security-operator
por kevjade
Coding Agents & IDEsResumo
Runtime security guardrails for OpenClaw agents.
Descrição
O que esta skill faz
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.
Quando usá-la
- 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
Exemplo de fluxo de trabalho
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
Instalação
clawhub install kevjade/security-operatorExecute o comando da CLI ou cole o prompt no Claude Code, Cursor, Codex ou no agente de código que você usa.