ClawHub
Back to skill

Security audit

Game Audit Scorecard

Security checks across malware telemetry and agentic risk

Overview

This is a narrow game-audit helper that creates project-local scorecard documentation and does not contain executable code or hidden data access.

Install this in game projects where you are comfortable with the agent reading project files and writing audit outputs under `docs/game-studio/audit/`. Review diffs before committing if existing scorecard or audit summary files matter.

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

Low
Confidence
85% confidence
Finding
The usage examples are broad enough that an orchestrating agent could invoke this skill in situations that only partially match its intended purpose, increasing the chance of inappropriate routing or overuse. In a security-sensitive workflow, ambiguous invocation guidance can cause the skill to be applied to projects outside game-audit scoring, leading to misleading outputs or workflow confusion rather than direct compromise.

VirusTotal

59/59 vendors flagged this skill as clean.

View on VirusTotal