plugin-auditor

0
0
Source

Automatically audits Claude Code plugins for security vulnerabilities, best practices, CLAUDE.md compliance, and quality standards when user mentions audit plugin, security review, or best practices check. Specific to claude-code-plugins repository standards.

Install

mkdir -p .claude/skills/plugin-auditor && curl -L -o skill.zip "https://mcp.directory/api/skills/download/8512" && unzip -o skill.zip -d .claude/skills/plugin-auditor && rm skill.zip

Installs to .claude/skills/plugin-auditor

About this skill

Plugin Auditor

Purpose

Automatically audits Claude Code plugins for security vulnerabilities, best practice violations, CLAUDE.md compliance, and quality standards - optimized for claude-code-plugins repository requirements.

Trigger Keywords

  • "audit plugin"
  • "security review" or "security audit"
  • "best practices check"
  • "plugin quality"
  • "compliance check"
  • "plugin security"

Audit Categories

1. Security Audit

Critical Checks:

  • ❌ No hardcoded secrets (passwords, API keys, tokens)
  • ❌ No AWS keys (AKIA...)
  • ❌ No private keys (BEGIN PRIVATE KEY)
  • ❌ No dangerous commands (rm -rf /, eval(), exec())
  • ❌ No command injection vectors
  • ❌ No suspicious URLs (IP addresses, non-HTTPS)
  • ❌ No obfuscated code (base64 decode, hex encoding)

Security Patterns:

# Check for hardcoded secrets
grep -r "password\s*=\s*['\"]" --exclude-dir=node_modules
grep -r "api_key\s*=\s*['\"]" --exclude-dir=node_modules
grep -r "secret\s*=\s*['\"]" --exclude-dir=node_modules

# Check for AWS keys
grep -r "AKIA[0-9A-Z]{16}" --exclude=README.md

# Check for private keys
grep -r "BEGIN.*PRIVATE KEY" --exclude=README.md

# Check for dangerous patterns
grep -r "rm -rf /" | grep -v "/var/" | grep -v "/tmp/"
grep -r "eval\s*\(" --exclude=README.md

2. Best Practices Audit

Plugin Structure:

  • ✅ Proper directory hierarchy
  • ✅ Required files present
  • ✅ Semantic versioning (x.y.z)
  • ✅ Clear, concise descriptions
  • ✅ Proper LICENSE file (MIT/Apache-2.0)
  • ✅ Comprehensive README
  • ✅ At least 5 keywords

Code Quality:

  • ✅ No TODO/FIXME without issue links
  • ✅ No console.log() in production code
  • ✅ No hardcoded paths (/home/, /Users/)
  • ✅ Uses ${CLAUDE_PLUGIN_ROOT} in hooks
  • ✅ Scripts have proper shebangs
  • ✅ All scripts are executable

Documentation:

  • ✅ README has installation section
  • ✅ README has usage examples
  • ✅ README has clear description
  • ✅ Commands have proper frontmatter
  • ✅ Agents have model specified
  • ✅ Skills have trigger keywords

3. CLAUDE.md Compliance

Repository Standards:

  • ✅ Follows plugin structure from CLAUDE.md
  • ✅ Uses correct marketplace slug
  • ✅ Proper category assignment
  • ✅ Valid plugin.json schema
  • ✅ Marketplace catalog entry exists
  • ✅ Version consistency

Skills Compliance (if applicable):

  • ✅ SKILL.md has proper frontmatter
  • ✅ Description includes trigger keywords
  • ✅ allowed-tools specified (if restricted)
  • ✅ Clear purpose and instructions
  • ✅ Examples provided

4. Marketplace Compliance

Catalog Requirements:

  • ✅ Plugin listed in marketplace.extended.json
  • ✅ Source path matches actual location
  • ✅ Version matches plugin.json
  • ✅ Category is valid
  • ✅ No duplicate plugin names
  • ✅ Author information complete

5. Git Hygiene

Repository Practices:

  • ✅ No large binary files
  • ✅ No node_modules/ committed
  • ✅ No .env files
  • ✅ Proper .gitignore
  • ✅ No merge conflicts
  • ✅ Clean commit history

6. MCP Plugin Audit (if applicable)

MCP-Specific Checks:

  • ✅ Valid package.json with @modelcontextprotocol/sdk
  • ✅ TypeScript configured correctly
  • ✅ dist/ in .gitignore
  • ✅ Proper mcp/*.json configuration
  • ✅ Build scripts present
  • ✅ No dependency vulnerabilities

7. Performance Audit

Efficiency Checks:

  • ✅ No unnecessary file reads
  • ✅ Efficient glob patterns
  • ✅ No recursive loops
  • ✅ Reasonable timeout values
  • ✅ No memory leaks (event listeners)

8. Accessibility & UX

User Experience:

  • ✅ Clear error messages
  • ✅ Helpful command descriptions
  • ✅ Proper usage examples
  • ✅ Good README formatting
  • ✅ Working demo commands

Audit Process

When activated, I will:

  1. Security Scan

    # Run security checks
    grep -r "password\|secret\|api_key" plugins/plugin-name/
    grep -r "AKIA[0-9A-Z]{16}" plugins/plugin-name/
    grep -r "BEGIN.*PRIVATE KEY" plugins/plugin-name/
    grep -r "rm -rf /" plugins/plugin-name/
    grep -r "eval\(" plugins/plugin-name/
    
  2. Structure Validation

    # Check required files
    test -f .claude-plugin/plugin.json
    test -f README.md
    test -f LICENSE
    
    # Check component directories
    ls -d commands/ agents/ skills/ hooks/ mcp/ 2>/dev/null
    
  3. Best Practices Check

    # Check for TODO/FIXME
    grep -r "TODO\|FIXME" --exclude=README.md
    
    # Check for console.log
    grep -r "console\.log" --exclude=README.md
    
    # Check script permissions
    find . -name "*.sh" ! -perm -u+x
    
  4. Compliance Verification

    # Check marketplace entry
    jq '.plugins[] | select(.name == "plugin-name")' .claude-plugin/marketplace.extended.json
    
    # Verify version consistency
    plugin_version=$(jq -r '.version' .claude-plugin/plugin.json)
    market_version=$(jq -r '.plugins[] | select(.name == "plugin-name") | .version' .claude-plugin/marketplace.extended.json)
    
  5. Generate Audit Report

Audit Report Format

🔍 PLUGIN AUDIT REPORT
Plugin: plugin-name
Version: 1.0.0
Category: security
Audit Date: 2025-10-16

━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━
🔒 SECURITY AUDIT
━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━

✅ PASSED (7/7)
- No hardcoded secrets
- No AWS keys
- No private keys
- No dangerous commands
- No command injection vectors
- HTTPS URLs only
- No obfuscated code

━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━
📋 BEST PRACTICES
━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━

✅ PASSED (10/12)
- Proper directory structure
- Required files present
- Semantic versioning
- Clear descriptions
- Comprehensive README

⚠️  WARNINGS (2)
- 3 scripts missing execute permission
  Fix: chmod +x scripts/*.sh

- 2 TODO items without issue links
  Location: commands/scan.md:45, agents/analyzer.md:67
  Recommendation: Create GitHub issues or remove TODOs

━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━
✅ CLAUDE.MD COMPLIANCE
━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━

✅ PASSED (6/6)
- Follows plugin structure
- Uses correct marketplace slug
- Proper category assignment
- Valid plugin.json schema
- Marketplace entry exists
- Version consistency

━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━
📊 QUALITY SCORE
━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━

Security:        10/10 ✅
Best Practices:   8/10 ⚠️
Compliance:      10/10 ✅
Documentation:   10/10 ✅

OVERALL SCORE: 9.5/10 (EXCELLENT)

━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━
🎯 RECOMMENDATIONS
━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━

Priority: MEDIUM
1. Fix script permissions (2 min)
2. Resolve TODO items (10 min)

Optional Improvements:
- Add more usage examples in README
- Include troubleshooting section
- Add GIF/video demo

✅ AUDIT COMPLETE
Plugin is production-ready with minor improvements needed.

Severity Levels

Critical (🔴):

  • Security vulnerabilities
  • Hardcoded secrets
  • Dangerous commands
  • Missing required files

High (🟠):

  • Best practice violations
  • Missing documentation
  • Broken functionality
  • Schema violations

Medium (🟡):

  • Code quality issues
  • Missing optional features
  • Performance concerns
  • UX improvements

Low (🟢):

  • Style inconsistencies
  • Minor documentation gaps
  • Nice-to-have features

Auto-Fix Capabilities

I can automatically fix:

  • ✅ Script permissions
  • ✅ JSON formatting
  • ✅ Markdown formatting
  • ✅ Version sync issues

Repository-Specific Checks

For claude-code-plugins repo:

  • Validates against CLAUDE.md standards
  • Checks marketplace integration
  • Verifies category structure
  • Ensures quality for featured plugins
  • Checks contributor guidelines compliance

Examples

User says: "Audit the security-scanner plugin"

I automatically:

  1. Run full security scan
  2. Check best practices
  3. Verify CLAUDE.md compliance
  4. Generate comprehensive report
  5. Provide recommendations

User says: "Is this plugin safe to publish?"

I automatically:

  1. Security audit (critical)
  2. Marketplace compliance
  3. Quality score calculation
  4. Publish readiness assessment

User says: "Quality review before featured status"

I automatically:

  1. Full audit (all categories)
  2. Higher quality thresholds
  3. Featured plugin requirements
  4. Recommendation: approve/reject

svg-icon-generator

jeremylongshore

Svg Icon Generator - Auto-activating skill for Visual Content. Triggers on: svg icon generator, svg icon generator Part of the Visual Content skill category.

8227

d2-diagram-creator

jeremylongshore

D2 Diagram Creator - Auto-activating skill for Visual Content. Triggers on: d2 diagram creator, d2 diagram creator Part of the Visual Content skill category.

4926

automating-mobile-app-testing

jeremylongshore

This skill enables automated testing of mobile applications on iOS and Android platforms using frameworks like Appium, Detox, XCUITest, and Espresso. It generates end-to-end tests, sets up page object models, and handles platform-specific elements. Use this skill when the user requests mobile app testing, test automation for iOS or Android, or needs assistance with setting up device farms and simulators. The skill is triggered by terms like "mobile testing", "appium", "detox", "xcuitest", "espresso", "android test", "ios test".

14217

performing-penetration-testing

jeremylongshore

This skill enables automated penetration testing of web applications. It uses the penetration-tester plugin to identify vulnerabilities, including OWASP Top 10 threats, and suggests exploitation techniques. Use this skill when the user requests a "penetration test", "pentest", "vulnerability assessment", or asks to "exploit" a web application. It provides comprehensive reporting on identified security flaws.

4615

designing-database-schemas

jeremylongshore

Design and visualize efficient database schemas, normalize data, map relationships, and generate ERD diagrams and SQL statements.

11514

analyzing-logs

jeremylongshore

Analyze application logs to detect performance issues, identify error patterns, and improve stability by extracting key insights.

11410

You might also like

flutter-development

aj-geddes

Build beautiful cross-platform mobile apps with Flutter and Dart. Covers widgets, state management with Provider/BLoC, navigation, API integration, and material design.

1,1421,171

drawio-diagrams-enhanced

jgtolentino

Create professional draw.io (diagrams.net) diagrams in XML format (.drawio files) with integrated PMP/PMBOK methodologies, extensive visual asset libraries, and industry-standard professional templates. Use this skill when users ask to create flowcharts, swimlane diagrams, cross-functional flowcharts, org charts, network diagrams, UML diagrams, BPMN, project management diagrams (WBS, Gantt, PERT, RACI), risk matrices, stakeholder maps, or any other visual diagram in draw.io format. This skill includes access to custom shape libraries for icons, clipart, and professional symbols.

969933

ui-ux-pro-max

nextlevelbuilder

"UI/UX design intelligence. 50 styles, 21 palettes, 50 font pairings, 20 charts, 8 stacks (React, Next.js, Vue, Svelte, SwiftUI, React Native, Flutter, Tailwind). Actions: plan, build, create, design, implement, review, fix, improve, optimize, enhance, refactor, check UI/UX code. Projects: website, landing page, dashboard, admin panel, e-commerce, SaaS, portfolio, blog, mobile app, .html, .tsx, .vue, .svelte. Elements: button, modal, navbar, sidebar, card, table, form, chart. Styles: glassmorphism, claymorphism, minimalism, brutalism, neumorphism, bento grid, dark mode, responsive, skeuomorphism, flat design. Topics: color palette, accessibility, animation, layout, typography, font pairing, spacing, hover, shadow, gradient."

683829

godot

bfollington

This skill should be used when working on Godot Engine projects. It provides specialized knowledge of Godot's file formats (.gd, .tscn, .tres), architecture patterns (component-based, signal-driven, resource-based), common pitfalls, validation tools, code templates, and CLI workflows. The `godot` command is available for running the game, validating scripts, importing resources, and exporting builds. Use this skill for tasks involving Godot game development, debugging scene/resource files, implementing game systems, or creating new Godot components.

691549

nano-banana-pro

garg-aayush

Generate and edit images using Google's Nano Banana Pro (Gemini 3 Pro Image) API. Use when the user asks to generate, create, edit, modify, change, alter, or update images. Also use when user references an existing image file and asks to modify it in any way (e.g., "modify this image", "change the background", "replace X with Y"). Supports both text-to-image generation and image-to-image editing with configurable resolution (1K default, 2K, or 4K for high resolution). DO NOT read the image file first - use this skill directly with the --input-image parameter.

797540

pdf-to-markdown

aliceisjustplaying

Convert entire PDF documents to clean, structured Markdown for full context loading. Use this skill when the user wants to extract ALL text from a PDF into context (not grep/search), when discussing or analyzing PDF content in full, when the user mentions "load the whole PDF", "bring the PDF into context", "read the entire PDF", or when partial extraction/grepping would miss important context. This is the preferred method for PDF text extraction over page-by-page or grep approaches.

697374

Stay ahead of the MCP ecosystem

Get weekly updates on new skills and servers.