测试与安全

wxmini-security-audit

reason-machines/security-skills

Automated WeChat mini-program security auditing framework using Claude Code Agent Teams with 7 specialized agents for comprehensive static analysis

  • 1078 次安装
  • 12 星标
  • 收录于

安装命令

npx skills add https://github.com/reason-machines/security-skills --skill wxmini-security-audit

SKILL.md

wxmini-security-audit

Skill by ara.so — Security Skills collection.

Automated security auditing framework for WeChat mini-programs using Claude Code Agent Teams. Orchestrates 7 specialized agents to perform comprehensive static analysis covering sensitive information leakage, API endpoint extraction, cryptographic analysis, and vulnerability detection across seven security dimensions.

What It Does

  • Multi-Agent Orchestration: Coordinates 7 specialized agents (decompiler, secret scanner, endpoint miner, crypto analyzer, vulnerability analyzer, custom analyzer, reporter)
  • Dual-Layer Architecture: Python regex scripts ensure 100% rule coverage, LLM agents provide intelligent analysis with context awareness
  • Parallel Phase 2 Execution: Runs 4 analysis agents simultaneously to minimize audit time
  • User Intent Parsing: Automatically triggers deep custom analysis when specific endpoints/parameters are mentioned
  • Pure Static Analysis: Zero network requests, no attack code generation, fully local processing
  • Comprehensive Reporting: Generates both summary reports and detailed documentation with structured data exports

Architecture

The framework operates in sequential phases:

wxmini-security-audit

Skill by ara.so — Security Skills collection.

Automated security auditing framework for WeChat mini-programs using Claude Code Agent Teams. Orchestrates 7 specialized agents to perform comprehensive static analysis covering sensitive information leakage, API endpoint extraction, cryptographic analysis, and vulnerability detection across seven security dimensions.

What It Does

  • Multi-Agent Orchestration: Coordinates 7 specialized agents (decompiler, secret scanner, endpoint miner, crypto analyzer, vulnerability analyzer, custom analyzer, reporter)
  • Dual-Layer Architecture: Python regex scripts ensure 100% rule coverage, LLM agents provide intelligent analysis with context awareness
  • Parallel Phase 2 Execution: Runs 4 analysis agents simultaneously to minimize audit time
  • User Intent Parsing: Automatically triggers deep custom analysis when specific endpoints/parameters are mentioned
  • Pure Static Analysis: Zero network requests, no attack code generation, fully local processing
  • Comprehensive Reporting: Generates both summary reports and detailed documentation with structured data exports

Architecture

The framework operates in sequential phases: