UseAI-pro

UseAI-pro / openclaw-skills-security

Public

Curated, security-first OpenClaw skills (Markdown-based). Security audit skills - detect prompt injection, supply chain attacks, credential leaks. Works with Codex CLI, Claude Code, any LLM.

useclaw.pro ai-safety ai-security llm-security malware-detection moltbot
21
2
69% credibility
Found Feb 06, 2026 at 12 stars -- GitGems finds repos before they trend. Get early access to the next one.
Sign Up Free
AI Analysis
JavaScript
AI Summary

Security checkers for OpenClaw skills and setups that scan for threats like sneaky permissions and data leaks before use.

How It Works

1
🔍 Spot a new skill

You discover an exciting new ability for your AI helper that could make tasks easier and more fun.

2
🛡️ Pick up safety tools

You get these handy security checkers to inspect things before letting them into your AI world.

3
Choose your check
🏠
Workspace review

Answer simple questions about your setup to uncover any hidden risks.

📄
Skill scan

Drop the skill's details into the checker for a full safety once-over.

4
📋 See the safety verdict

A clear report appears, saying if it's good to go or needs fixes, with easy steps to follow.

5
🔧 Make it secure

Follow the friendly advice to patch any issues and safely welcome the skill.

🎉 Worry-free using

Your AI helper now uses new skills confidently, with everything protected and running smoothly.

Sign up to see the full architecture

4 more

Sign Up Free

Star Growth

See how this repo grew from 12 to 21 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 openclaw-skills-security?

This GitHub curated list delivers markdown-based security skills for the OpenClaw ecosystem, focusing on auditing skills for prompt injection, supply chain attacks, and credential leaks. Developers get two main auditors—one vets any skill before install, scanning for typosquatting, permissions risks, and exfiltration; the other checks your environment via a wizard for leaks, sandbox gaps, and unsafe configs. Written in JavaScript, it plugs into Codex CLI, Claude Code, or any LLM without setup hassle.

Why is it gaining traction?

It stands out with coverage of 12 real-world attacks observed in LLM agents, plus a browser-based verifier for quick checks and deep protocols for thorough audits. The markdown format means instant copy-paste into chats or CLIs, no installs needed, and it includes fix checklists plus incident playbooks. Devs hook on the security-first approach in a wild west of untrusted skills.

Who should use this?

OpenClaw users installing third-party skills from GitHub curated sources, especially those running Codex CLI or Claude Code in production. Security-conscious devs auditing LLM chains for injection or leaks before deployment. Teams hardening agent setups against persistence or over-privileges in shared workspaces.

Verdict

Early maturity with 13 stars and a 0.7% credibility score signals it's niche but promising—strong docs and threat matrix outweigh thin adoption. Grab it if OpenClaw security keeps you up at night; skip for general JS tools.

(178 words)

Sign up to read the full AI review Sign Up Free

Similar repos coming soon.