Code Vuln Audit logo

Code Vuln Audit

CommunityPopular
zebbern
code-vuln-audit

Scan code for security issues: dependency vulnerabilities (npm/pip audit), secret leaks (regex and entropy analysis), and OWASP anti-patterns like SQL injection, XSS, or command injection. Use when the user mentions security scans, vulnerability detection, secret leaks, API keys, OWASP, npm audit, pip-audit, hardcoded passwords, or code security checks.

Overview

Publisherzebbern
Repositoryclaude-code-guide
Skill namecode-vuln-audit
Stars
4.6K
Forks
464
Bundled files
1
LicenseMIT
Links
  • Markdown instructions

    A SKILL.md file the model loads on demand, so it only costs tokens when a request actually matches.

  • Works with any LLM

    AI skills are plain Markdown, not provider-specific code, so this works with GPT, Claude, Gemini, Grok, or a local model.

  • 1 bundled files

    Scripts, templates, and references the model can read while it works. Files are read-only and never executed.

  • Open source

    Published by zebbern on GitHub. Read the source before you install it.

Installation

Install the Code Vuln Audit AI skill in TypingMind to use it with any LLM, or drop it into another agent that reads SKILL.md.

1

Install in TypingMind

TypingMind installs a skill straight from its GitHub folder — it reads SKILL.md, bundles the resource files, and stores the result locally.

  1. Open the app and go to Plugins → Skills.
  2. Choose "Install from GitHub".
  3. Paste the skill folder URL below and confirm.
  4. Enable the skill in any chat where you want it available.
Plugins → Skills → Add skill → From GitHub URL, then paste the folder URL and press Continue.
2

Install in another agent

Any agent that reads the Agent Skills format can use this skill — copy the folder into that agent's skills directory.

Claude Code — .claude/skills
git clone --depth 1 https://github.com/zebbern/claude-code-guide.git /tmp/claude-code-guide
mkdir -p .claude/skills
cp -r /tmp/claude-code-guide/skills/code-vuln-audit .claude/skills/code-vuln-audit
Restart Claude Code after copying so it picks up the new skill.

Use it in TypingMind

Enable Code Vuln Audit in any TypingMind chat and the model takes it from there. Its name and description sit in the system prompt, and the moment a request matches, the model loads the full instructions itself — you never invoke it by hand, and it costs no tokens until it is actually used.

The model loads Code Vuln Audit on its own as soon as a request matches it.

Works with any AI model

AI skills are plain Markdown instructions rather than provider-specific code, so Code Vuln Audit is not tied to the model it was written for. Install it once in TypingMind and use it with GPT-5, Claude, Gemini, Grok, DeepSeek, Mistral, Llama, or a local model you run yourself — all on your own API keys.

  • Loaded only when it is needed

    The system prompt carries just the name and description. The instructions are fetched on the first matching request, so an idle skill costs nothing.

  • Switch models mid-chat

    Because the skill is instructions rather than code, changing model does not break it — the next model reads the same SKILL.md.

Skill instructions

This is the SKILL.md content the model loads. Read it before installing — a skill is instructions your model will follow.

code-vuln-audit

A code security scanning tool with three core scanning capabilities:

  1. Dependency Vulnerability Scanning — Automatically detects known vulnerabilities in npm / pip dependencies
  2. Secret Leak Detection — Discovers hardcoded secrets, tokens, and passwords via regex matching + Shannon entropy analysis
  3. OWASP Pattern Detection — Identifies common security anti-patterns such as SQL injection, XSS, command injection, and insecure deserialization

Quick Start

bash
# Scan the current directory (all checks)
python3 scripts/security_scan.py .

# Scan dependencies only
python3 scripts/security_scan.py --mode deps .

# Detect secret leaks only
python3 scripts/security_scan.py --mode secrets /path/to/project

# Detect OWASP security patterns only
python3 scripts/security_scan.py --mode owasp .

# Output report in JSON format
python3 scripts/security_scan.py --format json --output report.json .

# Only show findings at high severity and above
python3 scripts/security_scan.py --severity high .

Scan Module Details

1. Dependency Vulnerability Scanning (deps)

Automatically detects the project type and invokes the appropriate tool:

Project TypeDetection FileTool Used
Node.jspackage.json + package-lock.jsonnpm audit
Pythonrequirements.txt / pyproject.toml / Pipfilepip-audit

If the corresponding audit tool is not installed, a helpful message is displayed instead of an error.

2. Secret Leak Detection (secrets)

Detection is performed in two ways:

Regex Matching: Covers common secret formats

Secret TypeExample Pattern
AWS Access Key20-character string starting with AKIA
GitHub TokenStarts with ghp_ or github_pat_
Slack TokenStarts with xoxb- or xoxp-
Stripe KeyStarts with sk_live_ or pk_live_
Private Key File-----BEGIN PRIVATE KEY-----
Generic API KeyFormat like api_key = "..."
Credentials in URLhttps://user:pass@host
JWT TokeneyJ... format

Shannon Entropy Analysis: Computes information entropy for string constants in code (threshold > 4.5 and length >= 20) to discover secrets in non-standard formats.

3. OWASP Pattern Detection (owasp)

Covers statically detectable security patterns from the OWASP Top 10:

OWASP CategoryDetection Patterns
A02: Cryptographic FailuresWeak hashes (MD5/SHA1), weak ciphers (DES/RC4)
A03: InjectionSQL injection, command injection (os.system / subprocess shell / eval / exec), XSS (innerHTML / document.write / dangerouslySetInnerHTML / v-html)
A04: Insecure DesignPath traversal
A05: Security MisconfigurationDebug mode enabled, CORS wildcard, binding to 0.0.0.0
A08: Integrity FailuresInsecure deserialization (pickle / yaml.load / marshal / unserialize)
A10: SSRFUser input passed directly to HTTP requests

Supported languages: Python, JavaScript/TypeScript, Java, PHP, Ruby, Go, and more.

Parameters

ParameterDescriptionDefault
TARGETDirectory to scanCurrent directory
--mode MODEScan mode: all, deps, secrets, owaspall
--format FORMATOutput format: text, jsontext
--output FILEOutput file pathstdout
--severity LEVELMinimum reporting level: low, medium, high, criticallow
--exclude-dir DIRAdditional directories to exclude (repeatable)-
--max-file-kb SIZEMaximum file size to scan in KB512
-h, --helpShow help-

Output Format

Text Output (default)

=== Security Scan Report ===
Target: /path/to/project
Modules: deps, secrets, owasp

[CRITICAL] AWS Access Key ID
  File: src/config.py:15
  Code: AWS_KEY = "AKIAIOSFODNN7EXAMPLE"

[HIGH] SQL Injection (f-string)
  File: src/db.py:42
  Code: cursor.execute(f"SELECT * FROM users WHERE id={user_id}")

--- Summary ---
Critical: 1 | High: 1 | Medium: 0 | Low: 0
Total findings: 2

JSON Output

json
{
  "target": "/path/to/project",
  "scan_time": "2026-04-14T10:30:00",
  "findings": [
    {
      "scanner": "secrets",
      "name": "AWS Access Key ID",
      "severity": "critical",
      "file": "src/config.py",
      "line": 15,
      "snippet": "AWS_KEY = \"AKIAIOSFODNN7EXAMPLE\"",
      "category": "secret-pattern"
    }
  ],
  "summary": {"critical": 1, "high": 0, "medium": 0, "low": 0, "total": 1}
}

Exit Codes

Exit CodeMeaning
0No findings
1Findings present (at least one security issue)
2Scanner internal error

Prerequisites

  • Python 3.7+ (uses standard library only)
  • Dependency scanning requires the corresponding tools: npm (for Node.js projects), pip-audit (for Python projects)
  • If an audit tool is missing, that module will be skipped with a notice — other modules continue to run normally

Bundled files

The model reads these on demand while the skill is loaded. They are exposed as readable files and are never executed.

Frequently asked questions

What does the Code Vuln Audit AI skill do?

Scan code for security issues: dependency vulnerabilities (npm/pip audit), secret leaks (regex and entropy analysis), and OWASP anti-patterns like SQL injection, XSS, or command injection. Use when the user mentions security scans, vulnerability detection, secret leaks, API keys, OWASP, npm audit, pip-audit, hardcoded passwords, or code security checks.

Why use Code Vuln Audit on TypingMind?

Because you install it once and use it with any model. Code Vuln Audit is plain Markdown rather than provider-specific code, so the same skill runs on GPT-5, Claude, Gemini, Grok, or a local model — and you can switch model mid-chat without it breaking. TypingMind runs on your own API keys, so you pay providers directly instead of a per-seat subscription, and your skills and chats stay in your own storage.

How do I install Code Vuln Audit in TypingMind?

Open Plugins → Skills → Install from GitHub in TypingMind and paste https://github.com/zebbern/claude-code-guide/tree/main/skills/code-vuln-audit. TypingMind reads its SKILL.md and bundles its files and installs it as a skill you can enable per chat.

Which AI models can use Code Vuln Audit?

Any model you connect in TypingMind. AI skills are plain Markdown instructions rather than provider-specific code, so GPT, Claude, Gemini, Grok, and local models can all load this skill when a request matches it.

How many AI models can I use with Code Vuln Audit?

As many as you like. As long as a model supports skills, you can use Code Vuln Audit with it — GPT, Claude, Gemini, Grok, DeepSeek, Mistral, Llama and more — all on TypingMind with your own API keys.

Is the Code Vuln Audit AI skill free?

Yes. It is published on GitHub by zebbern under the MIT license. You only pay your own AI provider for the tokens you use.

What are AI skills?

An AI skill is a reusable instruction bundle that teaches an AI model how to do one specific task. It follows the open Agent Skills format: a SKILL.md file with a name and description, plus any scripts, templates or reference files the model may need. The model reads the instructions only when your request matches the skill, so an installed skill costs nothing until it is used.

How are AI skills different from plugins or MCP servers?

A plugin or MCP server gives a model new tools to call — code that runs somewhere and returns a result. An AI skill gives the model knowledge and process instead: how to approach a task, which steps to follow, what good output looks like. Skills are plain Markdown, so they need no server, no API key and no runtime, and they work with any model.

View all

Set up your own AI workspace now

Get notified about new features and future giveaways by subscribing to our newsletter 👇