ClawHub

Ecommerce Assistant

Security checks across malware telemetry and agentic risk

Overview

This skill is not malware, but it markets live ecommerce research while key Amazon and price-monitoring results are simulated without clear disclosure.

Install only if you are comfortable treating this as a demo or prototype. Do not rely on its Amazon search results, price alerts, or reports for purchasing, pricing, dropshipping, or competitor decisions unless you first verify that real API-backed data collection has been implemented. Review ~/.ecommerce-assistant for retained watchlist/history data, and run store analysis only against public stores you are allowed to query.

SkillSpector

By NVIDIA
Vulnerability Patterns
  • Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
  • MCP Least PrivilegeUnderdeclared Capability, Wildcard Permission, Missing Permission Declaration
  • MCP Tool PoisoningHidden Instructions, Unicode Deception, Parameter Description Injection
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
Findings (3)

Lp3

Medium
Category
MCP Least Privilege
Confidence
90% confidence
Finding
The skill advertises executable scripts that perform network access and likely read/write local files, but the skill metadata does not declare any permissions or operational boundaries. This creates a transparency and governance gap: an agent or reviewer may authorize or invoke the skill without understanding that it can access external sites and persist data locally.

Intent-Code Divergence

Medium
Confidence
97% confidence
Finding
The function claims to check current prices for tracked items, but it generates random mock prices instead of retrieving real marketplace data. In an e-commerce assistant, this can mislead users into making pricing, purchasing, or monitoring decisions based on fabricated information, causing false alerts and incorrect reports.

Vague Triggers

Medium
Confidence
81% confidence
Finding
The 'use when' scope is very broad and covers common e-commerce research tasks, which increases the chance the skill will be auto-selected for loosely related prompts. Because the skill also exposes networked scripts and report generation, overbroad routing could lead to unnecessary external requests, data collection, or file creation in contexts where the user did not intend those actions.

VirusTotal

64/64 vendors flagged this skill as clean.

View on VirusTotal