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.
★ 11,067⑂ 1,506👁 70⑃ 46● 18▤ 2
+765
Daily
+765
Weekly
+3,618
Monthly
11,067
stars
1,506
forks
70
watchers
46
prs
18
issues
2
releases
README
!claude-red banner claude-red Offensive security skills for Claude — drop-in SKILL.md files that turn Claude into a context-aware red team operator. Overview • Quickstart • Categories • Skill Index • Roadmap • Contributing --- Overview claude-red is a curated library of offensive security skills 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 SQL injection to shellcode, EDR evasion to ADCS abuse. Drop a skill into your Claude environment and it behaves like a domain specialist: it knows the techniques, the tooling, the edge cases, and the escalation paths. Skills load on demand based on conversational triggers — you don't pay context for skills you aren't using. Use cases: authorized red team engagements, bug bounty triage, security research, CTF preparation, operator training, and methodical attack surface exploration. for our actual research using skills - https://snailsploit.com --- Quickstart Claude Skills System (Recommended) bash git clone https://github.com/SnailSploit/claude-red ~/.claude/skills/claude-red Claude auto-loads matching skills based on conversational triggers (e.g., mentioning SQL injection loads offensive-sqli). To install a single category: bash git clone --filter=blob:none --sparse https://github.com/SnailSploit/claude-red cd claude-red && git sparse-checkout set Skills/web Skills/active-directory Claude Code bash cat Skills/web/offensive-sqli/SKILL.md | claude --system-file - cat Skills/active-directory//SKILL.md | claude --system-file - Claude.ai (Manual) Paste the contents of a SKILL.md into a Project's system prompt or prepend it to your conversation. Install Script bash ./install.sh interactive ./install.sh --target ~/.claude/skills explicit target ./install.sh --category web single category --- Categories | Category | Skills | Focus | |---|---:|---| | Web Application | 16 | OWASP Top 10, business logic, advanced web vulnerability classes | | Auth & Identity | 2 | JWT exploitation, OAuth/OIDC abuse | | Active Directory | 1 | On-prem AD attack methodology | | Wireless | 14 | 802.11, WPA2/3, EAP, WPS, evil-twin, BLE, Zigbee, Z-Wave, LoRa, sub-GHz | | Cloud | 1 | AWS, Azure, GCP attack paths | | Mobile | 1 | Android and iOS application testing | | IoT & Embedded | 1 | Hardware, firmware, RTOS, ICS/OT | | Infrastructure & Red Team | 7 | Initial access, EDR evasion, advanced red team operations, Windows internals | | Exploit Development | 6 | Stack/heap corruption, ROP, mitigations, crash analysis, TOCTOU | | Fuzzing & Vulnerability Research | 4 | libFuzzer, AFL++, coverage-guided fuzzing, vulnerability taxonomy | | Reconnaissance | 2 | OSINT tooling and structured intelligence collection | | API Security | 2 | REST/gRPC/WebSocket testing, business logic abuse | | Container & Kubernetes | 2 | Container es
Top issues
#61claude flags these skills2 comments · 2026-10-31#32Remote access backdoor in this repo2 comments · 2026-09-23#2828 of 78 SKILL.md files lack YAML frontmatter — `npx skills add` silently installs only 50 skills1 comments · 2026-09-15#66Tried everything claude isn't allowing it to install0 comments · 2026-11-09#65bütün modeller için yapma şansınız varmı gemini chatgpt0 comments · 2026-11-03#64Safety: destructive verbs in verb-enumeration loop should be opt-in0 comments · 2026-11-03#3018 skill descriptions exceed the 1024-character Agent Skills spec limit (longest 1522)0 comments · 2026-09-15#21Fagan pleading preparation0 comments · 2026-09-12
Latest release
v0.3.0 — 78 Skills, 23 Categories, Full Wireless Suite v0.3.0 2026-08-30What's New Major expansion — claude-red goes from 37 skills in flat directories to 78 skills across 23 organized categories. This release adds full-spectrum offensive coverage from container escapes to wireless protocol attacks. 20 New Skills Across 10 Categories - container/ — Docker/containerd breakout, runc CVEs, K8s RBAC abuse, etcd, kubelet API, pod escape - - cicd/ — GitHub Actions injection, Jenkins RCE, GitLab CI, secret extraction, OIDC federation - - api/ — OWASP API Top 10, REST/gRPC/WebSocket, batching attacks, webhook hijacking - - crypto/ — Padding oracle, ECB, hash