OpenClaw Operator
Security checks across malware telemetry and agentic risk
Overview
This skill is a disclosed OpenClaw troubleshooting tool that reads local OpenClaw operational files and can optionally run a recurring health check, with no evidence of hidden or malicious behavior.
Install this if you want OpenClaw operational diagnostics and are comfortable with a skill reading local OpenClaw logs, session metadata, cron configuration, and AGENTS.md size. Review the two bash scripts before running them, register the cron watchdog only if you want recurring checks, keep watchdog output in trusted channels, and make backups before following manual recovery steps that edit OpenClaw JSON state.
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
64/64 vendors flagged this skill as clean.