OpenClaw的Sandwrap-技能（skill）的描述

使用软沙箱保护可安全运行不受信任的技能。将技能包裹在多层基于提示的防御中（约85%的攻击预防率）。在以下情况使用：（1）运行来自未知来源的第三方技能，（2）处理可能包含提示注入的不受信任内容，（3）安全分析可疑文件或URL，（4）在信任新技能之前进行测试。支持手动模式（“run X in sandwrap”）和对高风险技能的自动包裹。

OpenClaw's Sandwrap skill

Run untrusted skills safely with soft-sandbox protection. Wraps skills in multi-layer prompt-based defense (~85% attack prevention). Use when: (1) Running third-party skills from unknown sources, (2) Processing untrusted content that might contain prompt injection, (3) Analyzing suspicious files or URLs safely, (4) Testing new skills before trusting them. Supports manual mode ('run X in sandwrap') and auto-wrap for risky skills.

Sandwrap - skill原始代码包

该作者的其他技能