ClawHub
Back to skill

Security audit

Game Design Player Values Mapper

Security checks across malware telemetry and agentic risk

Overview

This skill only gives game-design analysis instructions and does not install code, access accounts, or run background actions.

Install only if you want an agent to analyze player behavior for design and personalization. Use aggregated or consented telemetry where possible, avoid raw personal identifiers, and do not use the outputs for exploitative monetization, psychological pressure, or sensitive-attribute inference.

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
84% confidence
Finding
The skill description is broad enough to trigger in many ordinary game-design conversations, which can cause the agent to invoke this skill on loosely related inputs and over-collect or over-infer sensitive motivational attributes from player behavior. In this context, the skill explicitly supports personalization, segmentation, live-ops targeting, and monetization alignment, so overbroad activation increases the risk of manipulative profiling or use outside the user's intended scope.

VirusTotal

65/65 vendors flagged this skill as clean.

View on VirusTotal

Static analysis

No suspicious patterns detected.