detect-vulnerability

Identify security vulnerabilities in git diffs using a multi-agent analysis pipeline.

3|2|Updated Mar 14, 2026

Search Tags:#security #vulnerability #mcp #static-analysis #git-diff #cwe #rag-retrieval

Ready to run

npx skills add https://github.com/wzh4464/claude-skills --skill detect-vulnerability

💬 Prompt for ChatGPT / Claude Chat▼

Please help me install this Agent Skill.
Skill: detect-vulnerability
Source: https://github.com/wzh4464/claude-skills/tree/main/detect-vulnerability
Command: npx skills add https://github.com/wzh4464/claude-skills --skill detect-vulnerability

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

Scans incremental code changes (git diff) to surface security vulnerabilities before merges, reducing risk in code reviews and CI workflows.

Core Features & Use Cases

Multi-agent vulnerability analysis using evolved prompts, RAG retrieval, and heuristic validation to identify CWE-labeled issues in diffs.
Works offline with host model reasoning and a local MCP server, enabling secure, API-free vulnerability detection during development.
Ideal for pre-commit checks, CI gates, or manual reviews to surface security flaws in incremental changes and guide fixes.

Quick Start

Run the git-diff vulnerability scan using the MCP server evoprompt-detect to generate a report of findings.

Frequently Asked Questions about detect-vulnerability

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

FAQPage Schema

How do I detect security vulnerabilities in git diff before merging?▼

Detect vulnerabilities in incremental git diff changes using a multi-agent pipeline. It analyzes code against the last commit to surface CWE-labeled security flaws and guide fixes before merges.

Can I perform static analysis for vulnerabilities without external API configuration?▼

Yes, static vulnerability analysis works offline without external API configuration. It relies on host model reasoning and a local MCP server to securely identify CWE-labeled issues in code.

What types of security vulnerabilities can multi-agent static analysis identify in code?▼

Multi-agent static analysis identifies vulnerabilities across Memory, Injection, Logic, Input, and Crypto categories. Findings include specific CWE IDs and actionable fixes for security flaws.

How does RAG retrieval work in vulnerability detection for incremental code changes?▼

RAG retrieval augments multi-agent vulnerability analysis by fetching relevant security context for incremental code changes. This validates heuristic findings and improves CWE identification accuracy.

Is there a way to automate pre-commit security checks using static analysis?▼

Automate pre-commit security checks by running git-diff vulnerability scans to generate reports. This surfaces flaws in incremental changes, serving as a CI gate or manual review aid.