LaunchKit · 2026
Back to Skills

audit-code

Security-focused code review for hardcoded secrets, dangerous calls, and common vulnerabilities.

2
1.9k downloads
by @itsnishi

Setup & Installation

openclaw skills install @itsnishi/audit-code

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

npx clawhub install audit-code

What This Skill Does

Runs a Python-based static analysis script against a project directory to surface security issues. Checks for hardcoded secrets, dangerous function calls, SQL injection patterns, sensitive committed files, and data exfiltration patterns. Produces a severity-ranked report with file locations and remediation steps.

Combines multiple vulnerability categories (secrets, dangerous calls, SQL injection, exfiltration) into a single automated pass instead of running separate tools for each concern.

When to use it

  • Scanning a codebase before opening a pull request
  • Reviewing AI-generated code for accidentally embedded secrets
  • Auditing third-party contributions before merging
  • Checking for .env files accidentally committed to git
  • Running a periodic security sweep on a growing codebase

Example Workflow

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

INPUT

User asks: audit the src/ directory for security issues

AGENT
  1. 1Resolve the target path to src/ within the project root
  2. 2Run audit_code.py against src/
  3. 3Parse the structured output for severity-ranked findings
  4. 4Report file locations and remediation steps for each finding
OUTPUT

A ranked list of findings, such as a hardcoded AWS key in config.js (high severity) and a subprocess shell=True call in deploy.py (medium severity), each with remediation guidance