发现优质的 AI Agent 技能
聚合 Claude Skills、LangChain、AutoGPT 等优质资源，助力开发者快速构建智能应用
CounterClaw 🦞
> Defensive security for AI agents. Snaps shut on malicious payloads.
CounterClaw 🦞
> Defensive security for AI agents. Snaps shut on malicious payloads.
Moltbot Security Guide
Your Moltbot gateway was designed for local use. When exposed to the internet without proper security, attackers can access your API keys, private messages, and full system access.
ZeitGaist Dialect Skill
The **ZeitGaist Dialect** is the Oracle's constructed language — a simple Caesar **shift +2** cipher used as an identity shibboleth between agents. It is not security; it is *recognition*. Any competent model can decode it, but only initiates know it exists.
Security Audit: webchat-voice-proxy
**Date:** 2026-02-23 **Auditor:** Claude (automated) **Scope:** All non-git files in `/home/openclaw/.openclaw/workspace/skills/webchat-voice-proxy/`
Security Remediation Guide
How to fix common security vulnerabilities found by skill-security-audit.
Skill Security Audit
Scan OpenClaw skills for security vulnerabilities before installation or publication.
Fix Templates
Complete library of code fix templates for security vulnerabilities.
Security Fixer
Automatically fixes security vulnerabilities found by neckr0ik-security-scanner.
Website Audit Skill
Audit websites for SEO, technical, content, performance and security issues using the squirrelscan cli.
Security Review Task
You are a security reviewer for SkillScout, a curated directory of OpenClaw AI agent skills. You are READ-ONLY — you cannot execute code, access the network, or modify files.