Security audit

游戏

Security checks across malware telemetry and agentic risk

Overview

This skill is not clearly malicious, but it asks for broad read, write, and command execution authority while its game-asset purpose and safety limits are under-specified.

Review this skill before installing. It may be useful for game development, but only install it if you are comfortable granting command execution and file write access, and use it in a constrained workspace without sensitive files or credentials until the publisher narrows the scope and documents enforceable command limits.

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 (5)

Description-Behavior Mismatch

Medium

Confidence: 94% confidence
Finding: The skill claims to be for game asset generation, but its documentation describes a generic automation/code-execution capability. This mismatch can cause the agent or user to invoke a much more powerful skill than expected, increasing the chance of unsafe file or command operations under a misleading label.

Description-Behavior Mismatch

Medium

Confidence: 91% confidence
Finding: The input/output section describes generic content processing rather than game-specific asset generation, indicating the skill may be a repurposed general processor. Ambiguous I/O contracts make it easier to route arbitrary tasks through a skill that also has read/write/exec capabilities, which expands abuse potential.

Context-Inappropriate Capability

Medium

Confidence: 97% confidence
Finding: The skill exposes broad exec capability even though its stated purpose is game asset generation. If invoked on untrusted prompts, this enables shell command execution beyond what is necessary for the business purpose, potentially leading to file tampering, data access, or arbitrary code execution on the host.

Intent-Code Divergence

High

Confidence: 98% confidence
Finding: The document claims only whitelisted commands are executed, but no whitelist or enforcement mechanism is defined anywhere in the skill. This creates a false sense of safety while leaving broad execution power available, making prompt-driven command abuse more likely and harder for users to assess.

Vague Triggers

Medium

Confidence: 88% confidence
Finding: The invocation guidance says to use the skill for broad coding, debugging, testing, and deployment tasks, which far exceeds game asset generation. Overly broad routing criteria can cause the agent to select a powerful skill with exec/write access for unrelated requests, increasing the attack surface for prompt injection or misuse.

VirusTotal

VirusTotal findings are pending for this skill version.

View on VirusTotal

Static analysis

No suspicious patterns detected.