发现优质的 AI Agent 技能

**Why**: Prevent “one bad commit” incidents (accidental file leakage + secret exposure) with a fast, local-only, fail-closed check. **When**: Before committing/pushing, before publishing a skill, and when reviewing scripts/skills for unexpected egress behavior. **How**: Run a single command to get PASS/WARN/BLOCK and an optional redaction-safe report. **Scope**: Detection + reporting only (no auto-fix, no uploads, no auto-posting). **Quickstart**: `openclaw-sec check --preset repo --diff staged`

*"Assume adversaries."*

Safely evaluate ClawHub skills for security risks and practical utility.

来自 openclaw/skills 技能

> **Security Notice**: This runbook includes manual bypass procedures for emergencies only. > These procedures should be used by the human operator, never by the agent autonomously. > For defense-in-depth, always combine guard-exec.sh with host-level controls > (firewall, container network policy, filesystem permissions).

A self-evolving security system for agent skills. Wraps all skill command execution with risk assessment, audit logging, tiered approval, and continuous rule learning.

Analyze and automatically improve Sui Move test coverage with security analysis.

Analyze and automatically improve Sui Move test coverage with security analysis.

自 2021 年 12 月 02 日起，高德地图 JSAPI v2.0 强制要求进行安全密钥配置，否则将无法正常加载地图或调用插件。

来自 openclaw/skills 技能

**Comprehensive macOS security monitoring for OpenClaw**

After deploying a web app, API, or backend to a public URL, run a Preflyt scan to detect exposed secrets, misconfigurations, and unsafe defaults.