360 Secure SkillHub
360 安全技能中心

Oc Guard Skill

核心功能：管控OpenClaw配置变更，禁止直接修改配置文件，提供plan（规划）、apply（应用）合规流程，高风险变更需确认，输出真实执行回执或未执行说明。典型场景：所有OpenClaw配置变更需求。输入可为变更描述文本或提案文件，通过指定CLI命令执行，输出双语执行回执，未执行时返回【模型说明-未执行】。

edmond-ai
edmond-ai
热度 64.59
最近更新 2026-05-11 17:28:54
分类：自动化依赖：代码执行应用场景：工作流 / 自动化脚本 / DevOps

安装技能

复制下面的话术发给你的 Agent，它会通过 secure-skills 检索并安装该技能。

执行命令安装此 skill： npx secure-skills-cli add oc-guard-skill
Metadata
name
oc_guard
description
Safe OpenClaw config planning/apply workflow with bilingual execution receipts.
metadata
{"openclaw":{"requires":{"bins":["python3","openclaw","opencode"]}}}

oc-guard Skill

Purpose

All config-changing requests must go through oc-guard. Do not directly edit ~/.openclaw/openclaw.json. When possible, invoke the bundled CLI at {baseDir}/scripts/oc-guard.py.

Hard Rules

  1. Use oc-guard plan before apply.
  2. High-risk changes require oc-guard apply --confirm.
  3. Always return execution receipt first.
  4. If command is not executed, return 【模型说明-未执行】.
  5. Never claim success without a real oc-guard receipt.

Common Commands

  • {baseDir}/scripts/oc-guard.py --help
  • {baseDir}/scripts/oc-guard.py plan "<requirement>"
  • {baseDir}/scripts/oc-guard.py apply --confirm "<requirement>"
  • {baseDir}/scripts/oc-guard.py plan --proposal <file>
  • {baseDir}/scripts/oc-guard.py apply --confirm --proposal <file>