ClawHub
Back to skill

Security audit

Security Scanner Pro

Security checks across malware telemetry and agentic risk

Overview

The skill is very under-documented, but the reviewed artifacts contain only markdown marketing/instructions and no executable malware, hidden persistence, credential access, or destructive behavior.

Before installing or paying, verify the publisher and exact package name, and do not rely on the 24/7 monitoring/API claims until the skill documents what it scans, what data it sends externally, how to stop it, and what results it produces.

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
85% confidence
Finding
The skill metadata and description are broad and do not define clear activation boundaries, permitted tasks, or trigger constraints. For a security-related skill, this increases the chance of over-broad invocation, misuse in unintended contexts, or users assuming stronger scanning coverage and authority than the skill actually provides.

Natural-Language Policy Violations

Low
Confidence
78% confidence
Finding
The skill content is presented only in Chinese without indicating language negotiation or user preference handling. This can cause misunderstanding of security warnings, pricing, limitations, or operational behavior for non-Chinese-speaking users, which is especially problematic in a security tool where precision and informed consent matter.

VirusTotal

64/64 vendors flagged this skill as clean.

View on VirusTotal

Static analysis

No suspicious patterns detected.