跳到正文
TakoAPI
返回技能列表

dcg-guard

由 starensen 提供

Coding Agents & IDEs
459下载量由 clawskills.sh 提供
0浏览量
0 个赞登录后即可为这个技能点赞
—暂无评分
你的评分

简介

Hard-blocks dangerous shell commands (rm -rf, git push --force, etc.) before execution via OpenClaw's.

描述

该技能的功能

DCG Guard intercepts every shell command before execution and blocks dangerous ones like `rm -rf`, `git push --force`, and Windows equivalents such as `Remove-Item -Recurse -Force`. Safe commands pass through silently with no added latency. Built-in rules work without the DCG binary; the binary is optional and adds extra Unix-specific checks.

Blocks commands before they reach the shell, so dangerous operations never execute, unlike post-execution logging or manual review workflows.

何时使用

  • Blocking accidental recursive deletions during agent file cleanup tasks
  • Preventing force pushes to shared git repositories
  • Stopping irreversible Windows registry deletes in automated workflows
  • Catching destructive git branch deletions before they run
  • Guarding against disk format commands in agent sessions

示例工作流

输入

User asks: Clean up the project by removing all build artifacts

智能体
  1. 1

    Agent calls exec tool with rm -rf ./dist

  2. 2

    DCG Guard intercepts the call via before_tool_call hook

  3. 3

    Command is checked against built-in dangerous command rules

  4. 4

    Command matches the rm -rf pattern and is flagged as dangerous

  5. 5

    Plugin returns { block: true } to OpenClaw, command never executes

输出

Command blocked; agent is notified and must request explicit user permission before retrying

安装

clawhub install starensen/dcg-guard

运行 CLI 命令,或把这段提示词粘贴到 Claude Code、Cursor、Codex 或你在用的任意编程智能体里。

链接