MH healthcheck
Security checks across malware telemetry and agentic risk
Overview
This is a transparent host security audit and hardening skill that requires user approval before making changes.
Install this if you want an agent to help audit and harden the host running OpenClaw. Review each proposed command before approving changes, especially firewall, SSH, services, packages, update policy, cron scheduling, or memory writes.
SkillSpector
By NVIDIA
Vulnerability Patterns
- Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
- Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
- Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
- Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
- Excessive AgencyUnrestricted Tool Access, Autonomous Decision Making, Scope Creep
VirusTotal
65/65 vendors flagged this skill as clean.