Skip to content
TrustedSkillsbeta
Back to all skills

Code Auditor

Checked
mhattingpete·vlatest·backend·Apache-2.0

The Code Auditor skill analyzes your code for potential vulnerabilities and style issues, improving security & maintainability.

Repository

Install on your platform

Showing Claude Code. One command installs this skill into any of the agents below.

  1. 1

    Run this in your project

    terminal
    $ npx skills add mhattingpete/claude-skills-marketplace --skill code-auditor -a claude-code

  2. Uses the open-source skills CLI and needs Node.js. Add -g to install it for your user instead of this project.

What we know about this skill

Publisher

mhattingpete

Taken from the source listing. We haven't verified who controls this account.

Install target

Live repository

Not pinned. Installing fetches whatever the repository holds at the time you run the command.

No human has reviewed this code. The checks below are a static scan of the files at one commit — nobody has run this skill or judged whether it works. A skill runs with whatever access you give your agent, so read the source before you install it.

Automated safety checks

scanned

This skill passed all 6 checks. We read its files at one commit and looked for the things that make a skill dangerous to run — not for whether it works.

  • Declares what it does: passed

    SKILL.md parses and declares a name and a description.

    SKILL.md exists, its frontmatter parses, and it declares a name and a description.

  • No undeclared network calls: passed

    Makes no network calls.

    Every host the skill dials — from its scripts, its config endpoints or the commands it tells the agent to run — is either well-known package and API infrastructure or declared in its own frontmatter. Links in documentation are not counted.

  • No obfuscated payloads: passed

    No encoded or obfuscated payloads.

    No base64, hex or compressed blob is decoded and then executed, and no encoded shell commands.

  • No credential access: passed

    Reads no keys, tokens, keychains or credential files.

    Neither the code nor the SKILL.md instructions read SSH keys, cloud credentials, keychains, token stores, browser cookie databases or dotfiles that hold secrets.

  • No pipe-to-shell installers: passed

    No pipe-to-shell or download-and-run installers.

    No `curl … | sh` pattern, in the code or in the instructions, that runs code fetched at run time.

  • Pinned to a commit: passed

    Scanned mhattingpete/claude-skills-marketplace at b5b34bcf4c.

    The exact upstream commit SHA that was scanned is recorded, so the result refers to specific bytes.

Commit
b5b34bcf4c
Manifest
productivity-skills-plugin/skills/code-auditor/SKILL.md
Scanned
1 file, 141 lines
This is a static scan, not a review. It reads the skill's files; it does not run them, and it cannot tell you whether the skill is any good or whether the code does what its description says. A skill runs with whatever access you give your agent.
What each check looks for →

About this skill

What it does

The Code Auditor skill performs comprehensive analyses of codebases to identify potential vulnerabilities, style issues, and areas for improvement. It assesses architecture, code quality, security, performance, testing practices, and maintainability. The analysis results in a detailed report with prioritized recommendations to enhance the codebase's overall health and reduce technical debt.

When to use it

  • To quickly identify critical issues within a project ("audit the code").
  • When needing a thorough review of code quality and potential problems ("analyze code quality").
  • For security assessments, specifically looking for common vulnerabilities ("security audit").
  • To understand the overall architecture and design patterns used in a codebase ("review the codebase").
  • To uncover areas of technical debt that may impact future development ("find technical debt").
  • When needing to evaluate performance bottlenecks within an application ("performance review").

Key capabilities

  • Architecture & Design Analysis: Evaluates structure, design patterns, module boundaries, and dependency management.
  • Code Quality Assessment: Identifies complexity hotspots, code duplication, naming inconsistencies, and anti-patterns.
  • Security Vulnerability Detection: Checks for common vulnerabilities (OWASP Top 10), input validation issues, and secrets management problems.
  • Performance Review: Examines algorithmic complexity, database queries, memory usage, and caching opportunities.
  • Testing Evaluation: Assesses test coverage, quality, missing scenarios, and integration/unit test balance.
  • Maintainability Analysis: Evaluates technical debt, coupling, ease of future changes, and documentation quality.
  • Thoroughness Levels: Offers Quick (15-30 min), Standard (30-60 min), and Deep (60+ min) analysis options.

Example prompts

  • "Code Auditor: audit the code for security vulnerabilities."
  • "Code Auditor: analyze code quality, focusing on potential performance issues."
  • "Code Auditor: review the codebase with a standard thoroughness level."

Tips & gotchas

  • The skill utilizes the Explore agent in "thorough mode," which can take significant time depending on the size of the codebase.
  • Analysis depth is configurable (Quick, Standard, Deep) to balance speed and comprehensiveness. Start with Quick for a fast overview.
  • The output is structured as a report including an executive summary, findings categorized by area, prioritized action plan, and key metrics.