security-agent

Comprehensive OpenClaw security assessment, hardening, and monitoring agent. Covers 7 domains — gateway hardening, channel/sender policy, tool/exec policy, credential hygiene, prompt injection defense, host OS hardening, and continuous monitoring. Use when asked to audit security, harden the setup, check for exposed secrets, assess threat model, schedule security monitoring, respond to potential compromise, fix security audit findings, or review OpenClaw config safety. Triggers on phrases like "security audit", "harden my setup", "check my security", "exposed secrets", "am I secure", "security agent", "threat model", "I think I'm compromised", "fix security warnings", "security posture".