Security audit

text-game-arcade-universe-v3

Security checks for vulnerabilities and agentic risk

Overview

This is a chat-only text game skill whose behavior is disclosed and aligned with running ASCII board and puzzle games.

Install this if you want a Chinese-first text game arcade in chat. Be aware that generic phrases like asking for a small game may open the game lobby, and English-only users may need to explicitly ask for English responses.

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

Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
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 (16)

Natural-Language Policy Violations

Medium

Confidence: 88% confidence
Finding: The README is entirely written in Chinese and describes the skill as oriented to OpenClaw / ClawHub without indicating that language selection is optional. Under the policy, forcing a specific language or locale without user opt-in can be a natural-language policy violation unless the regional constraint is explicitly justified.

Vague Triggers

Medium

Confidence: 95% confidence
Finding: The recommended trigger phrase "来个小游戏" is very broad and can easily overlap with ordinary conversation, causing the skill to activate unintentionally. In a multi-skill or agent environment, overly generic routing phrases can hijack unrelated user requests and lead to incorrect behavior, reduced reliability, or unintended game-mode responses.

Vague Triggers

Medium

Confidence: 94% confidence
Finding: The high-priority trigger phrases are broad enough to match ordinary conversational requests such as asking to draw a board or casually asking to play, which can cause the skill to activate when the user did not explicitly intend to enter this game skill. In a routed agent system, this can override more appropriate skills or alter the assistant's behavior unexpectedly, reducing reliability and potentially causing consent/context issues.

Vague Triggers

Medium

Confidence: 92% confidence
Finding: The weak trigger examples are highly ambiguous phrases like asking for a 'small game' or a 'game lobby,' which can appear in non-skill contexts and still route into this skill. Because the section explicitly permits activation on vague intent, it increases the chance of false routing and unintended stateful behavior during normal chat.

Natural-Language Policy Violations

Medium

Confidence: 88% confidence
Finding: The file presents all user-facing instructions and style guidance in Chinese, including the suggested host narration, without indicating that language selection is optional. Under the policy, forcing a specific language without user opt-in can be a natural-language policy violation unless the locale constraint is clearly justified.

Natural-Language Policy Violations

Medium

Confidence: 86% confidence
Finding: The file is written entirely in Chinese and labels itself as a Chinese-language variant, but it does not state that the user can choose another language or that the locale restriction is required for a region-specific purpose. This creates a natural-language policy concern because the skill appears to impose a language preference without opt-in.

Natural-Language Policy Violations

Medium

Confidence: 92% confidence
Finding: The skill instructions are written in Chinese and specify output text in Chinese (for example, the required per-turn echo at L18), with no indication that users may choose another language. This creates a language/locale policy issue because it imposes a specific language without user opt-in or justification.

Natural-Language Policy Violations

Medium

Confidence: 95% confidence
Finding: The document’s instructional content is written entirely in Chinese and uses Chinese user-facing example text such as “你在 H8 落子，AI 在 H9 应对。” without offering a language choice. This creates a natural-language locale policy issue because it effectively forces a specific language for skill behavior absent any user opt-in or documented regional justification.

Natural-Language Policy Violations

Medium

Confidence: 95% confidence
Finding: The file presents all instructional content in Chinese, aside from the title and command tokens, and does not indicate that language selection is optional. Under the policy, forcing a specific language without user opt-in is a natural-language policy violation unless the locale restriction is clearly justified.

Natural-Language Policy Violations

Medium

Confidence: 74% confidence
Finding: The routing instructions and trigger definitions are written primarily in Chinese and do not state that users may choose another language or locale. This can be a language policy concern when the skill behavior is effectively constrained to one language without opt-in or explicit justification.

Vague Triggers

Medium

Confidence: 95% confidence
Finding: The trigger phrases '来个小游戏', '开一局', and '陪我玩' are broad, conversational expressions that can appear in ordinary chat without a clear request to invoke this specific skill. In an agent environment, such broad activation language can cause unintended routing into the game skill, overriding user intent or interrupting unrelated conversations.

Vague Triggers

Medium

Confidence: 88% confidence
Finding: The listed triggers include generic terms like '文字游戏', '标准棋盘', and broad game-category names, which makes the activation scope ambiguous. This increases the chance that normal discussion about games, boards, history, or examples will incorrectly route into gameplay behavior rather than answering the user's actual query.

Natural-Language Policy Violations

Low

Confidence: 92% confidence
Finding: This markdown file contains user-facing natural language exclusively in Chinese, but does not state that the skill is China-specific or that other languages are optional. Under the language/locale policy rule, forcing a specific language without opt-in can be a policy concern.

Natural-Language Policy Violations

Low

Confidence: 96% confidence
Finding: The instruction “中文为主” imposes a language preference on the user experience without indicating that the user can choose another language. This is a natural-language locale policy concern because it sets a default language rather than offering opt-in or respecting user language preference.

Natural-Language Policy Violations

Low

Confidence: 88% confidence
Finding: The file's headings and instructions are written entirely in Chinese and do not offer any language choice or opt-in mechanism. Under the policy, forcing a specific language or locale without user choice is a natural-language policy violation unless clearly justified as region-specific.

Natural-Language Policy Violations

Low

Confidence: 92% confidence
Finding: The file's operational instructions and labels are written in Chinese, which imposes a specific language on users. Under the policy, locale or language constraints should either be optional/opt-in or clearly documented as justified; this file does neither.

Static analysis

No suspicious patterns detected.