Back to skill

Security audit

Testcase Reviewer

Security checks for vulnerabilities and agentic risk

Overview

This skill is a Chinese-language test case review template that reads user-provided requirements and test cases, then produces a local Markdown review report.

Install this if you want a Chinese-language structured reviewer for functional test cases. Before running it in a shared repository, confirm where the generated report will be written and avoid overwriting existing reports.

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
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
  • Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
  • Excessive AgencyUnrestricted Tool Access, Autonomous Decision Making, Scope Creep
Findings (3)

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
96% confidence
Finding

The skill’s name, description, headings, and operational instructions are entirely specified in Chinese, indicating the skill is intended to operate in Chinese by default. There is no statement that users may choose another language or that the Chinese-only behavior is required for a region-specific compliance purpose, which creates a locale-policy concern.

Content

No source excerpt is available for this finding.

Missing User Warnings

Low
Category
Not specified by scanner
Confidence
91% confidence
Finding

The skill instructs the agent to write a report into a local report/ directory without clearly warning the user that filesystem writes will occur. Undisclosed file creation can surprise users, overwrite existing artifacts, or create unwanted persistence in sensitive workspaces, especially when run in shared repositories or automation environments.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Low
Category
Not specified by scanner
Confidence
92% confidence
Finding

该 markdown 模板全文以中文编写,且未说明这是仅适用于中文团队/中文文档环境的区域性模板,也未提供其他语言选项。根据语言/locale 政策,若技能或模板强制单一语言而没有用户选择或明确适用范围,可能构成自然语言策略问题。

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.