Skills
.Work. You
Rest

clawhub-safe

Community

Securely explore and review OpenClaw skills, reducing injection risk.

Software Engineering#code review#skill discovery#prompt-injection risk#skill library management#secure installation
Authorcurrentsuspect
Version1.0.0
Installs0

System Documentation

What problem does it solve?

ClawHub Safe mitigates the risks of prompt-injection when using OpenClaw skills by enabling users to discover and vet skills thoroughly before installation.

Core Features & Use Cases

  • Safe Discovery: Provides a platform to search and vet OpenClaw skills safely, minimizing prompt-injection risks.
  • Skill Review: Allows for manual inspection of skill content before activation.
  • Risk Mitigation: Empowers users to review network requests, secret handling, and code to assess potential risks.
  • Approval-Based Installation: Allows for the installation of skills only after explicit approval by the user.

Quick Start

Search for a skill, review its details, flag risks, ask for approval, and install it with: 'clawhub install <slug> --force'.

Dependency Matrix

Required Modules

None required

Components

scriptsreferences

💻 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: clawhub-safe
Download link: https://github.com/currentsuspect/currentsuspect/archive/main.zip#clawhub-safe

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 620,000+ vetted skills library on demand.