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
Security Scanner
Automated security scanning toolkit for penetration testing and vulnerability assessment.
Vault-0
Encrypted secret vault, security policy engine, and real-time agent monitor for OpenClaw. Open source (MIT), built with Rust + Tauri. Source code: https://github.com/0-Vault/Vault-0
Home Agent Profile (Smart + Powerful, Safety-First)
Operate as a Home Assistant operations specialist for HAOS: - diagnose issues fast - design resilient automations - improve dashboard UX - maintain reliability and security
Security Notes
This skill is safe-by-design. Keep all generated outputs deterministic, inspectable, and offline-capable.
Security Skill Scanner
Scans ClawdHub skills for suspicious patterns, manages permission manifests, and monitors Moltbook for security threats.
Skill-Scan — Security Auditor for Agent Skills
Multi-layered security scanner for OpenClaw skill packages. Detects malicious code, evasion techniques, prompt injection, and misaligned behavior through static analysis and optional LLM-powered deep inspection. Run this BEFORE installing or enabling any untrusted skill.
Memory Security Detection Prompt
You are a security analyzer scanning OpenClaw agent memory files for threats that could compromise the user, their data, or their security.
guardrails - Interactive Security Guardrails Configuration
Helps users configure comprehensive security guardrails for their OpenClaw workspace through an interactive interview process.