ClawHub
Back to skill

Security audit

《厨房战争》全面红警化，并在多个维度做了"超越"。

Security checks for vulnerabilities and agentic risk

Overview

This skill is a self-contained browser RTS game with disclosed local test scripts and no evidence of hidden network, credential, or destructive behavior.

This appears safe to install for users who want the bundled Kitchen War RTS game. Expect it to copy/open a local HTML game, run optional local Playwright verification scripts when the game is edited, and store minor browser localStorage progress/preferences. Review the Chinese-only UI if you need localization.

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
  • 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
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
Findings (9)

Tp4

High
Category
MCP Tool Poisoning
Confidence
97% confidence
Finding

The description says this skill provides and maintains a playable self-contained RTS game in index.html. However, the provided code chunk is an external JavaScript audit script (_audit2.js) whose primary purpose is quality assurance: launching Chromium, opening the HTML file, simulating clicks, spawning units, forcing superweapon state, checking repair/sell/capture/production behavior, and asserting no crashes or warnings. While this code is related to the Kitchen War project, it does not itself implement the declared gameplay features or serve as the browser game artifact. Instead, it adds a significant undeclared capability: automated end-to-end testing and auditing of the game using Playwright and Node. That is a material description-behavior mismatch.

Content

No source excerpt is available for this finding.

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
94% confidence
Finding

The manifest description says to use this skill when the user asks for 'a playable browser strategy game' or '帮我做个能玩的战略游戏', which are broad requests not uniquely tied to this Kitchen War/Red Alert-style skill. Without tighter scope limits or exclusion examples, the trigger may cause unintended invocation for generic strategy-game requests.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
88% confidence
Finding

The description mandates delivery and maintenance of a game identified with Chinese names and UI strings, but does not indicate that the user can choose another language or that the locale is region-specific. This creates a natural-language policy issue because the skill appears to enforce a specific language presentation by default.

Content

No source excerpt is available for this finding.

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
91% confidence
Finding

The usage bullets include 'playable browser RTS game' and broad Chinese phrases, plus 'create, fix, extend, or re-verify the Kitchen War game.' The first two are not constrained with exclusions, so they may overlap with common requests for browser games or strategy games that are not intended for this specific skill.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
86% confidence
Finding

The delivery instructions require specific Chinese UI text such as '烤鸭空袭', and the feature list throughout the document continues to prescribe Chinese labels. Because no alternative language choice is offered, the skill appears to impose a locale on the user rather than adapting to preference.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
89% confidence
Finding

This code embeds natural-language unit names in Chinese, such as '激光兵', and elsewhere the script uses Chinese-only assertion labels. Because SQP-3 applies to all file types, this is a policy concern if the skill effectively assumes a single language/locale with no user opt-in or documented justification.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
83% confidence
Finding

The embedded display name '工程师' is a natural-language string that enforces Chinese as the only visible locale in this file. Under SQP-3, forcing a specific language without user choice or clear regional justification is a policy violation.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Low
Category
Not specified by scanner
Confidence
97% confidence
Finding

The document declares lang="zh-CN", and the visible UI text throughout the page is Chinese-only. Under the policy rule, forcing a specific language/locale without user opt-in is a natural-language policy concern unless the skill is clearly region-specific or offers a language choice.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Low
Category
Not specified by scanner
Confidence
92% confidence
Finding

The script hard-codes user-facing natural-language strings in Chinese for assertion names and expected UI labels, such as "首次访问自动弹出操作说明" and "速度 1x". This enforces a specific language/locale in the skill behavior without offering a language choice or documenting a justified locale restriction.

Content

No source excerpt is available for this finding.

Static analysis

Detected: suspicious.dynamic_code_execution

Dynamic code execution detected.

Critical
Code
suspicious.dynamic_code_execution
Location
scripts/verify_game.js:140