Patent Software Ip

• Outcome: Pass
• Latest audit: Sep 16, 2026 · 8:45 AM UTC
• Version: 2.0.0

Overview

The skill is a markdown-only guide for generating Chinese patent and software-copyright documents, with expected but privacy-sensitive project analysis and online prior-art search steps.

Install only if you want a China-focused patent/software-copyright drafting helper. Before using prior-art search, ask the agent to show and sanitize search queries so confidential code, unpublished invention details, keys, endpoints, names, and business data are not sent to external services.

A.I.G

Vulnerability Patterns

• Skill Instruction Hijacking: Alters the agent's session goals or safety constraints when the skill loads
• Agent Memory Poisoning: Writes attacker-controlled rules into memory that affect later sessions
• Remote Payload Retrieval and Execution: Fetches external code whose behavior can change after review
• Embedded Malicious Code: Ships malicious scripts inside the skill and executes them locally
• Unauthorized Access and Privilege Escalation: Obtains permissions beyond the task's legitimate needs

SkillSpector

Vulnerability Patterns

• Prompt Injection: Instruction Override, Hidden Instructions, Exfiltration Commands
• Data Exfiltration: External Transmission, Env Variable Harvesting, File System Enumeration
• Trigger Abuse: Overly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
• Privilege Escalation: Excessive Permissions, Sudo/Root Execution, Credential Access
• Supply Chain: Unpinned Dependencies, External Script Fetching, Obfuscated Code

Findings (10)

Hidden Instructions

High

• Category: Prompt Injection

Content

---
---# AI项目软件著作权登记特殊指南

## 1. AI项目类型识别

• Confidence: 60% confidence
• Finding: Hidden instructions were detected in comments or invisible text. These could contain malicious directives. Manual review is recommended.

Hidden Instructions

High

• Category: Prompt Injection

Content

---
---# AI项目软件著作权登记特殊指南

## 1. AI项目类型识别

• Confidence: 60% confidence
• Finding: Hidden instructions were detected in comments or invisible text. These could contain malicious directives. Manual review is recommended.

Hidden Instructions

High

• Category: Prompt Injection

Content

---
---# AI项目软件著作权登记特殊指南

## 1. AI项目类型识别

• Confidence: 60% confidence
• Finding: Hidden instructions were detected in comments or invisible text. These could contain malicious directives. Manual review is recommended.

Hidden Instructions

High

• Category: Prompt Injection

Content

---
---# AI项目软件著作权登记特殊指南

## 1. AI项目类型识别

• Confidence: 60% confidence
• Finding: Hidden instructions were detected in comments or invisible text. These could contain malicious directives. Manual review is recommended.

Vague Triggers

Medium

• Confidence: 96% confidence
• Finding: The trigger list contains broad generic terms such as "patent," "claims," and "specification," which are common in normal discussion and could cause the skill to activate unintentionally. In a skill that processes project code, docs, and potentially sensitive IP, accidental invocation increases the chance of unnecessary data exposure or execution of privacy-impacting workflow steps.

Missing User Warnings

Medium

• Confidence: 95% confidence
• Finding: The skill instructs the agent to perform online prior-art searches against external services using project-derived technical information, but it does not disclose network access, data sharing, or require consent/redaction before transmission. Because the skill is specifically designed to analyze proprietary code, design docs, and research papers for patent drafting, this creates a meaningful risk of leaking confidential or unpublished invention details to third-party systems.

External Transmission

Medium

• Category: Data Exfiltration

Content

- [ ] 删除内网地址和域名
- [ ] 删除个人邮箱、姓名
- [ ] 删除具体硬件型号（A100/H100→GPU，Jetson→边缘计算设备）
- [ ] 删除云服务端点URL（替换为 `https://api.example.com/`）
- [ ] 删除数据库连接串中的密码
- [ ] 保留注释中关键算法说明（审查员可能参考）

• Confidence: 50% confidence
• Finding: Data is being sent to an external URL. This could be legitimate telemetry or data exfiltration. Manual review is recommended.

Natural-Language Policy Violations

Low

• Confidence: 91% confidence
• Finding: The title and the overwhelming body of the guide are presented in Chinese, with no indication that language selection is optional or that the skill is intended only for Chinese-speaking users or a China-specific legal context. Under the policy rule, a fixed language or locale without user opt-in can be a natural-language policy violation.

Natural-Language Policy Violations

Low

• Confidence: 93% confidence
• Finding: This markdown file contains instructional content exclusively in Chinese, and there is no indication that users may choose another language or that the skill is intentionally limited to a Chinese-speaking audience. Under the natural-language policy rule, forcing a specific language without user opt-in can be a locale-policy violation.

Natural-Language Policy Violations

Low

• Confidence: 97% confidence
• Finding: This markdown file contains user-facing instructional content exclusively in Chinese, and nowhere indicates that the skill is China-specific or that users may choose another language. That can conflict with language/locale policy expectations when a skill is intended for a broader audience.

Static analysis

No suspicious patterns detected.