ClawHub

Pre-installation Security Check

Security checks across malware telemetry and agentic risk

Overview

This appears to be a security-review skill with no artifact-backed evidence of hidden access, persistence, data theft, or destructive behavior.

Reasonable to install if you want a skill-safety review step. Before relying on it, check that it only runs when you intend to review a ClawHub/OpenClaw skill and does not replace the platform's normal install confirmation flow.

SkillSpector

By NVIDIA
Vulnerability Patterns
  • 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
  • Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
Findings (2)

Vague Triggers

Medium
Confidence
90% confidence
Finding
The trigger phrases "is this skill safe" and "check skill security" are broad enough to activate outside the narrow pre-install/install-review context, potentially causing this skill to intercept general security questions. Because this skill is positioned as mandatory and pre-installation focused, overbroad matching can create shadowing and unintended execution paths that affect user intent and downstream actions.

Shadow Command Trigger

Medium
Category
Trigger Abuse
Confidence
84% confidence
Finding
The skill advertises triggers including "install skill," which can conflict with a built-in install command flow and create command shadowing. In a security-gating skill, such interception is especially sensitive because it can alter normal install behavior, capture unrelated install requests, or create confusing approval loops.

VirusTotal

63/63 vendors flagged this skill as clean.

View on VirusTotal