ClawHub
Back to skill

Security audit

Freebie

Security checks across malware telemetry and agentic risk

Overview

This is an instruction-only shopping/free-sample lookup skill with no code, installer, credentials, or hidden privileged behavior.

Safe to install based on the provided artifacts. When using it for nearby stores or navigation, share only the location details you are comfortable using for that lookup.

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 (1)

Vague Triggers

Medium
Confidence
87% confidence
Finding
The example invocations are overly broad and overlap with ordinary user phrasing, which can cause the skill to trigger unintentionally during unrelated conversations. In a location- and coupon-oriented skill, accidental activation could lead to unnecessary retrieval of nearby store, queue, or navigation-related information and degrade routing reliability or user trust.

VirusTotal

65/65 vendors flagged this skill as clean.

View on VirusTotal

Static analysis

No suspicious patterns detected.