SnailSploit/Claude-Red

claude-red is a curated library of offensive security skills designed for the Claude skills system. Each skill is a structured SKILL.md file that primes Claude with expert-level methodology for a specific attack surface — from SQLi to shellcode, EDR evasion to exploit development.

What it solves

Claude-Red provides a curated library of offensive security skills to transform Claude into a context-aware red team operator. It solves the problem of general-purpose LLMs lacking the deep, structured methodology required for specialized attack surfaces, allowing security professionals to prime the AI with expert-level knowledge on specific vulnerabilities and exploitation techniques.

How it works

The project consists of a collection of structured SKILL.md files. These files act as system prompts or priming documents that provide Claude with the necessary techniques, tooling, and escalation paths for a specific domain. These skills can be integrated into the Claude Skills system for on-demand loading based on conversational triggers, used as system files in Claude Code, or manually pasted into Claude.ai projects.

Who it’s for

It is designed for authorized red team engagements, bug bounty hunters, security researchers, CTF participants, and security operators in training.

Highlights

  • Extensive Coverage: Includes 78 skills across 23 categories, covering everything from Web Applications (SQLi, XSS, SSRF) and Active Directory to Wireless (WPA3, BLE, Zigbee) and AI Security (prompt injection, RAG poisoning).
  • On-Demand Loading: When used with the Claude Skills system, skills load only when triggered by the conversation, saving context window space.
  • Broad Attack Surface: Spans multiple domains including Cloud, IoT/Embedded, Mobile, Container/Kubernetes, and Exploit Development.
  • Flexible Deployment: Supports multiple installation methods including a dedicated install script, git clone for the Claude Skills system, and manual integration for the Claude.ai web interface.

Related

  • Project
    Masriyan/Claude-Code-CyberSecurity-Skill

    A genuine open‑source project that provides 22 “Claude Code” skill packs turning Anthropic’s Claude‑Code assistant into a cybersecurity co‑pilot. Each skill is a markdown file with triggers, methodology, templates and optional Python scripts, covering everything from OSINT and vulnerability scanning to AI‑LLM security and purple‑team emulation. Install by copying the `skills/` folders into `~/.claude/skills/` (or a project‑local `.claude/skills/`). Claude then auto‑activates the appropriate skill during conversation, runs helper scripts, and returns ready‑to‑use reports, rules, or commands. MIT‑licensed, with safety gates for offensive actions.

  • Project
    elementalsouls/Claude-OSINT

    A library of specialized skills for Claude that provides expert-level OSINT methodology and tactical tradecraft for authorized red-team and bug-bounty reconnaissance.

  • Project
    elementalsouls/Claude-BugHunter

    A comprehensive skill bundle for Claude Code that turns the AI into a senior bug-hunting researcher and red-team operator for external attack surface testing.

  • Project
    Jeffallan/claude-skills

    A plugin for Claude Code providing 67 specialized developer skills and structured workflows to automate full-stack engineering tasks.

  • Project
    0xSteph/pentest-ai-agents

    A collection of 50 specialized Claude Code sub-agents that turn Claude into an offensive security research assistant for penetration testing and red teaming.