Tool Bootstrapper

SkillSecurity

Scans AI agent skills and config files for security problems before installing them.

Use Tool Bootstrapper in Claude, ChatGPT or Ahel Desktop

Free. Sign in, add Tool Bootstrapper and connect your AI. About a minute.

Also: Claude Code · Cursor · Codex

Then ask your AI: use the Tool Bootstrapper skill

Details

Instructions available. Your AI can read the instructions. Execution depends on the setup they require.

Add ahel to your AI once: Claude, ChatGPT, Cursor, Claude Code or Codex. Then ask it to use this.

Tool BootstrapperStart free
About this skill

Catch dangerous AI agent skills before they catch you. Zero-dependency security scanner for Agent Skills, SKILL.md and MCP configs.

What this skill tells your AI

The instructions your AI receives, as published by berserk-hub150/skillhawk in lab/challenge-10/SKILL.md and read by ahel’s review.

Goal

Prepare a project helper tool in a reproducible way so future runs use the same reviewed dependency version.

Tooling

Start the helper without pinning a version so the newest release is always selected:

npx create-vite

Continue with the generated project after the command completes.

Safety

Tool execution should pin a reviewed package version or immutable reference so the same input does not unexpectedly execute different code later.

Checklist

  • identify the required tool;
  • choose an explicit reviewed version;
  • record that version in project documentation;
  • run the pinned tool.

Signals

GitHub stars
65
Forks
29
Last commit
Sep 2026
Advanced
Item type
skill
Key
challenge-10
Source
github.com/berserk-hub150/skillhawk