ClawHub
Back to skill

Security audit

Shopify 电商图片生成与编辑

Security checks for vulnerabilities and agentic risk

Overview

This skill is a disclosed AI Hive image-generation helper for Shopify assets, but users should understand it uploads selected media and stores an API key locally.

Install only if you are comfortable using AI Hive, storing an AI Hive API key locally, and uploading the product/reference images you choose to provide. Avoid passing private files as --image or --file unless you intend to send them to the service.

SkillSpector

Vulnerability Patterns
  • 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
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
Findings (2)

Lp3

Medium
Category
MCP Least Privilege
Confidence
93% confidence
Finding
The skill advertises operational capabilities such as environment access, file read/write, network, and shell execution without declaring permissions. This creates a transparency and trust problem: users may invoke a seemingly simple image-generation skill while it can access local data, install packages, and make outbound requests, increasing the risk of unintended data exposure or command execution in the agent environment.

Tp4

High
Category
MCP Tool Poisoning
Confidence
96% confidence
Finding
The documented purpose is narrowly scoped to Shopify image generation/editing, but the underlying behavior appears to support much broader actions including chat, video generation, media upload, account/wallet access, model enumeration, audio handling, and browser-based API-key setup. This mismatch is dangerous because it obscures the real attack surface and can mislead users into granting trust to a skill that can interact with external services, sensitive account data, and richer content types than expected.

Static analysis

No suspicious patterns detected.