ClawHub
Back to skill

Security audit

Windows Remote

Security checks across malware telemetry and agentic risk

Overview

This skill does what it says, but it gives an agent broad remote Windows command and file-transfer power while weakening SSH host identity checks.

Install only if you intentionally want Codex/OpenClaw to administer a specific Windows host over SSH. Use a dedicated least-privilege SSH key and account, avoid Administrator unless required, confirm destructive commands and file transfers yourself, and consider editing the scripts to remove StrictHostKeyChecking=no and rely on known_hosts verification before use.

SkillSpector

By NVIDIA
Vulnerability Patterns
  • Excessive AgencyUnrestricted Tool Access, Autonomous Decision Making, Scope Creep
  • Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
Findings (2)

Context-Inappropriate Capability

Medium
Confidence
98% confidence
Finding
The script explicitly disables SSH host key verification with StrictHostKeyChecking=no, which removes protection against man-in-the-middle and host impersonation attacks. In a remote command execution skill, this is especially dangerous because an attacker who can intercept or redirect the connection could capture commands, credentials, or execute commands on an unintended host.

Vague Triggers

Medium
Confidence
87% confidence
Finding
The skill advertises broad trigger phrases such as "run on Windows", "execute on remote", and "check GPU", which can cause the agent to invoke a capability that performs arbitrary remote command execution in situations where the user may not have intended it. In a skill that can run commands on remote hosts, accidental activation materially increases the chance of unintended remote actions against sensitive systems.

VirusTotal

52/52 vendors flagged this skill as clean.

View on VirusTotal

Static analysis

No suspicious patterns detected.