Back to skill

Security audit

Game Dev QA Test

Security checks for vulnerabilities and agentic risk

Overview

This is a game QA documentation skill that provides templates and may create project QA files, with no evidence of hidden code, credential access, network activity, or persistence.

Install this if you want structured game QA templates and testing workflows. Be aware it may create Markdown QA documents in your project, so confirm the destination path before asking it to generate files.

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 (3)

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
94% confidence
Finding

The trigger phrase at this location is broad enough to match common user requests outside a narrowly scoped invocation context, which can cause the skill to activate unintentionally. In an agent environment, accidental activation may lead to irrelevant instructions being injected into the conversation or unintended file-creation guidance being followed.

Content

No source excerpt is available for this finding.

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
90% confidence
Finding

This trigger is also ambiguous and likely to overlap with ordinary conversation, increasing the chance of misrouting a general request into this skill. Even though the skill content is not overtly harmful, unintended invocation can still alter agent behavior and push workspace-modifying recommendations or structured outputs the user did not request.

Content

No source excerpt is available for this finding.

Missing User Warnings

Low
Category
Not specified by scanner
Confidence
88% confidence
Finding

The platform note states the skill can create test suites as files, and the document structure instructs creating files under a project directory, but there is no explicit user-facing warning that the skill may write new files into the workspace. For markdown guidance, this omission matters because file creation can affect user data and repository state.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.