Security audit

中文写作润色助手

Security checks for vulnerabilities and agentic risk

Overview

This is a simple Chinese writing-polish skill with no code execution, dependencies, persistence, or credential access.

Install this if you want a Chinese writing and editing assistant. Be aware that broad requests like resume or email polishing may invoke it, and it will naturally default to Chinese-language editing unless the user steers otherwise.

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 (3)

Vague Triggers

Medium

Category: Not specified by scanner
Confidence: 92% confidence
Finding: 触发词中包含“帮我润色中文”“修改中文语法”“优化中文表达”等较日常、泛化的短语，确实可能在普通对话中被误匹配，导致技能被非预期调用。该技能本身仅执行文本润色，危险性不高，但误触发会带来路由错误、用户意图偏离和不必要的数据暴露给该技能处理的问题。
Content: No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium

Category: Not specified by scanner
Confidence: 91% confidence
Finding: The description states the skill is a professional Chinese writing polishing tool and lists only Chinese-language writing use cases. This natural-language description imposes a language-specific constraint without any indication that users can choose another language or explicitly opt into the locale restriction.
Content: No source excerpt is available for this finding.

Natural-Language Policy Violations

Low

Category: Not specified by scanner
Confidence: 81% confidence
Finding: L004 将技能描述为“专业的中文写作润色工具”，整体文档也默认仅输出中文，但未明确说明这是用户主动选择中文场景后的专用技能，或在非中文请求时如何处理。按语言/locale 政策，若技能对输出语言作强约束，最好明确这是基于用户选择或提供可选语言机制。
Content: No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.