发现优质的 AI Agent 技能

Scan any skill directory for permissions and dangerous patterns. Get a safety rating before you install.

The definitive security scanner for OpenClaw/ClawHub skills. Best-in-class detection across 18 security checks including **prompt injection detection** — the first scanner to catch agent manipulation attacks in skill documentation. 5-dimension trust scoring, trend tracking, diff analysis, and benchmarking. Zero false positives on legitimate skills.

来自 openclaw/skills 技能

Security-first vetting protocol for AI agent skills. **Never install a skill without vetting it first.**

env: required: [RAGFLOW_BASE_URL] optional: [RAGFLOW_API_KEY, OPENCLAW_PRIMARY_CHAT_ID] metadata: env:

ReefWatch is a lightweight host-based intrusion detection system (HIDS) that runs as a background daemon on the same machine as OpenClaw. It continuously monitors the local system for security threats and alerts the user through OpenClaw's messaging channels ONLY when something suspicious is detected.

This playbook defines the standard operating procedures when Scam Guards detects a potential threat.

- Gateway and node health checks - Pairing/connectivity incident response - Execution-path stabilization - Security and configuration optimization

来自 openclaw/skills 技能

审计 skills 目录中的安全风险，生成报告。

👽语 supports three security levels. This document details the implementation of encrypted communication.

Terminal is **disabled by default** for security. Must be enabled in extension settings, and only whitelisted commands are allowed.