LaunchKit · 2026
Back to Skills

code-security-audit

Comprehensive code security audit toolkit combining OWASP Top 10 vulnerability scanning, dependency analysis.

0
0 downloads
by @wisdomsword

Setup & Installation

openclaw skills install @wisdomsword/code-security-audit

Or with the ClawHub CLI, for registry-managed skill folders outside a full OpenClaw workspace:

npx clawhub install code-security-audit

What This Skill Does

A security audit toolkit covering OWASP Top 10 detection, dependency vulnerability scanning, secret detection, SSL/TLS verification, and AI agent security checks. Produces a quantified 0-100 security score with categorized findings. Supports JavaScript, TypeScript, Python, Go, Java, Rust, PHP, Ruby, and Solidity.

Consolidates OWASP scanning, dependency analysis, secret detection, SSL verification, and AI-specific security checks into a single scored workflow rather than requiring separate tools for each concern.

When to use it

  • Scanning a codebase for hardcoded API keys before a code review
  • Running OWASP Top 10 compliance checks before a security audit
  • Detecting floating-point precision issues in AI agent financial logic
  • Checking npm, pip, or cargo dependencies for known CVEs
  • Verifying SSL/TLS certificate validity and cipher suite support on a live domain

Example Workflow

Here's how your AI assistant might use this skill in practice.

INPUT

User asks: Run a full security audit on my Node.js codebase

AGENT
  1. 1Execute ./scripts/security-audit.sh --full to run all audit modules
  2. 2Scan source files for OWASP Top 10 patterns including injection, broken access control, and XSS
  3. 3Run npm audit to detect dependency vulnerabilities and flag high/critical findings
  4. 4Search for hardcoded secrets matching 70+ patterns including AWS keys, OpenAI tokens, and private keys
  5. 5Calculate a 0-100 security score weighted across OWASP compliance, dependencies, secrets, SSL, and AI agent risks
OUTPUT

Security report with an overall score (e.g., 72/100 Medium Risk), findings grouped by severity with file paths and line numbers, and specific remediation steps for each issue