发现优质的 AI Agent 技能

来自 openclaw/skills 技能

**Date:** 2026-02-11 **Patch Version:** 1.0.1 → 1.0.2 (security hardening + portability fix)

**CRITICAL: Read this entire document before executing any transactions.**

Patterns for including scripts in ClawHub skills that pass the security scanner.

After publishing a skill to ClawHub, an automated security scanner evaluates it across 5 categories. Each category receives a rating:

Step-by-step process for publishing a skill to ClawHub and iterating until the security scanner gives all ✓ ratings.

Publish OpenClaw skills to ClawHub with clean security scanner ratings. This guide supplements the built-in `skill-creator` skill with ClawHub-specific publishing knowledge — especially frontmatter schema and scanner compliance.

> **Identity & Trust Protocol: v1.0** > **Registry ID:** sovereign-identity > **Compliance:** W3C DID Core, JWT (RFC 7519), SD-JWT

<!-- SECURITY NOTE: This file contains patterns for DETECTING security issues in codebases. These are NOT exploitation patterns — they help developers FIND and FIX bugs. This is the same approach used by: - GitHub's secret scanning

> **Scan before you install. Every time.**

Audit ClawHub skills for security threats before installing them.

Audit ClawHub skills for security threats before installing them.