# Crawsecure

> Offline security analysis skill that helps detect unsafe patterns in ClawHub skills before installation.

- Skill: `kbarbel640-del/crawsecure-2` (Agent Skill, multi-file: 3 files)
- Install (CLI): `npx skillmds@latest add kbarbel640-del/crawsecure-2`
- Raw SKILL.md: https://api.skillmd.com/api/skills/kbarbel640-del/crawsecure-2/raw
- Safety review: pending (external: skill-scanner PASS, skillspector PASS)
- Works with: Claude Code, Claude.ai, OpenAI Codex
- Category: Security
- Author: kbarbel640-del (https://skillmd.com/u/kbarbel640-del)
- Updated: 2026-09-21
- Page: https://skillmd.com/skills/kbarbel640-del/crawsecure-2

---

Offline security analysis skill that helps detect unsafe patterns in ClawHub skills before installation.

# CrawSecure

CrawSecure is an offline security analysis skill that helps users detect potentially unsafe patterns in ClawHub / OpenClaw skills **before installing or trusting them**.

It was created to promote safer usage, transparency, and awareness when working with third-party skills.

---

## 🔍 What CrawSecure does

- Analyzes skill-related content
- Identifies potentially dangerous patterns
- Highlights security concerns clearly
- Encourages safer usage of third-party skills

---

## 🚨 Risk Signals Analyzed

- Dangerous command patterns (e.g. destructive or execution-related behavior)
- References to sensitive files or credentials
- Indicators of unsafe practices

---

## 🔒 Security Philosophy

- Read-only analysis
- No network access
- No code execution
- No file modifications

CrawSecure exists to **increase trust** inside the ClawHub ecosystem.

---

## 📦 Version

**v1.0.2** – Fixed skill summary extraction by adjusting SKILL.md structure.

---

## ✅ When to use CrawSecure

- Before installing a third-party skill
- When reviewing unfamiliar or community-made skills
- As a second opinion for security awareness
- To promote safer development practices