ClawHub
Back to skill

Security audit

Creatok Generate Image

Security checks across malware telemetry and agentic risk

Overview

This is a disclosed CreatOK image-generation helper that uses an API key and network calls to create images, with confirmation before paid generation.

Install only if you trust CreatOK with your image prompts and any reference images you choose to upload. Use a dedicated API key if possible, review cost and model details before confirming generation, and delete local .artifacts outputs if task IDs or image URLs are sensitive.

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
91% confidence
Finding
The skill declares `requires` metadata for environment and a Node binary, and the description explicitly requires network access to an external API, yet there is no clear top-level permissions declaration communicating those capabilities. This weakens reviewability and consent because a caller may not realize the skill can access secrets and make external requests, increasing the risk of unintended data exposure or unauthorized outbound actions.

VirusTotal

64/64 vendors flagged this skill as clean.

View on VirusTotal

Static analysis

No suspicious patterns detected.