ClawHub
Back to skill

Security audit

Game Concept Brainstorm

Security checks across malware telemetry and agentic risk

Overview

This is a documentation-only game design brainstorming skill that drafts local planning markdown and shows no hidden code, network, credential, or persistence behavior.

Install this if you want an agent to produce game concept and requirements notes in your workspace. Review the generated docs before using them as implementation requirements, and install the named companion skills only if you want the larger Game Superpowers workflow.

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 (1)

Vague Triggers

Medium
Confidence
94% confidence
Finding
The 'Use when' section describes situations like 'the request is exciting but blurry' and when a user says 'make it good' or 'make it fun,' which overlap with common feedback and are not specific trigger constraints. The file does not provide clear boundaries or negative examples to distinguish when this skill should activate versus when a different brainstorming or design skill should be used.

VirusTotal

65/65 vendors flagged this skill as clean.

View on VirusTotal

Static analysis

No suspicious patterns detected.