Zum Inhalt springen
TakoAPI
Zurück zu den Skills

security-operator

von kevjade

Coding Agents & IDEs
556Downloadzahlen laut clawskills.sh
0Aufrufe
0 LikesMelde dich an, um diesen Skill zu liken
—Noch nicht bewertet
Deine Bewertung

Kurzbeschreibung

Runtime security guardrails for OpenClaw agents.

Beschreibung

Was dieser Skill macht

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.

Wann du ihn einsetzt

  • 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

Beispiel-Workflow

EINGABE

User asks: Run the security setup wizard for my OpenClaw workspace

AGENT
  1. 1

    Run openclaw security audit --deep to assess current security posture

  2. 2

    Apply safe defaults with openclaw security audit --fix

  3. 3

    Verify spending limits are configured in the gateway or provider dashboard

  4. 4

    Check that logging is enabled and logs are being written to the expected path

  5. 5

    Ask user for approval, then append always-on guardrails to AGENTS.md

AUSGABE

Security guardrails written to AGENTS.md, safe defaults applied, and optional weekly audit cron offered

Installation

clawhub install kevjade/security-operator

Führe den CLI-Befehl aus oder füge den Prompt in Claude Code, Cursor, Codex oder deinen Coding-Agenten ein.

Links