Back to skill

Security audit

Game Design Document CN

Security checks for vulnerabilities and agentic risk

Overview

This is a disclosed Chinese GDD-writing workflow that edits project planning documents only after user confirmation and shows no hidden code execution or data exfiltration.

Install this if you want a Chinese-language game system design document workflow. Expect it to read existing project planning files and, after confirmation, create or edit GDD and session-tracking files in the project.

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
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 (6)

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
96% confidence
Finding

The trigger list includes broad phrases such as “写策划案”, “做系统策划案”, and “系统拆解”, which can overlap with ordinary conversation and unrelated requests. This can cause the skill to activate unexpectedly, steering the agent into a rigid file-writing workflow with tool usage and document modification behavior the user did not explicitly intend.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
91% confidence
Finding

The skill description hard-codes a Chinese game-design process and terminology without stating that this is an optional or scoped workflow. In practice, this can cause the agent to force a region-specific methodology, naming convention, and document structure onto users whose project standards differ, leading to procedural misalignment and unintended edits.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
97% confidence
Finding

The title and opening instruction require writers to avoid English-translated style and sound like domestic Chinese planners, which effectively imposes a specific language/locale standard. Under the policy, forcing a language or locale without user opt-in is a natural-language policy violation unless clearly justified as region-specific.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
96% confidence
Finding

The file’s instructions and required output template are entirely in Chinese and state that each perspective’s output format is fixed. This imposes a specific language/locale on the skill behavior without user opt-in, which matches the language/locale policy violation criteria.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
95% confidence
Finding

The title and opening instructions establish the skill content entirely in Chinese and present it as a required writing standard, with no indication that users may select another language. This is a natural-language locale policy issue because it imposes a language constraint without documented opt-in or justification.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Low
Category
Not specified by scanner
Confidence
92% confidence
Finding

The title and instructional text are written as mandatory guidance in Chinese, including prescriptive wording like '文档写规则,表写数值', with no indication that other languages are allowed or that the locale restriction is optional. Under the policy, forcing a specific language without user opt-in or a documented region-specific justification is a natural-language policy concern.

Content

No source excerpt is available for this finding.