Security audit

ym-game-balance-calc

Security checks for vulnerabilities and agentic risk

Overview

This skill is a local game-balance calculator with no evidence of hidden data access, persistence, networking, or destructive behavior.

Installers should know this is a Chinese-language offline calculator for game-design numbers. Use it when you want concrete DPS, leveling, or economy calculations, and ask for clarification if a request only mentions balance design generally without numeric inputs.

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 (3)

Vague Triggers

Medium

Confidence: 92% confidence
Finding: The trigger phrase "数值平衡" is broad enough to match ordinary game-design discussion that may not actually request execution of this skill. This can cause accidental or premature invocation, leading the agent to apply numeric-analysis behavior in contexts where the user only intended conceptual discussion, but the skill itself is otherwise constrained to local computation and does not expose high-risk capabilities.

Vague Triggers

Medium

Confidence: 90% confidence
Finding: Examples like "DPS 算一下" and "数值平衡" are open-ended and can over-trigger the skill during general discussion, especially because they lack constraints requiring concrete parameters or a request for calculation. The danger is mainly misrouting and unintended skill activation rather than code execution or data exfiltration, since the skill explicitly limits itself to built-in formulas and offline local analysis.

Natural-Language Policy Violations

Low

Confidence: 95% confidence
Finding: The file’s natural-language interface, examples, help text, and runtime output are all written in Chinese, and the header indicates UTF-8 output is enforced for that locale context. There is no option for users to choose another language or any documented justification that the tool is intentionally region-specific.

Static analysis

No suspicious patterns detected.