ClawHub
Back to skill

Security audit

Shopify Admin

Security checks across malware telemetry and agentic risk

Overview

This is a clearly disclosed Shopify Admin API helper, but it requires powerful store credentials and should be used carefully.

Install only if you want an agent to operate on your Shopify Admin API. Use least-privilege Shopify scopes, verify the store domain, keep tokens/client secrets out of chats and logs, rotate exposed credentials, avoid using placeholder OAuth redirect domains for real stores, and require explicit confirmation before product, inventory, theme, order, or customer-data changes.

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
92% confidence
Finding
The skill explicitly instructs use and storage of a Shopify Admin access token but does not warn that this credential grants privileged access to live store resources and must never be exposed in prompts, logs, screenshots, or responses. In an agent context, omission of credential-handling guidance increases the chance of accidental secret disclosure or unsafe transmission to untrusted destinations.

Missing User Warnings

Medium
Confidence
90% confidence
Finding
The skill is designed for write operations against the Shopify Admin API but does not include an upfront warning that actions can modify live production products, tags, inventory, themes, or other store data. In operational use, this omission can lead to accidental destructive or unauthorized changes, especially because the SOP encourages direct use of the HTTP tool for admin writes.

VirusTotal

56/56 vendors flagged this skill as clean.

View on VirusTotal

Static analysis

No suspicious patterns detected.