Claude Redteam — Security skill for Claude Code
Agentic pentest/red-team framework orchestrated by Claude Code — automated recon, hunt, validate, and report workflow with built-in safety guardrails.
How to install Claude Redteam
This entry records only its repository, not the path inside it, so there is no
exact command to give. Open PhanNhatTien090/claude-redteam and copy the folder into
~/.claude/skills/, or the file into ~/.claude/agents/.
What Claude Redteam does
Agentic pentest/red-team framework orchestrated by Claude Code — automated recon, hunt, validate, and report workflow with built-in safety guardrails.
Alternatives in Security
- Free Code — The free build of Claude Code 8.1k ★
- T3mp3st — autonomous red teaming platform; multi-agent offensive-security meta-harness 5.7k ★
- Skills Audit Report — Date: 2026-02-15 Auditor: Automated Skill Quality Audit Scope: Recently added skills in business-growth/, fina 5.3k ★
README
Claude RedTeam
Agentic pentest / bug-bounty framework orchestrated by Claude Code
Features • Quickstart • Structure • Scope of use • License
Recon → hunt → validate → report, with state that survives across sessions, 64 vulnerability-class playbooks, and a guard-hook layer built to stop long offensive-security sessions from getting killed mid-engagement by an LLM's own safety classifier.
[!NOTE] Most "AI agent does pentesting" demos break the moment a real engagement needs more than a handful of tool calls — raw HTTP dumps, exploit payloads, and offensive narration pile up in context until the session gets flagged and killed. This framework exists to run *real, client-scoped, contractually-authorized* engagements without that happening.
Features
| 🗂️ Persistent state | Facts, tokens, findings, and history live in versioned JSON/JSONL (state.py, history.py, api_catalog.py) — not chat context. Resume any engagement in a fresh session. |
| 📚 64 playbooks | IDOR, SSRF, GraphQL, OAuth/SAML, cache poisoning, prototype pollution, mobile (iOS/Android + Frida), cloud/IAM, LLM OWASP Top 10, and more — loaded on demand via /skill-load. |
| 🤖 6 subagents | recon, recon-ranking, chain-scouting, finding validation, a |
Related Skills
Web3 Bug Bounty Hunting AI Skills
18 Claude Code skill files for smart contract security — built from 2,749 Immunefi reports, 681 DeFiHack repro
My Security Auditor
Comprehensive Claude skill for authorized security auditing — OWASP, MITRE ATT&CK, ISO 27001, SOC 2, PCI-DSS,
Agent Penetration Tester
Dispatch hub:penetration-tester — Expert in offensive security, penetration testing, red team operations, and
Cw Audit
Red-team and premortem an existing plan or strategy. Takes any document and stress-tests it.
Agents For
List pentest-ai agents relevant to a domain or tag (web, ad, cloud, mobile, recon, etc.).
Pentest Swarm AI
Autonomous penetration testing using a swarm of AI agents. Orchestrates recon, classification, exploitation, a
Related Agents
Redteam Agent
Red Team penetration testing agent for HTB Expressway. Use when the user wants to attack or pentest the target
.github/workflows/redteam.yml
name: Continuous Red Team Assessment on: push: branches: [main, develop] pull_request: branches: [main] schedu
Redteam Finding Verifier
Independent verification agent for red-team findings. Use this agent after an analyzer, recon, CMS, or exploit
