cain-agent

Name: cain-agent
Author: cdxiaodong

Verified

Real-world AI penetration testing engineer for authorized assessments — built-in cloud module covering AWS/Azure/GCP + Aliyun/Tencent/Huawei clouds. Built on Claude Agent SDK

102stars

21forks

Python

Installation

# Add to your Claude Code skills
git clone https://github.com/cdxiaodong/cain-agent

Getting Started

Guides for using ai agents skills like cain-agent.

Caveman: Cut Claude Token Use by 65%
How agent-side prompt compression works, when to use it, and when not to.
What is an AI Skills Marketplace?
Definitions, how marketplaces work, and how to choose between them in 2026.
Getting Started with AI Skills

Security ReportVerified

Last scanned: 8/10/2026

{
  "issues": [],
  "status": "PASSED",
  "scannedAt": "2026-08-10T05:25:28.682Z",
  "npmAuditRan": true,
  "pipAuditRan": true,
  "promptInjectionRan": true
}

README.md

Frequently Asked Questions

What is cain-agent?

cain-agent is an open-source ai agents skill for AI coding assistants such as Claude Code, Codex CLI, and ChatGPT, built by cdxiaodong. Real-world AI penetration testing engineer for authorized assessments — built-in cloud module covering AWS/Azure/GCP + Aliyun/Tencent/Huawei clouds. Built on Claude Agent SDK. It has 102 GitHub stars.

Is cain-agent safe to use?

Yes. cain-agent passed SkillsLLM's automated security scan — a dependency vulnerability audit plus prompt-injection heuristics — with no high-severity issues. You can read the full report in the Security Report section on this page.

How do I install cain-agent?

Clone the repository with "git clone https://github.com/cdxiaodong/cain-agent" and add it to your Claude Code skills directory (see the Installation section above).

What programming language is cain-agent written in?

cain-agent is primarily written in Python. It is open-source under cdxiaodong on GitHub, so you can review or fork the full source.

Are there alternatives to cain-agent?

Yes. SkillsLLM lists many other AI Agents skills you can browse and compare side by side. Open the AI Agents category from the badge at the top of this page, or use the Related Skills and comparison links further down to weigh cain-agent against similar tools.

Agentic AI for Beginners

Build your first AI agent from scratch - tool use, ReAct pattern, memory, deployment

41 minBeginner

Comments (0)

to leave a comment.

No comments yet. Be the first to share your thoughts!

Related Skills

ECC

by affaan-m

The agent harness performance optimization system. Skills, instincts, memory, security, and research-first development for Claude Code, Codex, Opencode, Cursor and beyond.

239,056

awesome-amazon-ec-skills claude-research-plan-implement

Cain — Real-world AI Penetration Testing Engineer

🚧 Under active development. Star & watch for updates.

Cain is an AI penetration testing engineer built for real-world authorized security assessments — not a CTF toy. It understands business logic, maintains a global attack state machine, adapts to real WAF/risk-control environments, and ships with a built-in cloud penetration module covering AWS / Azure / GCP / 阿里云 / 腾讯云 / 华为云.

Built on Claude Agent SDK.

Why Cain

	CTF/靶场型 Agent	Cain (实战型)
Target	Static labs, preset flags	Real enterprise assets, bug bounty, authorized engagements
Vulnerability focus	Known syntax-pattern vulns	Business logic flaws, auth chains, cloud misconfigurations
Environment	No WAF, no rate limiting	Real WAF / risk control with dynamic strategy adjustment
Deliverable	A flag	Auditable evidence chain + reproducible PoC + remediation advice

Features

🎯 Real-world Focus: Business logic flaws, auth chains, cloud misconfigurations
☁️ Cloud Native: AWS / Azure / GCP / 阿里云 / 腾讯云 / 华为云 coverage
🔒 Safety First: Read-only by default, scope enforcement, credential redaction
🤖 AI-Powered: Claude Agent SDK with deterministic orchestration
📊 Benchmark: XBOW + self-built vulnerable-terraform evaluation
🛡️ OWASP Top10: SQLi, XSS, SSRF, CSRF, File Upload, XXE, Command Injection, Path Traversal

Core Design

Deterministic engineering constrains agent freedom — stage transitions, scope enforcement, and dangerous-operation circuit breakers are hard engineering constraints; path selection and evidence analysis are left to the agent.

Orchestrator — deterministic Python state machine (recon → test → framework → report)
Dual-LLM split — Planner (strategy) / Executor (Claude Agent SDK, tactics)
Hook-based safety — PreToolUse scope guard, credential redaction, token budget circuit breaker
Workspace external memory — all state as files; crash-resumable, auditable
Validation loop — finder/validator agent separation, 4-state structured verdicts
Cloud module (unique) — IAM privilege-escalation path analysis, storage exposure (S3/OSS/COS/Blob/GCS), metadata SSRF checks, serverless abuse — including Chinese clouds nobody else covers
65 built-in cloud attack skills — see skills/

⚠️ Legal & Ethical Use

Cain is strictly for authorized security testing — your own environments or engagements with written authorization. Core features run with read-only credentials. Scope is enforced by configuration, not by AI self-discipline. You are responsible for complying with applicable laws.

Quick Start

For Users

pip install cain-agent

For AI Agents — One-Click Install Prompt

"安装 cain-agent 到用户本地 Python 环境，克隆仓库 https://github.com/cdxiaodong/cain-agent，用 pip/uv 装 editable 模式，验证 CLI 可执行"

This single prompt instructs any AI agent to:

Clone the repository
Install in editable mode (pip install -e . or uv pip install -e .)
Verify installation by running cain-agent --version

Status

Phase 0 — project scaffolding. See ROADMAP.md and CHANGELOG.md.

License

Apache-2.0. See LICENSE.