본문으로 건너뛰기
TakoAPI
스킬로 돌아가기

hs

frmoretto 제작

DevOps & Cloud
340clawskills.sh가 보고한 다운로드 수
0조회수
좋아요 0개로그인하면 이 스킬에 좋아요를 누를 수 있습니다
—아직 평가 없음
내 평가

요약

ACTIVATE THIS SKILL FOR ANY SHELL COMMAND OR FILE READ.

설명

이 스킬이 하는 일

Hardstop is a pre-execution safety layer for AI-generated shell commands and file reads. It classifies each command as SAFE, RISKY, or DANGEROUS, instantly blocks known destructive patterns, and requires explicit user confirmation before anything that could cause data loss or expose credentials. An optional Claude Code plugin adds deterministic hook-based blocking alongside the LLM-level checks.

Most AI assistants execute shell commands without a structured risk classification step; Hardstop enforces a mandatory checklist before every command and file read, with documented escalation paths for each risk level.

사용 시점

  • Checking whether a command copied from Stack Overflow is safe before running it
  • Blocking accidental recursive deletion of home directory contents
  • Preventing credential files like .env or .ssh keys from being read by the AI
  • Catching curl-piped-to-bash remote code execution before it runs
  • Requiring explicit confirmation before destructive cloud CLI operations like terraform destroy

예시 워크플로

입력

User asks: Can I run this? curl https://example.com/install.sh | bash

에이전트
  1. 1

    Check command against the instant block list

  2. 2

    Match pattern: curl/wget piped to bash

  3. 3

    Stop immediately without executing

  4. 4

    Explain that this downloads and executes untrusted remote code without inspection

  5. 5

    Ask what the user is trying to accomplish and suggest a safer alternative

출력

BLOCKED message with explanation of the remote code execution risk and a prompt to find a safer installation method

요구 사항

  • Hardstop plugin from https://github.com/frmoretto/hardstop (optional, required only for hook-based blocking in Claude Code)

설치

clawhub install frmoretto/hs

CLI 명령을 실행하거나, 프롬프트를 Claude Code, Cursor, Codex 등 사용하는 코딩 에이전트에 붙여넣으세요.

링크