0xSteph/pentest-ai-agents
Turn Claude Code into your offensive security research assistant. Specialized AI subagents for authorized penetration testing plan engagements, analyze recon, research exploits, build detections, audit STIGs, and write reports.
ARCHETYPE
Orchestrator
A bench of specialised subagents. The main agent mostly delegates.
Copy this rig
# review before running: this installs third-party code $ npx degit 0xSteph/pentest-ai-agents/agents ./rig-pentest-ai-agents/agents $ npx degit 0xSteph/pentest-ai-agents/commands ./rig-pentest-ai-agents/commands
MCP servers are added to Claude Code at local scope; env vars are shown as YOUR_… placeholders — we never store values. Files are fetched with degit into a separate folder so you can review before merging.
$ curl -fsSL --create-dirs -o .claude/agents/_scope-guard.md https://raw.githubusercontent.com/0xSteph/pentest-ai-agents/main/agents/_scope-guard.md $ curl -fsSL --create-dirs -o .claude/agents/ad-attacker.md https://raw.githubusercontent.com/0xSteph/pentest-ai-agents/main/agents/ad-attacker.md $ curl -fsSL --create-dirs -o .claude/agents/ai-recon.md https://raw.githubusercontent.com/0xSteph/pentest-ai-agents/main/agents/ai-recon.md $ curl -fsSL --create-dirs -o .claude/agents/api-security.md https://raw.githubusercontent.com/0xSteph/pentest-ai-agents/main/agents/api-security.md $ curl -fsSL --create-dirs -o .claude/agents/attack-planner.md https://raw.githubusercontent.com/0xSteph/pentest-ai-agents/main/agents/attack-planner.md $ curl -fsSL --create-dirs -o .claude/agents/bizlogic-hunter.md https://raw.githubusercontent.com/0xSteph/pentest-ai-agents/main/agents/bizlogic-hunter.md $ curl -fsSL --create-dirs -o .claude/agents/bug-bounty.md https://raw.githubusercontent.com/0xSteph/pentest-ai-agents/main/agents/bug-bounty.md $ curl -fsSL --create-dirs -o .claude/agents/c2-operator.md https://raw.githubusercontent.com/0xSteph/pentest-ai-agents/main/agents/c2-operator.md $ curl -fsSL --create-dirs -o .claude/agents/cicd-redteam.md https://raw.githubusercontent.com/0xSteph/pentest-ai-agents/main/agents/cicd-redteam.md $ curl -fsSL --create-dirs -o .claude/agents/cloud-security.md https://raw.githubusercontent.com/0xSteph/pentest-ai-agents/main/agents/cloud-security.md $ curl -fsSL --create-dirs -o .claude/agents/code-auditor.md https://raw.githubusercontent.com/0xSteph/pentest-ai-agents/main/agents/code-auditor.md $ curl -fsSL --create-dirs -o .claude/agents/compliance-mapper.md https://raw.githubusercontent.com/0xSteph/pentest-ai-agents/main/agents/compliance-mapper.md $ curl -fsSL --create-dirs -o .claude/agents/container-breakout.md https://raw.githubusercontent.com/0xSteph/pentest-ai-agents/main/agents/container-breakout.md $ curl -fsSL --create-dirs -o .claude/agents/credential-tester.md https://raw.githubusercontent.com/0xSteph/pentest-ai-agents/main/agents/credential-tester.md $ curl -fsSL --create-dirs -o .claude/agents/crypto-analyzer.md https://raw.githubusercontent.com/0xSteph/pentest-ai-agents/main/agents/crypto-analyzer.md $ curl -fsSL --create-dirs -o .claude/agents/ctf-solver.md https://raw.githubusercontent.com/0xSteph/pentest-ai-agents/main/agents/ctf-solver.md $ curl -fsSL --create-dirs -o .claude/agents/data-exfiltrator.md https://raw.githubusercontent.com/0xSteph/pentest-ai-agents/main/agents/data-exfiltrator.md $ curl -fsSL --create-dirs -o .claude/agents/database-attacker.md https://raw.githubusercontent.com/0xSteph/pentest-ai-agents/main/agents/database-attacker.md $ curl -fsSL --create-dirs -o .claude/agents/detection-engineer.md https://raw.githubusercontent.com/0xSteph/pentest-ai-agents/main/agents/detection-engineer.md $ curl -fsSL --create-dirs -o .claude/agents/engagement-planner.md https://raw.githubusercontent.com/0xSteph/pentest-ai-agents/main/agents/engagement-planner.md $ curl -fsSL --create-dirs -o .claude/agents/evasion-specialist.md https://raw.githubusercontent.com/0xSteph/pentest-ai-agents/main/agents/evasion-specialist.md $ curl -fsSL --create-dirs -o .claude/agents/exploit-chainer.md https://raw.githubusercontent.com/0xSteph/pentest-ai-agents/main/agents/exploit-chainer.md $ curl -fsSL --create-dirs -o .claude/agents/exploit-guide.md https://raw.githubusercontent.com/0xSteph/pentest-ai-agents/main/agents/exploit-guide.md $ curl -fsSL --create-dirs -o .claude/agents/fix-verifier.md https://raw.githubusercontent.com/0xSteph/pentest-ai-agents/main/agents/fix-verifier.md $ curl -fsSL --create-dirs -o .claude/agents/forensics-analyst.md https://raw.githubusercontent.com/0xSteph/pentest-ai-agents/main/agents/forensics-analyst.md $ curl -fsSL --create-dirs -o .claude/agents/iot-pentester.md https://raw.githubusercontent.com/0xSteph/pentest-ai-agents/main/agents/iot-pentester.md $ curl -fsSL --create-dirs -o .claude/agents/lateral-movement.md https://raw.githubusercontent.com/0xSteph/pentest-ai-agents/main/agents/lateral-movement.md $ curl -fsSL --create-dirs -o .claude/agents/llm-redteam.md https://raw.githubusercontent.com/0xSteph/pentest-ai-agents/main/agents/llm-redteam.md $ curl -fsSL --create-dirs -o .claude/agents/malware-analyst.md https://raw.githubusercontent.com/0xSteph/pentest-ai-agents/main/agents/malware-analyst.md $ curl -fsSL --create-dirs -o .claude/agents/mobile-pentester.md https://raw.githubusercontent.com/0xSteph/pentest-ai-agents/main/agents/mobile-pentester.md $ curl -fsSL --create-dirs -o .claude/agents/network-attacker.md https://raw.githubusercontent.com/0xSteph/pentest-ai-agents/main/agents/network-attacker.md $ curl -fsSL --create-dirs -o .claude/agents/opsec-anonymizer.md https://raw.githubusercontent.com/0xSteph/pentest-ai-agents/main/agents/opsec-anonymizer.md $ curl -fsSL --create-dirs -o .claude/agents/osint-collector.md https://raw.githubusercontent.com/0xSteph/pentest-ai-agents/main/agents/osint-collector.md $ curl -fsSL --create-dirs -o .claude/agents/password-auditor.md https://raw.githubusercontent.com/0xSteph/pentest-ai-agents/main/agents/password-auditor.md $ curl -fsSL --create-dirs -o .claude/agents/payload-crafter.md https://raw.githubusercontent.com/0xSteph/pentest-ai-agents/main/agents/payload-crafter.md $ curl -fsSL --create-dirs -o .claude/agents/persistence-planner.md https://raw.githubusercontent.com/0xSteph/pentest-ai-agents/main/agents/persistence-planner.md $ curl -fsSL --create-dirs -o .claude/agents/phishing-operator.md https://raw.githubusercontent.com/0xSteph/pentest-ai-agents/main/agents/phishing-operator.md $ curl -fsSL --create-dirs -o .claude/agents/poc-validator.md https://raw.githubusercontent.com/0xSteph/pentest-ai-agents/main/agents/poc-validator.md $ curl -fsSL --create-dirs -o .claude/agents/privesc-advisor.md https://raw.githubusercontent.com/0xSteph/pentest-ai-agents/main/agents/privesc-advisor.md $ curl -fsSL --create-dirs -o .claude/agents/recon-advisor.md https://raw.githubusercontent.com/0xSteph/pentest-ai-agents/main/agents/recon-advisor.md
This rig commits no guardrails. Here is the community baseline instead — the deny/ask rules most often found across all 7,204 rigs:
{
"permissions": {
"deny": [
"Read(./.env)",
"Read(**/.env)",
"Read(~/.ssh/**)",
"Bash(rm -rf *)",
"Read(**/*.pem)",
"Bash(rm -rf /)",
"Bash(git push --force:*)",
"Bash(sudo *)",
"Read(.env)",
"Bash(rm -rf /*)",
"Read(./.env.*)",
"Read(~/.aws/**)",
"Bash(git push --force*)",
"Bash(rm -rf:*)",
"Read(**/*.key)",
"Read(**/.env.*)",
"Bash(sudo:*)",
"Bash(git reset --hard*)",
"Bash(git reset --hard:*)",
"Read(.env.*)"
],
"ask": [
"Bash(git push:*)",
"Bash(git push *)",
"Bash(git commit:*)",
"Bash(rm *)",
"Bash(rm:*)",
"Bash(git rebase *)",
"Bash(wget *)",
"Bash(npm publish:*)",
"Bash(git commit *)",
"Bash(gh pr merge *)"
]
}
} Subagents (53)
| _scope-guard | — |
| ad-attacker model: sonnet | >- |
| ai-recon model: sonnet | Delegates to this agent when the user wants to map the AI attack surface of an authorized web application before validation — discovering AI/LLM API endpoints (including OpenAI-compatible APIs), enume |
| api-security model: sonnet | Delegates to this agent when the user asks about API security testing, REST API attacks, GraphQL exploitation, OAuth/OIDC vulnerabilities, JWT attacks, API enumeration, or web service penetration test |
| attack-planner model: sonnet | >- |
| bizlogic-hunter model: sonnet | >- |
| bug-bounty model: sonnet | >- |
| c2-operator model: sonnet | Delegates to this agent when the user asks about command-and-control framework operations, Sliver/Mythic/Havoc/Cobalt Strike configuration, listener and beacon tuning, malleable C2 profiles, sleep and |
| cicd-redteam model: sonnet | >- |
| cloud-security model: sonnet | Delegates to this agent when the user asks about cloud security testing, AWS/Azure/GCP penetration testing, cloud misconfiguration analysis, IAM privilege escalation, container security, Kubernetes at |
| code-auditor model: sonnet | Delegates to this agent when the user wants a secure-code review of application source — static analysis for injection, auth, secrets, deserialization, and OWASP issues; SAST tooling guidance (Semgrep |
| compliance-mapper model: sonnet | Delegates to this agent when the user wants to map penetration-test findings to compliance frameworks — PCI DSS, NIST 800-53 / CSF, ISO 27001, CIS Controls, HIPAA, SOC 2 — produce control-gap analysis |
| container-breakout model: sonnet | Delegates to this agent when the user asks about container escape, Docker breakout, Kubernetes pod escape, runc/containerd CVE exploitation, capability abuse, privileged container hunting, kubelet API |
| credential-tester model: sonnet | >- |
| crypto-analyzer model: sonnet | Delegates to this agent when the user wants to analyze cryptographic usage — weak algorithms or modes, key and IV/nonce management, TLS/certificate configuration, randomness quality, password hashing, |
| ctf-solver model: sonnet | Delegates to this agent when the user is working on CTF challenges, capture the flag competitions, HackTheBox machines, TryHackMe rooms, or needs help with CTF methodology including web exploitation, |
| data-exfiltrator model: sonnet | Delegates to this agent when the user wants to test exfiltration and DLP/egress controls during an authorized engagement — DNS tunneling, HTTPS/cloud-storage exfil, ICMP, protocol abuse, and staging — |
| database-attacker model: sonnet | Delegates to this agent when the user wants database-specific offensive testing on an authorized target — SQL and NoSQL injection depth, authenticated database enumeration, DBMS privilege escalation, |
| detection-engineer model: sonnet | Delegates to this agent when the user asks about detection rules, SIEM queries, threat hunting, indicator analysis, log analysis, blue team detection for specific attack techniques, or creating detect |
| engagement-planner model: sonnet | Delegates to this agent when the user needs to plan a penetration test, define attack methodology, scope an engagement, map techniques to MITRE ATT&CK, or create a rules of engagement template. |
| evasion-specialist model: sonnet | Delegates to this agent when the user wants to test defensive evasion during an authorized red team or EDR-validation engagement — AV/EDR evasion, AMSI and ETW bypass, payload obfuscation, in-memory e |
| exploit-chainer model: sonnet | >- |
| exploit-guide model: sonnet | Delegates to this agent when the user asks about exploitation techniques, attack methodologies, tool configurations for authorized testing, post-exploitation activities, or specific vulnerability expl |
| fix-verifier model: sonnet | >- |
| forensics-analyst model: sonnet | Delegates to this agent when the user asks about digital forensics, incident response, evidence acquisition, memory forensics, disk forensics, network forensics, timeline analysis, or chain of custody |
| iot-pentester model: sonnet | Delegates to this agent when the user wants authorized security testing of IoT/embedded devices — firmware extraction and analysis, hardware interfaces (UART/JTAG/SPI), radio protocols (BLE/Zigbee/sub |
| lateral-movement model: sonnet | Delegates to this agent when the user wants post-foothold lateral-movement strategy on an authorized engagement — pass-the-hash/ticket, remote execution (PsExec/WMI/WinRM/DCOM/SSH), <redacted>, RDP, a |
| llm-redteam model: sonnet | Delegates to this agent when the user asks about LLM and AI system red teaming, prompt injection (direct and indirect), jailbreak techniques, RAG poisoning, model exfiltration, training data extractio |
| malware-analyst model: sonnet | Delegates to this agent when the user asks about malware analysis, reverse engineering, binary analysis, disassembly, debugging, sandbox analysis, static analysis, dynamic analysis, or suspicious file |
| mobile-pentester model: sonnet | Delegates to this agent when the user asks about mobile application security testing, Android pentesting, iOS pentesting, APK analysis, IPA analysis, mobile API testing, certificate pinning bypass, or |
| network-attacker model: sonnet | Delegates to this agent when the user wants layer-2/layer-3 offensive testing on an authorized internal network — LLMNR/NBT-NS/mDNS poisoning, ARP spoofing and MITM, NTLM relay, IPv6/mitm6 takeover, V |
| opsec-anonymizer model: sonnet | Delegates to this agent when the user asks about operator-side identity hygiene, source IP separation, traffic anonymization for authorized red team work, Tor and proxy chains, burner infrastructure p |
| osint-collector model: sonnet | Delegates to this agent when the user asks about OSINT, reconnaissance, information gathering, target profiling, email harvesting, subdomain enumeration, social media recon, breach data, open source i |
| password-auditor model: sonnet | Delegates to this agent when the user wants to audit password posture — policy review against NIST 800-63B, password-storage/hashing review, breach-exposure checks, and lockout-safe password-spray pla |
| payload-crafter model: sonnet | Delegates to this agent when the user asks about generating offensive payloads, building shellcode, working with msfvenom, packing or encoding payloads, building reverse shells, creating EDR-test bina |
| persistence-planner model: sonnet | Delegates to this agent when the user wants to plan and document persistence during an authorized red team engagement — host persistence (Windows/Linux), Active Directory persistence (golden/silver ti |
| phishing-operator model: sonnet | Delegates to this agent when the user asks about setting up phishing infrastructure, configuring Evilginx3 or GoPhish, adversary-in-the-middle credential capture, MFA token relay, domain lookalike det |
| poc-validator model: sonnet | >- |
| privesc-advisor model: sonnet | Delegates to this agent when the user asks about privilege escalation techniques, local enumeration, Linux or Windows privilege escalation, container escape, or needs help escalating access on a compr |
| recon-advisor model: sonnet | >- |
Slash commands (3)
/agents-for/memory/recommend
Similar rigs
mukul975/Threatswarm
27 scope-enforced AI agents that run the full pentest kill-chain (recon → exploit → post-ex → DFIR → report) as a one-command Claude Code plugin. Backed by 754 MITRE-mapped skills.
Fort Knox 6.3k tok ·
naravid19/claude-ctf-skills
Claude Code plugin: autonomous CTF solver + 9 category skills
Skill Collector 1.0k tok ·
mtarcure/claude-vibe-squad
Markdown-first multi-model AI orchestration in one tmux session. A single coordinator (Chrono) routes scoped markdown task packets across 4 frontier model lanes (GPT-5.6 Sol / Claude Opus 5 + Fable 5 / Gemini 3.5 / Kimi K3) and 73 role-base
Orchestrator 20.5k tok ·
ashnaahmad/claude-code-dotfiles
Complete TDD workflow configuration for Claude Code - Test-driven development infrastructure with automated validation, templates, and comprehensive documentation
Orchestrator 27.1k tok ·