본문으로 건너뛰기
TakoAPI
스킬로 돌아가기

lobsterguard

jarb02 제작

Coding Agents & IDEs
297clawskills.sh가 보고한 다운로드 수
0조회수
좋아요 0개로그인하면 이 스킬에 좋아요를 누를 수 있습니다
—아직 평가 없음
내 평가

요약

Bilingual security auditor for OpenClaw. 68 checks across 6 categories, 11 auto-fixes, OWASP Agentic AI Top 10.

설명

이 스킬이 하는 일

LobsterGuard audits OpenClaw installations for security issues, running 68 checks across system security, network, OWASP Agentic AI Top 10, forensic detection, and skill ecosystem categories. It includes 11 auto-fixes that require explicit user confirmation before execution. A real-time gateway plugin intercepts prompt injection, path traversal, and command injection threats before they reach the agent.

Unlike generic Linux hardening tools, it targets AI agent-specific threats including OWASP Agentic AI Top 10, tool poisoning, and rogue skill detection.

사용 시점

  • Scanning an OpenClaw setup for firewall and kernel misconfigurations
  • Auto-fixing UFW rules after a failed firewall check
  • Detecting prompt injection attempts before they reach an AI agent
  • Receiving Telegram alerts when suspicious skills are quarantined
  • Auditing OpenClaw skill permissions for unauthorized access patterns

예시 워크플로

입력

User asks: Check my OpenClaw installation for security issues

에이전트
  1. 1

    Runs check.py --compact to execute all 68 checks locally

  2. 2

    Displays the raw compact report showing only failed checks and overall score

  3. 3

    Identifies which failed checks have auto-fix support

  4. 4

    Presents a fix plan and asks for user confirmation before making any changes

  5. 5

    Executes fixes step-by-step, then runs verify to confirm each fix worked

출력

Security score with list of failed checks, applied fixes, and verification results

요구 사항

  • TELEGRAM_BOT_TOKEN environment variable
  • TELEGRAM_CHAT_ID environment variable
  • Telegram bot created via @BotFather

설치

clawhub install jarb02/lobsterguard

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

링크