execute-script-safely

Community

Gate ephemeral scripts through haiku pre-review.

Authorebal5
Version1.0.0
Installs0

System Documentation

What problem does it solve?

Running disposable Python or shell scripts inside a sandbox without prior security validation is risky. This Skill enforces a haiku Agent pre-review to judge safety before execution, preventing unsafe actions and potential data exposure.

Core Features & Use Cases

  • Pre-execution security review using a configurable prompt to assess scripts.
  • Sandbox evaluation that blocks external exfiltration while allowing safe inspection of code behavior.
  • Use Case: You need to validate a temporary snippet or a sub-agent generated script before it runs in your environment.

Quick Start

Request a pre-review before executing any ephemeral script and follow the haiku Agent workflow to decide whether to execute, stop, or prompt the user.

Dependency Matrix

Required Modules

None required

Components

Standard package

💻 Claude Code Installation

Recommended: Let Claude install automatically. Simply copy and paste the text below to Claude Code.

Please help me install this Skill:
Name: execute-script-safely
Download link: https://github.com/ebal5/agent-skills/archive/main.zip#execute-script-safely

Please download this .zip file, extract it, and install it in the .claude/skills/ directory.
View Source Repository

Agent Skills Search Helper

Install a tiny helper to your Agent, search and equip skill from 471,000+ vetted skills library on demand.