본문으로 건너뛰기
TakoAPI
스킬로 돌아가기

arc-skill-sandbox

trypto1019 제작

Health & Fitness
600clawskills.sh가 보고한 다운로드 수
0조회수
좋아요 0개로그인하면 이 스킬에 좋아요를 누를 수 있습니다
—아직 평가 없음
내 평가

요약

Test untrusted skills in an isolated environment before installing.

설명

이 스킬이 하는 일

Runs untrusted skills in a monitored environment before installation. Tracks filesystem access, environment variable reads, network connections, and subprocess calls during execution. Produces a JSON report with a safety verdict (SAFE / SUSPICIOUS / DANGEROUS).

Static analysis misses runtime behavior, so executing the skill in a monitored environment reveals what it actually does with your data and credentials.

사용 시점

  • Testing a ClawHub skill before installing it on your real agent
  • Checking if a downloaded script reads API keys or tokens
  • Catching outbound network calls made by an unknown skill
  • Running a skill with fake credentials to detect exfiltration attempts
  • Generating a safety report before a team-wide skill rollout

예시 워크플로

입력

User asks: sandbox this skill at ~/.openclaw/skills/some-skill/ and tell me if it's safe to install

에이전트
  1. 1

    Runs sandbox.py against the skill directory with --monitor-network and --fake-env flags

  2. 2

    Captures all filesystem operations, environment variable accesses, and outbound network requests

  3. 3

    Injects fake API keys and tokens to observe whether the skill attempts to exfiltrate them

  4. 4

    Generates a JSON report listing all observed activity and flags suspicious patterns

  5. 5

    Returns the safety verdict with a summary of findings

출력

JSON safety report covering filesystem, network, subprocess, and env var activity with a final SAFE / SUSPICIOUS / DANGEROUS verdict

설치

clawhub install trypto1019/arc-skill-sandbox

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

링크