security-operator
kevjade 제작
Coding Agents & IDEs요약
Runtime security guardrails for OpenClaw agents.
설명
이 스킬이 하는 일
Runtime security guardrails for OpenClaw agents covering prompt injection, credential leaks, cost runaway, and cascade failures. Two operating modes separate browsing from autonomous execution, each with distinct trust boundaries. Includes a one-time setup wizard, credential audit commands, and community skill vetting workflows.
Guardrails are behavioral rather than tool-based, adding zero token overhead during normal operation while still blocking high-risk actions.
사용 시점
- Block prompt injection attempts embedded in untrusted web content during research tasks
- Audit OpenClaw config files for plaintext API keys or misconfigured .env permissions
- Vet a community skill from ClawHub before installing it in a production workspace
- Enforce explicit approval gates before destructive actions like force pushes or credential exports
- Schedule a weekly automated security health check via cron
예시 워크플로
User asks: Run the security setup wizard for my OpenClaw workspace
- 1
Run
openclaw security audit --deepto assess current security posture - 2
Apply safe defaults with
openclaw security audit --fix - 3
Verify spending limits are configured in the gateway or provider dashboard
- 4
Check that logging is enabled and logs are being written to the expected path
- 5
Ask user for approval, then append always-on guardrails to AGENTS.md
Security guardrails written to AGENTS.md, safe defaults applied, and optional weekly audit cron offered
설치
clawhub install kevjade/security-operatorCLI 명령을 실행하거나, 프롬프트를 Claude Code, Cursor, Codex 등 사용하는 코딩 에이전트에 붙여넣으세요.