Back to skill

Security audit

industrial-testcase-generator

Security checks for vulnerabilities and agentic risk

Overview

This is a coherent Chinese-language industrial test-case generation skill that reads requirements and produces an Excel test-case workbook without hidden execution, persistence, or data exfiltration behavior.

Installers should expect this skill to process potentially sensitive industrial requirement documents and generate Chinese-language Excel test cases. Review outputs before using them for safety, compliance, or certification work, especially because the skill may infer implicit requirements and default standards when source documents are incomplete.

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
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
  • MCP Tool PoisoningHidden Instructions, Unicode Deception, Parameter Description Injection
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
Findings (7)

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
93% confidence
Finding

文件标题及全文均以中文撰写,并明确面向中文语境输出,但没有说明是否支持用户选择其他语言或 locale。根据规则,若技能强制特定语言且未提供 opt-in/choice,应视为自然语言政策风险。

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
85% confidence
Finding

The skill metadata and behavior are written to operate in Chinese/localized form without indicating a user-selectable language option. While not a direct code-execution issue, forced localization can cause users to misunderstand outputs, validation criteria, or safety/compliance assumptions in an industrial context, increasing the chance of incorrect test artifacts being accepted or used.

Content

No source excerpt is available for this finding.

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
92% confidence
Finding

The trigger description enumerates many broad industrial and testing-related keywords, which can cause the skill to activate for loosely related prompts rather than only when the user explicitly requests testcase generation. Over-broad activation is dangerous because it can misroute user requests, pull sensitive industrial documents into an inappropriate workflow, or suppress a more suitable skill with stricter boundaries.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
95% confidence
Finding

This markdown file presents all instructions and requirements exclusively in Chinese, including the expected output guidance, with no indication that the user can choose another language. Under the policy, forcing a specific language without user opt-in is a natural-language policy violation unless the locale constraint is clearly documented and justified.

Content

No source excerpt is available for this finding.

Ae4

Medium
Category
analysis-evasion
Confidence
80% confidence
Finding

Suspicious Unicode normalization or mixed-script content

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
92% confidence
Finding

The document’s title and operational instructions are written entirely in Chinese, and the guidance assumes readers will use this Chinese knowledge base before generating test cases. Under the policy, language-specific requirements should either offer user opt-in or clearly justify a region-specific constraint; this file does neither.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
94% confidence
Finding

The file title and core instruction text require readers to follow a Chinese-language format specification, and there is no indication that users may choose another language or locale. Under the policy rules, forcing a specific language without opt-in is a natural-language policy violation unless the locale constraint is explicitly justified.

Content

No source excerpt is available for this finding.