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
Skill Install Guardian v3.0 - Professional Security Audit
来自 openclaw/skills 技能
Security Evaluation Heuristics
**Purpose:** Mental checklist before installing ANY external skill, code, or integration.
Anti-Bot Evasion Guide
Bypass every major bot detection system: Cloudflare, DataDome, PerimeterX (Human Security), Akamai Bot Manager, and Kasada. Each system has different detection methods — this skill covers how to evade each one.
Pinchtab Security & Trust
**TL;DR**: Pinchtab is a local, sandboxed browser control tool. It does not phone home, steal credentials, or exfiltrate data. Source code is public; binaries are signed and published via GitHub.
Pipelock Security Harness
Pipelock is a fetch proxy that sits between you and the internet. Every outbound HTTP request passes through a 7-layer scanner pipeline that catches API key leaks, SSRF attempts, prompt injection, and data exfiltration.
SafeExec - AI Agent Security Layer
> 🛡️ The last line of defense for AI Agents - Intercept dangerous commands and protect your system
ClawShell
Human-in-the-loop security layer for OpenClaw. ClawShell intercepts shell commands before execution, analyzes their risk level, and requires your explicit approval (via push notification) for dangerous operations.
Signal Integration
Complete Signal messenger integration with security-first contact management.
Design: Agent Teleport
**Role:** Migration Utility **Mechanism:** Tarball -> BLOB -> SQL -> New Host. **Security:** DSN acts as the "Private Key". Anyone with DSN can restore.