ClawHub
Back to skill

Security audit

Shopify MCP

Security checks across malware telemetry and agentic risk

Overview

This appears to be a legitimate Shopify admin helper, but it grants powerful store-changing access with limited safety guidance.

Install only if you are comfortable giving a local MCP server Shopify Admin access. Review and pin the external repository before use, create a dedicated Shopify app with only the scopes you need, start with read-only scopes where possible, explicitly confirm the store and action before any mutation, keep .env out of source control, and rotate or revoke the token if exposed or no longer needed.

SkillSpector

By NVIDIA
Vulnerability Patterns
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
  • Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
  • Excessive AgencyUnrestricted Tool Access, Autonomous Decision Making, Scope Creep
Findings (2)

Missing User Warnings

Medium
Confidence
89% confidence
Finding
The skill exposes natural-language access to destructive operations such as canceling orders, fulfilling orders, and modifying inventory, but provides no warning, confirmation guidance, or caution about irreversible business effects. In an agent-driven context, this increases the chance of accidental or socially engineered misuse because users may invoke high-impact actions as casually as read-only queries.

Missing User Warnings

Medium
Confidence
93% confidence
Finding
The setup instructions tell users to place a live Shopify access token in a local .env file and show token formats directly, but do not include any warning about secrecy, rotation, storage hygiene, or avoiding commits/logging. Because these tokens grant administrative API access, poor handling can lead to unauthorized store access and tampering.

VirusTotal

65/65 vendors flagged this skill as clean.

View on VirusTotal

Static analysis

Detected: suspicious.exposed_secret_literal

File appears to expose a hardcoded API secret or token.

Critical
Code
suspicious.exposed_secret_literal
Location
SKILL.md:43