AI BriefingClaude-Red: 70+ Offensive Security Skills to Inject into Claude
SnailSploit/Claude-Red
About the project
A library of offensive security skills designed to plug directly into the Claude Skills system. It provides expert-level methodologies tailored to specific attack surfaces, ranging from SQL injection to shellcode development and EDR evasion, in the form of SKILL.md files. When relevant keywords are detected during a conversation, the corresponding skill is automatically loaded to manage context efficiently.
It includes over 70 skills across 20 categories, including web applications, wireless, cloud, mobile, IoT, infrastructure, and exploit development. It covers specific technical details such as OWASP Top 10, Active Directory attacks, WPA2/3 vulnerabilities, AWS/Azure/GCP attack paths, ROP chains, and firmware extraction, with each skill teaching domain-expert-level tool usage and edge cases.
Unlike generic LLM prompts, it injects structured knowledge tailored to specific attack vectors. It is immediately applicable in real-world security tasks such as authorized red teaming, bug bounty triage, security research, CTF preparation, and operator training. Released under the MIT license, it can be loaded as a system prompt or file in various environments, including Claude Code and Claude.ai.
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.
Python