Smartbrain skill auditor

Skill smartbrainactivity/smartbrain-skill-auditor

Antigravity. Claude-code. 🇬🇧 Zero-dependency Node.js CLI to statically audit third-party AI Skills for malicious code patterns before local execution. | 🇪🇸 CLI Node.js sin dependencias para auditar estáticamente Skills de IA buscando código malicioso antes de ejecutarlos.

Install

npx -y skills add smartbrainactivity/smartbrain-skill-auditor

Assembled from the repository path, not quoted from the project. Check it against their README if it does not work.

One thing to look at

4 stars4 stars. Stars are a popularity signal and not a quality one, but at this level it is likely that nobody has read this closely except its author, and you would be relying on your own review.

What its author says it does

Copied from the file, not written here

A universal, dependency-free Node.js tool to statically audit AI Skills and local agents for malicious patterns.

SKILL.md

1.3 KB, as published. Nobody here has run it

`ai-skill-auditor`

This skill provides the AI Assistant the capability to automatically audit and review local code directories (such as other downloaded AI Skills) looking for standard malicious patterns (eval, destructive child_process, hidden HTTP requests) before running them.

Instructions for the AI Assistant:

When the user asks you to "audit a skill", "check a folder for security", or "verify the integrity of this downloaded repo":

Use the run_command tool to execute the central audit script.
The argument is the path the user wants to audit.
- Example 1: node {workspaceRoot}/smartbrain-skill-auditor/bin/audit.js "C:/path/to/target/skill"
- Example 2 (If auditing the current folder): node {workspaceRoot}/smartbrain-skill-auditor/bin/audit.js .
Wait for the terminal output.
If it returns 0 vulnerabilities, tell the user the audit passed and provide them with the SMARTbrain Security Badge returned by the console.
If it returns vulnerabilities, explicitly list the files and the malicious patterns found so the user can review them manually. DO NOT run any script in that folder without user consent.