gabrielsoltz

gabrielsoltz / clauditor

Public

Security configuration scanner for Claude Code

11
0
100% credibility
Found Mar 14, 2026 at 11 stars -- GitGems finds repos before they trend. Get early access to the next one.
Sign Up Free
AI Analysis
Python
AI Summary

Clauditor scans AI coding assistant configurations for security weaknesses and generates hardened settings files.

How It Works

1
🔍 Hear about a security checker

You learn about a simple tool that spots risks in your AI coding helper's setup while reading docs or GitHub.

2
📥 Grab the tool

You install it quickly on your computer so it's ready to use anytime.

3
📁 Check your project

You run it on your work folder to see how safe your AI assistant is configured.

4
📊 Spot the issues clearly

A neat table shows what's good, what's risky, and exactly how to fix each problem.

5
✨ Make safe settings

You create a ready-to-use file with all the secure choices for your setup.

6
🔧 Apply the fixes

You copy the safe settings into place and feel in control.

🛡️ AI assistant secured

Your coding helper now runs safely, blocking risks without slowing you down.

Sign up to see the full architecture

5 more

Sign Up Free

Star Growth

See how this repo grew from 11 to 11 stars Sign Up Free
Repurpose This Repo

Repurpose is a Pro feature

Generate ready-to-use prompts for X threads, LinkedIn posts, blog posts, YouTube scripts, and more -- with full repo context baked in.

Unlock Repurpose
AI-Generated Review

What is clauditor?

Clauditor is a Python CLI security configuration scanner for Claude Code, auditing settings across user, project, local, and managed scopes plus repo files like CODEOWNERS. It flags misconfigs like unrestricted Bash access or project-level credential helpers with 50+ YAML-defined checks, each tied to threats and remediations. Run `clauditor scan` on local paths, remote Git URLs, or CI pipelines for github security scanning-style reports with effective status after scope precedence.

Why is it gaining traction?

Unlike generic config linters, it understands Claude Code's scope hierarchy (managed > local > project > user), showing covered overrides and generating hardened JSON via `clauditor generate --scope managed`. CI exit codes, severity filters, and remote cloning hook devs into security github actions without setup hassle. Extensible checks and rich output make security configuration assessment feel actionable, not academic.

Who should use this?

Security teams doing security configuration assessment on enterprise Claude Code fleets with managed settings. Repo owners enforcing CODEOWNERS via GitHub security policy in AI-heavy projects. Devs cloning untrusted repos, scanning for supply chain risks like malicious hooks before firing up sessions.

Verdict

Practical security configuration tool for Claude Code users—pipx install and scan in seconds, with verbose remediations and auto-fixes. 11 stars and 1.0% credibility mark it alpha (v0.4.1), but pre-commit hooks, tests, and docs show polish; run in CI first to build trust.

(198 words)

Sign up to read the full AI review Sign Up Free

Similar repos coming soon.