Windows Health Monitor

Security checks across static analysis, malware telemetry, and agentic risk

Overview

This troubleshooting skill mostly matches its purpose, but it includes under-scoped recovery and export steps that could interrupt unrelated apps or expose operational details.

Review before installing. Use the diagnostic export only for trusted support channels after inspecting the archive yourself, and do not run any broad Node process kill command unless you have identified the specific OpenClaw process and accepted that unrelated Node services may stop.

SkillSpector (2)

By NVIDIA

Missing User Warnings

Medium

Confidence: 93% confidence
Finding: The skill recommends forcibly killing all node processes and restarting the scheduled task as a 'nuclear option' without any explicit warning about service disruption, collateral impact, or the need to verify process ownership first. In a troubleshooting skill, users may copy-paste this command directly, which can terminate unrelated Node.js workloads and cause data loss or interruption.

Missing User Warnings

Medium

Confidence: 89% confidence
Finding: The diagnostic bundle export is framed as sanitized, but the skill does not warn users that logs, metadata, health snapshots, and config shape may still contain sensitive operational information before sharing. This creates a privacy and data-handling risk because users may upload or send the bundle externally without reviewing its contents or understanding who will receive it.

Static analysis

No static analysis findings were reported for this release.

VirusTotal

63/63 vendors flagged this skill as clean.

View on VirusTotal