← Discover
Discover · GitHub · Claude-Red↑ +113 today

Security expert skills for Claude

Claude-Red is a library of offensive security skills integrated into the capability system of the AI model Claude. It aims to automate security testing by providing expert-level methodologies in areas such as SQL injection and bypassing endpoint protection systems.

Updates

  • September 13, 2026: Stars 3,787 → 3,791, latest release v0.3.0 (August 30, 2026).

What you get

  • Provides access to offensive security methodologies
  • Transforms the AI model into a penetration testing expert
  • Automatically loads required skills

Installation

Download all skills
git clone https://github.com/SnailSploit/claude-red ~/.claude/skills/claude-red
Interactive installation
./install.sh                           # interactive
./install.sh --target ~/.claude/skills # explicit target
./install.sh --category web            # single category

If you don't write code

🤖 Paste this into your AI agent (Claude Code · Codex · Antigravity)

From now on, I want you to act like a penetration testing expert. Analyze vulnerabilities using the methodologies in the skill files I share, evaluate attack surfaces, and guide me in my cybersecurity research.

Related dictionary terms

Offensive Security SkillsAI SkillsArtificial Intelligence
Who it is forSuitable for security researchers performing penetration testing and operators training in the field of cybersecurity.
LicenseMIT

Links

TreScout did not build this tool · we found it in GitHub trends and wrote it up. This page describes the repository as of 2026-09-13: The star count and our text belong to that day, the repository may have changed since. Check the repository link for the current state. This page was machine-translated from the Turkish original · the Turkish version prevails.