ClawHub
Back to skill

Security audit

game-asset-generator

Security checks for vulnerabilities and agentic risk

Overview

This skill is a documentation-only guide for generating toy/game assets through disclosed external APIs, with privacy and API-key handling cautions for users.

Install only if you are comfortable sending prompts, image URLs, session metadata, and generated assets to the OneKey Gateway and downstream 3D model providers. Do not submit confidential or regulated content unless that data sharing is approved, and protect the DEEPNLP_ONEKEY_ROUTER_ACCESS key as a secret.

SkillSpector

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
93% confidence
Finding
The skill explicitly describes sending user prompts, image URLs, and generation task data to an external gateway and third-party model providers, but it does not clearly warn users that their inputs may leave the local environment and be processed by outside services. This creates a real privacy and data-handling risk, especially if users submit proprietary designs, personal images, or sensitive project metadata under the assumption the skill is self-contained.

Missing User Warnings

Medium
Confidence
89% confidence
Finding
The documentation tells users to export and use an access key directly in shell commands and HTTP headers, but it does not warn about credential exposure through shell history, terminal logging, process inspection, CI logs, or shared environments. That omission can lead to accidental leakage of the gateway credential, enabling unauthorized API usage, quota abuse, or access tied to the user's account.

Static analysis

No suspicious patterns detected.