Перейти к содержимому
TakoAPI
Назад к навыкам

dcg-guard

от starensen

Coding Agents & IDEs
459Число загрузок по данным clawskills.sh
0Просмотры
0 лайковВойдите, чтобы поставить лайк навыку
—Ещё нет оценок
Ваша оценка

Кратко

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

Описание

Что делает этот навык

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.

Когда его использовать

  • 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

Пример сценария

ВВОД

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

АГЕНТ
  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

ВЫВОД

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

Установка

clawhub install starensen/dcg-guard

Выполните команду CLI или вставьте промпт в Claude Code, Cursor, Codex — любой кодинг-агент, которым пользуетесь.

Ссылки