Back to skill

Security audit

Game Dev GDD

Security checks for vulnerabilities and agentic risk

Overview

This skill is a straightforward game design document helper that may create markdown files, with only minor scope and clutter considerations.

Install this if you want a guided game design document workflow. Be aware that vague requests for a "design document" may invoke it, and it may create or update markdown files under a GDD folder in your workspace.

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
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
95% confidence
Finding

The trigger phrase "design document" is broad enough to match many non-game requests, causing the skill to activate outside its intended scope. That can lead to inappropriate file-generation behavior or irrelevant guidance in unrelated contexts, especially because the skill is oriented around creating a structured gdd/ workspace output.

Content

No source excerpt is available for this finding.

Missing User Warnings

Low
Category
Not specified by scanner
Confidence
84% confidence
Finding

The skill instructs creation of directories and markdown files in the workspace but does not clearly disclose that behavior up front. While not directly malicious, undisclosed write actions can surprise users, clutter repositories, or modify project state when the user expected chat-only assistance.

Content

No source excerpt is available for this finding.