code-audit

Audit code security using LSP-driven analysis for vulnerabilities and data flow.

Updated Jan 28, 2026
One-click install
npx skills add https://github.com/xuziqiang98/my-skills --skill code-audit-xuziqiang98
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: code-audit
Source: https://github.com/xuziqiang98/my-skills/tree/main/code-audit
Command: npx skills add https://github.com/xuziqiang98/my-skills --skill code-audit-xuziqiang98

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill includes scripts (resource) and references (resource) components.

What problem does it solve?

This Skill automates the process of identifying security vulnerabilities in codebases across various programming languages and project types, moving beyond simple rule-based scanning to intelligent, LSP-driven code comprehension.

Core Features & Use Cases

  • LSP-driven Code Understanding: Leverages Language Server Protocol for deep code analysis, symbol tracing, and data flow tracking.
  • Multi-dimensional Auditing: Covers taint analysis, authentication/authorization flaws, business logic errors, sensitive data exposure, and more.
  • Project-Type Agnostic: Adapts to any project type without pre-defined rules.
  • Use Case: Audit a complex web application codebase to identify potential SQL injection, cross-site scripting (XSS), and business logic vulnerabilities, generating a detailed report with PoCs.

Quick Start

Use the code-audit skill to perform a security audit on the current project directory.

Frequently Asked Questions about code-audit

High-intent search queries and answers about installing and using this skill.

FAQPage Schema
How do I perform static code security auditing on a complex web application?

Static code security auditing can be performed by leveraging LSP-driven code comprehension to trace data flow and identify vulnerabilities like SQL injection and XSS across diverse project types. This approach understands project-specific characteristics for deep analysis.

How does taint analysis work for vulnerability detection in multi-language codebases?

Taint analysis for vulnerability detection works by using Language Server Protocol to track data flow from untrusted sources to sensitive sinks. This LSP-driven approach adapts to various programming languages without relying on pre-defined rules.

Can I identify business logic errors and sensitive data exposure without predefined rules?

Yes, you can identify business logic errors and sensitive data exposure without predefined rules because the auditing process is project-type agnostic. It understands code structure and project-specific characteristics to detect multi-dimensional flaws.

What is the best way to find authentication and authorization flaws in my codebase?

The best way to find authentication and authorization flaws is through intelligent, LSP-driven static analysis that understands code structure. This method automates identifying vulnerabilities by analyzing multi-dimensional security issues across the codebase.

Does LSP-driven code audit work with any project type or language?

LSP-driven code audit works with any project type or language because it adapts to project-specific characteristics without requiring pre-defined rules. It leverages Language Server Protocol for symbol tracing and data flow tracking across diverse environments.