[opensourcedex]

pentest-ai-agents is a free, open source ai security & privacy project written in Shell and released under MIT. It has 2,239 GitHub stars, 428 forks and 1 open issues, and was last pushed 1 months ago. On this registry it ranks #13 of 34 tracked projects in AI Security & Privacy, with 5 head-to-head comparisons available. It gained 7 stars over the last 3 tracked days.

What is pentest-ai-agents?

What it is

pentest-ai-agents: 50 Claude Code subagents for authorized offensive security research. Lives in Claude Code ecosystem. Agents carry domain knowledge for recon, web, Active Directory, cloud, mobile, wireless, social engineering, payload crafting, reverse engineering, exploit chaining, detection engineering, forensics.

Project solves routing problem. User installs agent files. Opens Claude Code. Describes task. Claude routes to specialist. No servers. No Python deps. No setup beyond copying files. Repository also documents findings database, token optimization, local models, MCP server, container tool execution, prerequisites, legal constraints.

Key capabilities

  • Provides 50 subagents, including ai-recon, code-auditor, crypto-analyzer, password-auditor, database-attacker, network-attacker, traffic-analyzer, compliance-mapper, risk-scorer, evasion-specialist, persistence-planner, data-exfiltrator, scada-attacker, iot-pentester, lateral-movement, c2-operator, container-breakout, opsec-anonymizer, llm-redteam.
  • Pairs offensive techniques with detection they exercise. Supports red-team actions and detection engineering.
  • Enforces scope with _scope-guard.md. Requires block for Bash-capable Tier 2 agents. Hard-refusal list covers DoS, mass scanning, unattended worms, false-flag operations, safety-of-life systems.
  • Tracks findings in Findings Database v2. Adds vulns.tool_used, indexes cve and tool_used. Migrates via db/migrate.sh.
  • Installs as Claude Code plugin via marketplace, via install.sh, or via minimal offline Docker bundle. Docker bundle uses digest-pinned base, non-root user, packages only, no tooling baked in.
  • Validates agent frontmatter, plugin manifests, installer behavior, scope-guard coverage through hardened CI workflow.

Who uses it and how

  • Authorized penetration testers use it to plan engagements, analyze recon, research exploits, build detections, audit STIGs, write reports through Claude Code.
  • Bug-bounty and CTF participants use topic-aligned agents for web, network, cloud, mobile, wireless, Active Directory, reverse engineering, exploit chaining, forensics.
  • Security engineers use detection pairing plus compliance, risk, traffic agents to connect attack techniques to defensive coverage and reporting.
  • Container users run tools inside Docker with external tooling, keep engagement results in findings database.

Getting started

Install plugin with /plugin marketplace add 0xSteph/pentest-ai-agents, then /plugin install pentest-ai-agents@pentest-ai-agents, or use install.sh curl path. Open Claude Code, describe authorized task, let Claude route to subagent; Docker bundle is packaging only and needs external tooling.

When to use it — and when not to

Use when workflow relies on Claude Code and engagement is authorized, because agents are file-based and need no server or Python dependency stack. Avoid when team needs hosted platform, built-in scanning tools, or mature operational history. Repository is new, Docker bundle includes no tooling, user must supply and operate testing environment.

project readme (upstream, from github) — read inline

pentest-ai-agents

50 Claude Code subagents for penetration testing.

License: MIT Claude Code Agents Tools Tracked GitHub stars

Quick Start | Cheatsheet | Coverage | Agents | Examples

Table of Contents

pentest-ai-agents is a collection of 50 Claude Code subagents that turn Claude into an offensive security research assistant. Each agent carries deep domain knowledge in a specific area: recon, web, Active Directory, cloud, mobile, wireless, social engineering, payload crafting, reverse engineering, exploit chaining, detection engineering, forensics, and more.

Install the agent files. Open Claude Code. Describe your task. Claude routes to the right specialist automatically.

No servers, no Python deps, no setup beyond copying files.

What's New in v3.3

  • Installable as a Claude Code plugin. Two lines — /plugin marketplace add 0xSteph/pentest-ai-agents then /plugin install pentest-ai-agents@pentest-ai-agents. The install.sh curl path still works unchanged.
  • 15 new agents (35 → 50): ai-recon (AI attack-surface mapping), code-auditor, crypto-analyzer, password-auditor, database-attacker, network-attacker, traffic-analyzer, compliance-mapper, risk-scorer, plus the post-exploitation set — evasion-specialist, persistence-planner, data-exfiltrator, scada-attacker, iot-pentester, lateral-movement. Every offensive agent pairs its techniques with the detection they exercise.
  • Hardened CI validator. A SHA-pinned, least-privilege workflow validates each agent's frontmatter, requires the scope-guard block on every Bash-capable (Tier 2) agent, checks the plugin manifests, and smoke-tests the installer.
  • Scope-guard gap closed. cicd-redteam is Bash-capable but was missing the mandatory scope-enforcement block — now fixed (the new CI check would have caught it).
  • Installer fixes. curl | bash no longer crashes under set -u, the one-liner clone URL is corrected, slash commands now install alongside the agents, and --uninstall removes everything cleanly.
  • Minimal offline Docker bundle with a digest-pinned base and non-root user — packaging only, no tooling baked in.

What's New in v3.2

  • 4 new agents: c2-operator (Sliver/Mythic/Havoc/Cobalt Strike profile tuning, beacon hygiene, redirector design), container-breakout (Docker/K8s escape, runc/cri-o CVEs, kubelet exploitation, RBAC abuse), opsec-anonymizer (operator-side identity hygiene, source IP design, burner infrastructure, fingerprint hygiene), llm-redteam (OWASP LLM Top 10 testing, prompt injection, RAG poisoning, MCP server abuse, agent tool abuse).
  • Tightened scope guard: explicit hard-refusal list in _scope-guard.md covers DoS, mass scanning, unattended worms, false-flag operations, safety-of-life systems.
  • Findings DB v2: vulns.tool_used column for filtering findings by the tool that produced them; new indexes on cve and tool_used. Existing engagements migrate forward via db/migrate.sh.
  • Agent map diagram: visual flow from recon to closure mapped to agent names (see below).

Agent Map

flowchart LR
    classDef plan fill:#1a2a4a,stroke:#5a7ab8,color:#eaf0ff
    classDef recon fill:#1a3a2a,stroke:#5ab87a,color:#eaffea
    classDef exploit fill:#3a1a1a,stroke:#b85a5a,color:#ffeaea
    classDef post fill:#3a2a1a,stroke:#b8895a,color:#fff0ea
    classDef defense fill:#1a3a3a,stroke:#5ab8b8,color:#eaffff
    classDef report fill:#2a1a3a,stroke:#895ab8,color:#f0eaff

    EP[engagement-planner]:::plan
    OA[opsec-anonymizer]:::plan
    TM[threat-modeler]:::plan

    OS[osint-collector]:::recon
    RA[recon-advisor]:::recon
    VS[vuln-scanner]:::recon

    WH[web-hunter]:::exploit
    AS[api-security]:::exploit
    BL[bizlogic-hunter]:::exploit
    BB[bug-bounty]:::exploit
    AD[ad-attacker]:::exploit
    CS[cloud-security]:::exploit
    MP[mobile-pentester]:::exploit
    WP[wireless-pentester]:::exploit
    LR[llm-redteam]:::exploit
    SE[social-engineer]:::exploit
    PO[phishing-operator]:::exploit
    CT[ctf-solver]:::exploit
    CR[credential-tester]:::exploit
    PV[poc-validator]:::exploit
    EG[exploit-guide]:::exploit
    EC[exploit-chainer]:::exploit
    AP[attack-planner]:::exploit
    PC[payload-crafter]:::exploit
    RE[reverse-engineer]:::exploit

    PE[privesc-advisor]:::post
    CB[container-breakout]:::post
    C2[c2-operator]:::post
    CI[cicd-redteam]:::post
    SO[swarm-orchestrator]:::post

    DE[detection-engineer]:::defense
    FA[forensics-analyst]:::defense
    MA[malware-analyst]:::defense
    SA[stig-analyst]:::defense

    RG[report-generator]:::report

    EP --> OA --> OS
    EP --> TM
    OS --> RA --> VS
    VS --> WH & AS & BL & BB & AD & CS & MP & WP & LR
    SE --> PO
    BB --> WH
    PO --> PC --> C2
    AD --> CR
    AD --> PE
    CS --> CB
    CB --> PE
    WH --> PV
    AS --> PV
    PV --> EC --> AP
    EC --> EG
    PC --> RE
    RE --> MA
    AP --> SO
    C2 --> DE
    SO --> RG
    DE --> FA
    MA --> RG
    SA --> RG
    CT -.solo.-> RG
    CI -.pipeline.-> SO

Tier 1 (advisory) agents are routable from any task. Tier 2 (execution-capable) agents require a declared scope and live in the offensive operations cluster.

What's New in v3.1

  • 3 new agents: payload-crafter (msfvenom, Donut, custom loaders), reverse-engineer (Ghidra, JadX, Radare2, Binwalk), phishing-operator (Evilginx, GoPhish, dnstwist)
  • Slash commands: /recommend "freeform task" routes you to the right agent + concrete commands. /agents-for filters the catalog by domain.
  • db/doctor.sh: audits which underlying CLI tools are installed on your box, grouped by agent. Shows ✔ and ✘ per tool with install hints.
  • install.sh --tools: opt-in installer that pulls in the underlying tools via apt/brew/pacman + pipx/go/cargo.
  • Extended agents: Commix added to web-hunter, RouterSploit added to vuln-scanner, targeted wordlist generation (cupp, CeWL, Mentalist, Crunch, hashid, haiti) added to credential-tester, full steganography toolkit added to ctf-solver.

Quick Start

One command:

curl -fsSL https://raw.githubusercontent.com/0xSteph/pentest-ai-agents/main/install.sh | bash

That's it. The script clones the repo to a temp dir, copies the agents to ~/.claude/agents/, and exits. Idempotent: safe to re-run for updates.

Or install as a Claude Code plugin (no clone; updates through the marketplace):

/plugin marketplace add 0xSteph/pentest-ai-agents
/plugin install pentest-ai-agents@pentest-ai-agents

This registers all 52 agents and the slash commands through Claude Code's plugin system. Pick the plugin or the installer — you don't need both.

Then open Claude Code:

"Plan an internal network pentest for a 500-endpoint AD environment with a 2-week window."

Claude routes to the engagement planner agent and produces a phased plan with MITRE ATT&CK mappings.

Prefer to clone first?

git clone https://github.com/0xSteph/pentest-ai-agents.git
cd pentest-ai-agents && ./install.sh --global

Other install options:

./install.sh --project     # Install for current project only
./install.sh --global --lite  # Use Haiku for advisory agents (lower cost)
./install.sh --tools       # Install underlying CLI tools (nmap, nuclei, ffuf, etc.)
./install.sh --help        # All options

See INSTALL.md for step-by-step instructions, including first-time Claude Code setup.

Cheatsheet

Quick interactions once installed:

Command What It Does
/recommend "phish a small SaaS team's IT department" Picks the right agent and gives concrete next commands
/agents-for web Lists every agent relevant to web

readme truncated — read the full docs on github

Frequently asked questions

Is pentest-ai-agents free to use?

pentest-ai-agents is open source under the MIT licence. There is no licence fee and no seat count — you can self-host it or, where the project offers one, pay a vendor for a managed version instead.

What does pentest-ai-agents do?

Turn Claude Code into your offensive security research assistant. Specialized AI subagents for authorized penetration testing plan engagements, analyze recon, r

What is pentest-ai-agents written in?

pentest-ai-agents is primarily written in Shell. Its source is publicly available at https://github.com/0xSteph/pentest-ai-agents, and it has 2,239 GitHub stars.