Security audit

软件测试用例设计

Security checks for vulnerabilities and agentic risk

Overview

This is a Markdown-only Chinese test-case design skill with no executable code, persistence, credential handling, or hidden system access.

Installers should expect Chinese test-case templates and broad activation on testing-related prompts. Review output language and scope if your team needs multilingual behavior, but the artifact does not show security-sensitive execution or data handling.

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
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

Findings (2)

Natural-Language Policy Violations

Medium

Category: Not specified by scanner
Confidence: 96% confidence
Finding: 标题与全文说明均以中文呈现，并将技能定位为固定中文输出风格，但文档中没有说明可根据用户偏好切换语言，也没有给出区域性限制的合理性说明。按照语言/locale 政策，若强制特定语言且无用户选择或明确理由，属于自然语言层面的策略问题。
Content: No source excerpt is available for this finding.

Vague Triggers

Medium

Category: Not specified by scanner
Confidence: 93% confidence
Finding: The trigger section relies on broad natural-language examples such as '帮我写一下…测试用例' and similar generic requests, without clear exclusion conditions or stronger routing constraints. This can cause the skill to activate on loosely related prompts, leading to prompt hijacking of unrelated tasks, user confusion, and unintended disclosure or transformation of user-provided material into test artifacts.
Content: No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.