cain-agent
Real-world AI penetration testing engineer for authorized assessments — built-in cloud module covering AWS/Azure/GCP + Aliyun/Tencent/Huawei clouds. Built on Cl
What is cain-agent?
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
Overview of cain-agent
What it is
Cain is an AI penetration-testing engineer built for real-world authorized security assessments. It walks a deterministic attack pipeline, enforces scope with engineering constraints, and ships a cloud penetration module covering AWS, Azure, GCP, Aliyun, Tencent Cloud, and Huawei Cloud. It is built on the Claude Agent SDK.
Key features
- Real-world Focus: Business-logic flaws, auth chains, cloud misconfigurations - Cloud Native: AWS / Azure / GCP / Aliyun / Tencent Cloud / Huawei Cloud coverage - Safety First: Read-only by default, scope enforcement, credential redaction - AI-Powered: Claude Agent SDK with deterministic orchestration - Benchmark: self-built vulnerable-terraform evaluation, four-metric scoring - OWASP Top 10: SQLi, XSS, SSRF, CSRF, File Upload, XXE, Command Injection, Path Traversal
Use cases
Authorized penetration testing of real enterprise assets, bug bounty programs, and cloud security assessments (AWS, Azure, GCP, Aliyun, Tencent Cloud, Huawei Cloud). It is designed for testing business-logic flaws, authentication chains, and cloud misconfigurations in production-like environments with WAF and rate limiting.
Getting started
bash git clone https://github.com/cdxiaodong/cain-agent cd cain-agent pip install -e . # or: uv pip install -e . pip install -e .[cloud] # optional AWS S3, Huawei OBS, and Kubernetes checks cain-agent --version Run against a target: bash cain-agent run --target https://app.example.com --total-budget 1800
License and pricing
Licensed under Apache-2.0. Open source and free to use.
Based on the project's public README and repository metadata.