ClawHub
Back to skill

Security audit

Game Dev prototype

Security checks for vulnerabilities and agentic risk

Overview

This is a Markdown-only game prototyping workflow with minor broad-trigger quality concerns but no hidden, privileged, or unsafe behavior found.

Reasonable to install for game prototyping. Be aware it may activate on broad prototype or game-jam phrasing, and confirm any archive or delete step before letting an agent change local prototype files.

A.I.G

Vulnerability Patterns
  • Skill Instruction HijackingAlters the agent's session goals or safety constraints when the skill loads
  • Agent Memory PoisoningWrites attacker-controlled rules into memory that affect later sessions
  • Remote Payload Retrieval and ExecutionFetches external code whose behavior can change after review
  • Embedded Malicious CodeShips malicious scripts inside the skill and executes them locally
  • Unauthorized Access and Privilege EscalationObtains permissions beyond the task's legitimate needs

SkillSpector

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
Category
Not specified by scanner
Confidence
91% confidence
Finding

The trigger "prototype an idea" is generic and could match many everyday brainstorming or product-design requests beyond this skill's intended game-development scope. The file does not provide exclusion conditions or narrower context at the trigger list to prevent unintended invocation.

Content

No source excerpt is available for this finding.

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
87% confidence
Finding

The trigger "game jam" is extremely broad and may refer to discussion, participation, planning, or postmortem topics rather than this specific rapid-validation workflow. Because no activation boundaries or exclusions are listed, the skill could be invoked for unrelated game-jam requests.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.