docker/Kubernetes container security.
  • Operations & Compliance: Tools for incident triage, disk forensics, log analysis without dedicated SIEM infrastructure, and compliance mapping (GDPR, HIPAA, SOC 2).
  • Offensive Engagements: Built-in recon and web-pentest playbooks require explicit target authorisation checks prior to execution to prevent accidental misuse.

The framework provides smaller development teams and founders with structured security analysis capabilities directly within their coding environments.

Original post

Corey Haines

@coreyhainesco · 27 October 2026

My wife just released a HUGE update to her open source cybersecurity skills repo 👀 Now's the time for everyone to be on top of their game Give these skills to your agent to do a sweep or create a Grok Bot CISO t.co/DmsirIxHtm t.co/ZI9WPwtW7w

92 likes14 replies170 bookmarks7.6k views

View on X
Selected replies (5)
  • @andrewqu @coreyhainesco a couple who writes skills together 😍
  • @illyism @coreyhainesco @bot set this up for me
  • @CraigBarrDev @coreyhainesco @bot add this to skills-share
  • @brocmayo @coreyhainesco does it cover leaked api keys in a repo? that's the one i'd sweep first on my ios app
  • @opanteraos @coreyhainesco ei @bot já sabe: se algo aqui servir par anós, execute, meu cumpadi

Links and tools from this entry

Summary generated by AI (Gemini 3.8 Flash, 29 October 2026). It may contain errors – the original source is authoritative.

Similar in content, found by the AI search.

  • Repository:briiirussell/cybersecurity-skills

    Cybersecurity Skills: Security Workflows for AI Coding Agents

    An open-source repository provides structured cybersecurity skills for AI agents like Claude Code, Cursor, and Codex. It helps developers and security engineers run automated audits, dependency scans, and code reviews directly within agent workflows.

    479starsJavaScript

    AI & LLMs· Tool

  • X post:Brais Moure

    Cloudflare Releases Open-Source Security Audit Skill for Coding Agents

    Brais Moure highlights the release of Cloudflare's 'security-audit-skill'. The tool turns coding agents into multi-phase security auditors and served as the foundation for Cloudflare's internal vulnerability discovery harness.

    3.4kbookmarks139.4kviews

    AI & LLMs· Tool

  • Repository:cloudflare/security-audit-skill

    Cloudflare Open-Sources Security Audit Skill for Coding Agents

    Cloudflare's security-audit-skill is an open-source coding-agent workflow that orchestrates multi-phase security audits with independently verified, machine-readable findings.

    5.2kstarsJavaScript

    AI & LLMs· Tool

  • X post:0xMarioNawfal

    Cloudflare Open-Sources Coding-Agent Skill for Structured Security Audits

    Cloudflare has open-sourced an audit skill for coding agents that conducts multi-phase code security reviews with independent candidate verification. The project represents the standalone foundation of Cloudflare's internal vulnerability discovery harness.

    749bookmarks86.4kviews

    AI & LLMs· Tool

  • X post:Emre Savcı

    Cloudflare Releases Security Audit Skill for Coding Agents

    Cloudflare has open-sourced security-audit-skill, a coding-agent skill designed to run multi-phase, automated security audits on codebases. It coordinates isolated agent roles across reconnaissance, vulnerability hunting, and independent verification.

    2.8kbookmarks143.6kviews

    AI & LLMs· Tool

  • Repository:intercom/2x-skills

    Intercom fin-2x: Skill Collection and Marketplace for Claude Code

    Intercom's open-source '2x-skills' repository provides a marketplace of ready-to-use plugins and skills for Claude Code. The tools address everyday software engineering workflows, including code review, GitHub Actions hardening, flaky test fixes, and telemetry-based cost tracking.

    240starsShell

    AI & LLMs· Tool

Let's talk about your project

Locations

  • Mattersburg
    Johann Nepomuk Bergerstraße 7/2/14
    7210 Mattersburg, Austria
  • Vienna
    Ungargasse 64-66/3/404
    1030 Wien, Austria

Parts of this content were created with the assistance of AI.