본문으로 건너뛰기
TakoAPI
스킬로 돌아가기

benlee-skillguard

benlee2144 제작

Coding Agents & IDEs
—아직 평가 없음
내 평가

요약

Security scanner that audits OpenClaw skills for malicious code, prompt injection, supply chain attacks, data.

설명

이 스킬이 하는 일

Security scanner that audits OpenClaw skills for malicious code, prompt injection, supply chain attacks, hardcoded secrets, and data exfiltration. Uses a point-based scoring system with three risk levels and maintains SHA-256 file baselines to detect tampering between scans. Runs entirely on Python 3 stdlib with no external dependencies.

Generic code scanners don't understand the OpenClaw skill format or prompt injection patterns, while SkillGuard includes an 80+ domain allowlist and context-aware scoring that cuts false positives for skills making legitimate API calls.

사용 시점

  • Auditing all installed skills before running them on a new machine
  • Checking a newly downloaded skill from ClawHub before trusting it
  • Running scheduled cron alerts when a skill's files change unexpectedly
  • Detecting hardcoded AWS or GitHub tokens inside third-party skills
  • Identifying typosquatted package names in skill dependencies

예시 워크플로

입력

User asks: scan all my installed skills and write a report

에이전트
  1. 1

    Run skillguard.py scan against ~/clawd/skills/

  2. 2

    Compute SHA-256 baselines for each skill's files on first run

  3. 3

    Score each skill based on detected patterns, domain analysis, and sensitive file access

  4. 4

    Flag any skills that exceed thresholds or trigger automatic MALICIOUS conditions

  5. 5

    Write a markdown report with risk levels and per-finding recommendations

출력

Markdown report listing each skill as CLEAN, SUSPICIOUS, or MALICIOUS with one-line recommendations for every finding

설치

clawhub install benlee2144/benlee-skillguard

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

링크