ClawHub

Game Architect

Security checks across malware telemetry and agentic risk

Overview

This is a documentation-only game architecture planning skill with no executable code, hidden behavior, or sensitive access found.

This skill is reasonable to install as a game architecture reference and planning aid. Be aware that it may be invoked broadly for game-system design tasks and that its standalone workflow can produce or update architect/*.md planning files, so review those outputs before using them as implementation direction.

SkillSpector

By NVIDIA
Vulnerability Patterns
  • Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
  • 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 (2)

Vague Triggers

Medium
Confidence
90% confidence
Finding
The description says to read this skill when designing or planning 'any game system architecture' across many domains, which is very broad activation language. In agent ecosystems that auto-select skills from natural-language descriptions, this can cause the skill to be pulled into many ordinary requests, increasing prompt-surface area and the chance that its guidance overrides more appropriate workflow or security-constrained skills.

Vague Triggers

Medium
Confidence
85% confidence
Finding
The 'Knowledge Mode (Query)' trigger says the skill applies when the user requests to query game-architecture knowledge, but it does not define concrete boundaries for what counts as such a request. That vagueness can lead to over-activation on loosely related prompts, making the agent consult this skill unnecessarily and potentially biasing responses toward its framework even when a narrower source would be safer or more relevant.

VirusTotal

64/64 vendors flagged this skill as clean.

View on VirusTotal