vulnerability-scanning · aj-geddes — Claude Code skill: scan for vulnerabilities
A skill that walks your agent through finding vulnerabilities in dependencies, code, containers and secrets. Useful before deploys and during security audits.
npx skills add aj-geddes/useful-ai-prompts --skill vulnerability-scanning -a claude-codeWhat vulnerability-scanning does
The skill guides the agent through security checks: dependency scanning, code review, Docker image inspection and secret detection. Findings land in separate lists per category, so you can see where the problem actually is.
The bundled example is Node.js: a VulnerabilityScanner class shells out to npm audit --json via child_process and parses the output. Full implementations live in references/ — a Node.js scanner, a Python scanner built on OWASP tooling, and a CI/CD integration for GitHub Actions.
The skill advises automating scans in CI/CD, setting severity thresholds and documenting false positives. Relying on a single scanner is a bad idea: different tools catch different things, so mismatched reports are a reason to look closer, not to skip them.
What it helps with
- catch vulnerable dependencies before a release
- check a Docker image against known CVEs
- strip secrets out of a repository
- wire scanning into a GitHub Actions pipeline
- produce findings for a PCI-DSS or SOC 2 audit
Example prompts for the agent
- scan the project dependencies and list high severity vulnerabilities
- set up vulnerability scanning in GitHub Actions before deploy
- check the Docker image and the code for leaked secrets
How to install vulnerability-scanning
1Skills CLI (Vercel)
npx skills add aj-geddes/useful-ai-prompts --skill vulnerability-scanning -a claude-code2Manually: put the files in place
~/.claude/skills/vulnerability-scanning/SKILL.mdCopy the whole skill folder; for one project use .claude/skills/vulnerability-scanning/
1Skills CLI (Vercel)
npx skills add aj-geddes/useful-ai-prompts --skill vulnerability-scanning -a codex2Manually: put the files in place
.agents/skills/vulnerability-scanning/SKILL.mdFor all projects use ~/.agents/skills/
1Skills CLI (Vercel)
npx skills add aj-geddes/useful-ai-prompts --skill vulnerability-scanning -a cursor2Manually: put the files in place
.cursor/skills/vulnerability-scanning/SKILL.mdCursor also reads .agents/skills/ and .claude/skills/
1GitHub CLI
gh skill install aj-geddes/useful-ai-prompts vulnerability-scanning2Manually: put the files in place
.github/skills/vulnerability-scanning/SKILL.md1Skills CLI (Vercel)
npx skills add aj-geddes/useful-ai-prompts --skill vulnerability-scanning -a gemini-cli2Platform CLI
gemini skills install https://github.com/aj-geddes/useful-ai-prompts --path skills/vulnerability-scanningManually: put the files in place
.devin/skills/vulnerability-scanning/SKILL.mdThe legacy .windsurf/skills/ path still works
Skills CLI (Vercel)
npx skills add aj-geddes/useful-ai-prompts --skill vulnerability-scanning -a opencodeClaude.ai
Zip the folder and upload it in Settings → Capabilities → Skills
Step by step, with commands for each platform: How to install skills in Claude Code: five ways
Questions about vulnerability-scanning
How do I install vulnerability-scanning in Claude?
Run npx skills add aj-geddes/useful-ai-prompts --skill vulnerability-scanning -a claude-code. The skill lands at ~/.claude/skills/vulnerability-scanning/SKILL.md.
What does vulnerability-scanning do?
It walks the agent through automated scanning of dependencies, code, containers and secrets, using OWASP tools, CVE databases and security scanners.
Which platforms support it?
Claude, Codex, Cursor, GitHub Copilot, Gemini CLI and OpenCode, each with its own install command.
Source text
SKILL.md · MIT
---
name: vulnerability-scanning
description: >
Automated vulnerability detection using OWASP tools, CVE databases, and
security scanners. Use when performing security audits, compliance checks, or
continuous security monitoring.
---
# Vulnerability Scanning
## Table of Contents
- [Overview](#overview)
- [When to Use](#when-to-use)
- [Quick Start](#quick-start)
- [Reference Guides](#reference-guides)
- [Best Practices](#best-practices)
## Overview
Systematically identify security vulnerabilities in applications, dependencies, and infrastructure using automated scanning tools and manual security assessments.
## When to Use
- Pre-deployment security checks
- Continuous security monitoring
- Compliance audits (PCI-DSS, SOC 2)
- Dependency vulnerability detection
- Container security scanning
- Infrastructure security assessment
## Quick Start
Minimal working example:
```javascript
// scanner.js - Comprehensive vulnerability scanning
const { exec } = require("child_process");
const util = require("util");
const fs = require("fs").promises;
const execPromise = util.promisify(exec);
class VulnerabilityScanner {
constructor() {
this.results = {
dependencies: [],
code: [],
docker: [],
secrets: [],
};
}
async scanDependencies() {
console.log("Scanning dependencies with npm audit...");
try {
const { stdout } = await execPromise("npm audit --json");
const auditResults = JSON.parse(stdout);
for (const [name, advisory] of Object.entries(
// ... (see reference guides for full implementation)
```
## Reference Guides
Detailed implementations in the `references/` directory:
| Guide | Contents |
|---|---|
| [Node.js Vulnerability Scanner](references/nodejs-vulnerability-scanner.md) | Node.js Vulnerability Scanner |
| [Python OWASP Scanner](references/python-owasp-scanner.md) | Python OWASP Scanner |
| [CI/CD Integration - GitHub Actions](references/cicd-integration-github-actions.md) | CI/CD Integration - GitHub Actions |
## Best Practices
### ✅ DO
- Automate scans in CI/CD
- Scan dependencies regularly
- Use multiple scanning tools
- Set severity thresholds
- Track vulnerability trends
- Scan containers and images
- Monitor CVE databases
- Document false positives
### ❌ DON'T
- Skip vulnerability scanning
- Ignore low severity issues
- Trust single scanning tool
- Bypass security gates
- Commit secrets to repos
© aj-geddes · MIT · aj-geddes/useful-ai-prompts
Similar skills
Everything for Security →vulnerability-scanning by other authors comes first.