ClawHub
Back to skill

Security audit

DesignKit Ecommerce AI Studio

Security checks across malware telemetry and agentic risk

Overview

This is a disclosed DesignKit image-processing skill that uses an API key, uploads user-provided images for remote processing, and saves generated outputs locally.

Install only if you are comfortable setting a DesignKit/OpenClaw API key and sending selected product images to DesignKit/OpenClaw for processing. Keep request logging off unless debugging, avoid sensitive images, and review any custom output directory or API-base override before use.

SkillSpector

By NVIDIA
Vulnerability Patterns
  • MCP Least PrivilegeUnderdeclared Capability, Wildcard Permission, Missing Permission Declaration
  • 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)

Lp3

Medium
Category
MCP Least Privilege
Confidence
95% confidence
Finding
The skill clearly instructs the agent to invoke shell scripts, read sub-skill files, use environment credentials, upload local files, download outputs, and call a remote API, yet it does not declare a corresponding explicit permission model beyond OpenClaw metadata. That mismatch weakens security review and user consent because the platform may not surface the full set of sensitive capabilities being used, especially shell, filesystem, network, and secret access.

VirusTotal

53/53 vendors flagged this skill as clean.

View on VirusTotal

Static analysis

No suspicious patterns detected.