Security audit

Game Toolkit Free

Security checks for vulnerabilities and agentic risk

Overview

The skill is a game-design prompt package, but it declares broad read, write, and command-execution authority that is not needed for its stated purpose.

Review this before installing. It appears to be a game-design helper, not malware, but it asks for command execution and file read/write capabilities without a clear need. Install only in a tightly sandboxed environment or after the publisher narrows the permissions, removes the unrelated analytics trigger, and defines explicit limits for any save/export/import behavior.

A.I.G

Vulnerability Patterns

Unauthorized Access and Privilege EscalationObtains permissions beyond the task's legitimate needs
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

Findings (1)

T05 · Unauthorized Access and Privilege Escalation

Warning

Location: SKILL.md:24
Finding: Excessive and Ambiguous Tool Permissions
Content: View full analysis
Remediation: View remediation

SkillSpector

Vulnerability Patterns

Excessive AgencyUnrestricted Tool Access, Autonomous Decision Making, Scope Creep
Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
MCP Tool PoisoningHidden Instructions, Unicode Deception, Parameter Description Injection
Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration

Findings (7)

Context-Inappropriate Capability

High

Category: Not specified by scanner
Confidence: 98% confidence
Finding: exec is a high-risk capability and there is no legitimate, documented need for shell command execution in a personal game-design skill. If exposed to prompts or automation, this could be abused to run arbitrary local commands, inspect the environment, or chain into broader compromise depending on agent permissions.
Content: No source excerpt is available for this finding.

Vague Triggers

High

Category: Not specified by scanner
Confidence: 98% confidence
Finding: The trigger condition says to use the skill for data analysis, report generation, statistical insights, and visualization, which is unrelated to game design. Overbroad and misleading activation criteria can cause the agent to invoke this skill in inappropriate contexts, unintentionally exposing its write/exec capabilities to unrelated tasks where they pose greater risk.
Content: No source excerpt is available for this finding.

Description-Behavior Mismatch

Medium

Category: Not specified by scanner
Confidence: 96% confidence
Finding: The skill is presented as a pure local game-design generator, yet it declares both file writing and command execution capabilities. This creates a capability/description mismatch that can mislead users and agents into granting or invoking privileged actions not required for the advertised function, increasing the chance of unintended file changes or command execution.
Content: No source excerpt is available for this finding.

Context-Inappropriate Capability

Medium

Category: Not specified by scanner
Confidence: 91% confidence
Finding: The documented support for generic create/query/export, modify/reset/import, and save/convert operations is far broader than necessary for generating game rules. Broad state-changing operations without scope limits can be repurposed to alter files, overwrite user content, or import untrusted data under an innocuous game-design pretext.
Content: No source excerpt is available for this finding.

Missing User Warnings

Medium

Category: Not specified by scanner
Confidence: 90% confidence
Finding: The skill advertises export/save/modify/reset/import operations that can affect user data, but it provides no warnings, consent model, or safety boundaries. Without explicit disclosure and confirmation, a user may not realize the skill can change or overwrite content, creating avoidable integrity and privacy risks.
Content: No source excerpt is available for this finding.

Intent-Code Divergence

Medium

Category: Not specified by scanner
Confidence: 90% confidence
Finding: The documentation says the skill is local-only and does not require networking, but elsewhere it instructs network diagnostics and states execution depends on network conditions. These contradictions undermine trust boundaries and may normalize unexpected connectivity checks or network-dependent behavior that users did not consent to.
Content: No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium

Category: Not specified by scanner
Confidence: 93% confidence
Finding: L427-L429 中设置了 GAME_DESIGNER_LANGUAGE="zh"，体现出默认语言约束，但文档未说明这是可选默认值、也未向用户提供语言选择或显式 opt-in。根据语言/locale 政策，强制特定语言而无用户选择属于自然语言策略问题。
Content: No source excerpt is available for this finding.