Dependency Auditor logo

Dependency Auditor

Community
alirezarezvani
dependency-auditor

Check dependencies for known vulnerabilities using npm audit, pip-audit, etc. Use when package.json or requirements.txt changes, or before deployments. Alerts on vulnerable dependencies. Triggers on dependency file changes, deployment prep, security mentions.

Overview

Publisheralirezarezvani
Repositoryclaude-code-tresor
Skill namedependency-auditor
Stars
777
Forks
169
Bundled files
Instructions only
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.

  • Self-contained

    Everything the model needs lives in the instructions — no extra files to sync.

  • Open source

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

Installation

Install the Dependency Auditor 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.
    https://github.com/alirezarezvani/claude-code-tresor/tree/main/skills/security/dependency-auditor
  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/alirezarezvani/claude-code-tresor.git /tmp/claude-code-tresor
mkdir -p .claude/skills
cp -r /tmp/claude-code-tresor/skills/security/dependency-auditor .claude/skills/dependency-auditor
Restart Claude Code after copying so it picks up the new skill.

Use it in TypingMind

Enable Dependency Auditor 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 Dependency Auditor 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 Dependency Auditor 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.

Dependency Auditor Skill

Automatic dependency vulnerability checking.

When I Activate

  • ✅ package.json modified
  • ✅ requirements.txt changed
  • ✅ Gemfile or pom.xml modified
  • ✅ User mentions dependencies or vulnerabilities
  • ✅ Before deployments
  • ✅ yarn.lock or package-lock.json changes

What I Check

Dependency Vulnerabilities

  • Known CVEs in packages
  • Outdated dependencies with security fixes
  • Malicious packages
  • License compatibility issues
  • Deprecated packages

Package Managers Supported

  • Node.js: npm, yarn, pnpm
  • Python: pip, pipenv, poetry
  • Ruby: bundler
  • Java: Maven, Gradle
  • Go: go modules
  • PHP: composer

Example Alerts

NPM Vulnerability

bash
# You run: npm install lodash

# I automatically audit:
🚨 HIGH: Prototype Pollution in lodash
📍 Package: lodash@4.17.15
📦 Vulnerable versions: < 4.17.21
🔧 Fix: npm update lodash
📖 CVE-2020-8203
   https://nvd.nist.gov/vuln/detail/CVE-2020-8203

Recommendation: Update to lodash@4.17.21 or higher

Python Vulnerability

bash
# You modify requirements.txt: django==2.2.0

# I alert:
🚨 CRITICAL: Multiple vulnerabilities in Django 2.2.0
📍 Package: Django@2.2.0
📦 Vulnerable versions: < 2.2.28
🔧 Fix: Update requirements.txt to Django==2.2.28
📖 CVEs: CVE-2021-33203, CVE-2021-33571

Affected: SQL injection, XSS vulnerabilities
Recommendation: Update immediately to Django@2.2.28+

Multiple Vulnerabilities

bash
# After npm install:
🚨 Dependency audit found 8 vulnerabilities:
  - 3 CRITICAL
  - 2 HIGH
  - 2 MEDIUM
  - 1 LOW

Critical issues:
  1. axios@0.21.0 - SSRF vulnerability
     Fix: npm install axios@latest

  2. ajv@6.10.0 - Prototype pollution
     Fix: npm install ajv@^8.0.0

  3. node-fetch@2.6.0 - Information disclosure
     Fix: npm install node-fetch@^2.6.7

Run 'npm audit fix' to automatically fix 6/8 issues

Automatic Actions

On Dependency Changes

yaml
1. Detect package manager (npm, pip, etc.)
2. Run security audit command
3. Parse vulnerability results
4. Categorize by severity
5. Suggest fixes
6. Flag breaking changes

Audit Commands

bash
# Node.js
npm audit
npm audit --json  # Structured output

# Python
pip-audit
safety check

# Ruby
bundle audit

# Java (Maven)
mvn dependency-check:check

Severity Classification

CRITICAL 🚨

  • Remote code execution
  • SQL injection
  • Authentication bypass
  • Publicly exploitable

HIGH ⚠️

  • Cross-site scripting
  • Denial of service
  • Information disclosure
  • Wide attack surface

MEDIUM 📋

  • Limited impact vulnerabilities
  • Requires specific conditions
  • Difficult to exploit

LOW 💡

  • Minor security improvements
  • Best practice violations
  • Minimal risk

Fix Strategies

Automatic Updates

bash
# Safe automatic fixes
npm audit fix

# May include breaking changes
npm audit fix --force

Manual Updates

bash
# Check what will change
npm outdated

# Update specific package
npm update lodash

# Major version update
npm install lodash@latest

Alternative Packages

Vulnerable: request@2.88.0 (deprecated)
Alternative: axios or node-fetch
Migration guide: [link]

Integration with CI/CD

Block Deployments

yaml
# .github/workflows/security.yml
- name: Dependency audit
  run: |
    npm audit --audit-level=high
    # Fails if HIGH or CRITICAL found

Scheduled Audits

yaml
# Weekly dependency check
on:
  schedule:
    - cron: '0 0 * * 0'
jobs:
  audit:
    runs-on: ubuntu-latest
    steps:
      - uses: actions/checkout@v2
      - run: npm audit

Sandboxing Compatibility

Works without sandboxing: ✅ Yes Works with sandboxing: ⚙️ Needs npm/pip registry access

Sandbox config:

json
{
  "network": {
    "allowedDomains": [
      "registry.npmjs.org",
      "pypi.org",
      "rubygems.org",
      "repo.maven.apache.org"
    ]
  }
}

License Checking

I also check license compatibility:

⚠️ License issue: GPL-3.0 package in commercial project
📦 Package: some-gpl-package@1.0.0
📖 GPL-3.0 requires source code disclosure
🔧 Consider: Find MIT/Apache-2.0 alternative

Best Practices

  1. Regular audits: Run weekly or on every dependency change
  2. Update frequently: Keep dependencies current
  3. Review breaking changes: Test before major updates
  4. Pin versions: Use exact versions in production
  5. Audit lock files: Commit and audit lock files

Related Tools

  • security-auditor skill: Code vulnerability detection
  • @architect sub-agent: Dependency strategy
  • /review command: Pre-deployment security check

Frequently asked questions

What does the Dependency Auditor AI skill do?

Check dependencies for known vulnerabilities using npm audit, pip-audit, etc. Use when package.json or requirements.txt changes, or before deployments. Alerts on vulnerable dependencies. Triggers on dependency file changes, deployment prep, security mentions.

Why use Dependency Auditor on TypingMind?

Because you install it once and use it with any model. Dependency Auditor 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 Dependency Auditor in TypingMind?

Open Plugins → Skills → Install from GitHub in TypingMind and paste https://github.com/alirezarezvani/claude-code-tresor/tree/main/skills/security/dependency-auditor. TypingMind reads its SKILL.md and installs it as a skill you can enable per chat.

Which AI models can use Dependency Auditor?

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 Dependency Auditor?

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

Is the Dependency Auditor AI skill free?

Yes. It is published on GitHub by alirezarezvani 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 👇