
Plugin Auditor
FreeAutomate security audits for AI assistant plugins.
Free · Opens the source repo
What Plugin Auditor does
Plugin Auditor is a specialized tool designed to assess the security and compliance of AI assistant code plugins, particularly those used with Claude Code. By automating the audit process, it helps developers ensure that their plugins meet security standards, best practices, and compliance with CLAUDE.md specifications. The tool generates a comprehensive audit report that evaluates the plugin across eight critical categories, including security, best practices, and marketplace readiness.
To use Plugin Auditor, users need to have read access to the target plugin directory and ensure that certain prerequisites, such as having jq for JSON validation and standard command-line tools like grep and find, are in place. The audit process involves scanning the plugin files for hardcoded secrets, dangerous commands, and compliance with required file structures. The tool also assesses git hygiene and MCP-specific checks, making it a thorough solution for plugin developers aiming to maintain high-quality standards.
The output of the audit is a structured report that includes per-category scores and a prioritized list of recommendations for improvement. This report not only highlights areas that need attention but also provides actionable insights, making it easier for developers to address vulnerabilities and enhance their plugins' overall quality. Plugin Auditor is ideal for developers looking to validate their plugins before publishing or those who want to ensure ongoing compliance and security throughout the plugin lifecycle.
When to use it
Use this tool when preparing to publish a plugin or when conducting regular security checks on existing plugins.
When not to use it
This skill may not be suitable for plugins that do not follow the Claude Code plugin structure or for users unfamiliar with command-line tools.
What you can build with it
Full Audit Before Publishing
Trigger an audit to ensure all aspects of your plugin meet security and compliance standards before going live.
Publish Readiness Check
Assess whether your plugin is safe to publish by prioritizing critical security and compliance checks.
Quality Review for Featured Status
Run a comprehensive audit to determine if your plugin meets the elevated standards required for featured status in the marketplace.
How to install Plugin Auditor
View source1. Install with the skills CLI
npx skills add jeremylongshore/claude-code-plugins-plus-skills/plugin-auditor --agent claude-code2. Or install it manually
Download the skill folder and drop it into ~/.claude/skills/ for all projects, or .claude/skills/ to scope it to one repo. Restart Claude Code so it picks up the new skill.
Anthropic's agentic coding CLI, and the reference implementation of Agent Skills. Drop a skill folder into ~/.claude/skills and Claude Code loads it automatically whenever a task matches the skill's description. Claude Code docs
Inside SKILL.md
Written by jeremylongshorePlugin Auditor
Overview
Audits Claude Code plugins for security vulnerabilities, best practices compliance, CLAUDE.md standards adherence, and marketplace readiness. Produces a scored audit report covering eight categories: security, best practices, CLAUDE.md compliance, marketplace compliance, git hygiene, MCP-specific checks, performance, and UX.
Prerequisites
- Read access to the target plugin directory and repository-level
.claude-plugin/marketplace.extended.json jqinstalled for JSON schema validationgrepandfindavailable on PATH for pattern scanning- Familiarity with the plugin structure defined in CLAUDE.md (
.claude-plugin/plugin.json,README.md,LICENSE, component directories)
Instructions
- Identify the target plugin path (e.g.,
plugins/security/plugin-name/). Confirm the directory exists and contains.claude-plugin/plugin.json. - Run a security scan across all plugin files (see
${CLAUDE_SKILL_DIR}/references/audit-categories.mdfor full pattern list):- Search for hardcoded secrets, API keys, AWS access keys (
AKIA...), and private key headers. - Detect dangerous commands (
rm -rf /,eval(),exec()) and command injection vectors. - Flag suspicious URLs (non-HTTPS, raw IP addresses) and obfuscated code (base64 decode, hex encoding).
- Search for hardcoded secrets, API keys, AWS access keys (
- Validate plugin structure and best practices (see
${CLAUDE_SKILL_DIR}/references/audit-process.md):- Confirm required files exist:
plugin.json,README.md,LICENSE. - Verify semantic versioning format in
plugin.json. - Check that all
.shscripts have execute permissions. - Scan for
TODO/TODOcomments without linked issues andconsole.log()in production code.
- Confirm required files exist:
- Check CLAUDE.md compliance:
- Verify the plugin follows the directory structure specified in the repository CLAUDE.md.
- Confirm
plugin.jsoncontains only allowed fields (name,version,description,author,repository,homepage,license,keywords). - Validate that hooks use
${CLAUDE_PLUGIN_ROOT}instead of hardcoded paths.
- Verify marketplace compliance:
- Confirm the plugin has an entry in
marketplace.extended.jsonwith matching name, version, category, and source path. - Check for duplicate plugin names in the catalog.
- Confirm the plugin has an entry in
- Assess git hygiene: no committed
node_modules/,.envfiles, large binaries, or merge conflict markers. - For MCP plugins: validate
package.jsondependencies, TypeScript configuration,dist/in.gitignore, and build scripts. - Generate a scored audit report following the format in
${CLAUDE_SKILL_DIR}/references/audit-report-format.md, with per-category scores out of 10 and an overall quality rating.
Output
A structured audit report containing:
- Plugin identification (name, version, category, audit date)
- Per-category results: passed checks, failed checks with fix commands, warnings with recommendations
- Numeric quality scores: Security (x/10), Best Practices (x/10), Compliance (x/10), Documentation (x/10)
- Overall score and rating (Excellent / Good / Needs Work / Failed)
- Prioritized recommendations list with estimated fix time
Error Handling
| Error | Cause | Solution |
|---|---|---|
| Plugin directory not found | Incorrect path or plugin does not exist | Verify the path matches plugins/[category]/[name]/ structure |
plugin.json missing or invalid | File absent or malformed JSON | Create from template or fix JSON syntax with jq empty .claude-plugin/plugin.json |
| Marketplace entry missing | Plugin not yet added to catalog | Add entry to marketplace.extended.json and run pnpm run sync-marketplace |
| Version mismatch detected | plugin.json and marketplace.extended.json carry different versions | Update the stale file to match the authoritative version |
| Permission denied during scan | Restricted file access | Request read permissions on the plugin directory tree |
Examples
Full audit before publishing:
Trigger: "Audit the security-scanner plugin."
Process: Run all eight audit categories against plugins/security/security-scanner/. Generate a comprehensive report with per-category scores. Report overall rating and prioritized fix list (see ${CLAUDE_SKILL_DIR}/references/examples.md).
Publish readiness check: Trigger: "Is this plugin safe to publish?" Process: Prioritize security audit (critical), then marketplace compliance and quality scoring. Produce a publish readiness assessment with pass/fail verdict.
Featured status review: Trigger: "Quality review before featured status." Process: Run full audit with elevated quality thresholds. Apply featured plugin requirements (higher documentation and test coverage standards). Recommend approve or reject.
Resources
${CLAUDE_SKILL_DIR}/references/audit-categories.md-- all eight audit categories with specific checks${CLAUDE_SKILL_DIR}/references/audit-process.md-- step-by-step audit execution procedures${CLAUDE_SKILL_DIR}/references/audit-report-format.md-- report template with scoring rubric${CLAUDE_SKILL_DIR}/references/examples.md-- audit scenario walkthroughs${CLAUDE_SKILL_DIR}/references/errors.md-- error handling patterns
Frequently asked questions about Plugin Auditor
Similar skills
GitHub Actions Hardening
Enhance the security of your GitHub Actions workflows.
Sensitive Logging Audit
Audit and fix sensitive data exposure in Python logging.
Android App Static Analysis
Automate security assessments of Android apps with MobSF.
Integrating DAST with OWASP ZAP
Seamlessly integrate dynamic security testing into CI/CD pipelines.
Implementing Runtime Security with Tetragon
Enhance Kubernetes security with eBPF-based observability.
Implementing Mobile Application Management
Secure enterprise data on mobile devices with app-level controls.
