Security audit

中国专利审查意见答复（CN Patent OA Response）

Security checks for vulnerabilities and agentic risk

Overview

This skill is mostly coherent for CNIPA office-action drafting, but it can send sensitive patent/legal files to a cloud OCR service without an explicit consent step.

Install only if users are allowed to process the relevant patent and legal documents through PatSnap/Zhihuiya cloud OCR. For confidential, unpublished, privileged, or client-restricted files, require explicit approval first, prefer local/text extraction when possible, and use environment-based credential handling instead of passing API keys on the command line.

A.I.G

Vulnerability Patterns

Insecure Skill Coding PracticesFinds exploitable flaws such as hardcoded secrets or command injection
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

Findings (1)

T09 · Insecure Skill Coding Practices

Warning

Location: SKILL.md:24
Finding: Cloud Upload of Potentially Confidential Patent Documents Without Explicit User Consent
Content: View full analysis
Remediation: View remediation

SkillSpector

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
Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code

Findings (6)

Natural-Language Policy Violations

Medium

Category: Not specified by scanner
Confidence: 87% confidence
Finding: L004 的描述整体以中文规定技能用途与输出场景，但未说明是否仅适用于中文用户、中文输出，或是否允许用户选择其他语言。这可能构成语言/locale 强制约束，尤其在技能说明层面没有给出用户选择或明确的区域合规理由。
Content: No source excerpt is available for this finding.

Missing User Warnings

Medium

Category: Not specified by scanner
Confidence: 80% confidence
Finding: This markdown file instructs users to pass credentials through --api-key or AI_API_KEY, which is a sensitive operation affecting privacy and security. Although it says not to paste credentials later in the file, it does not clearly warn at the point of use about exposure risks such as shell history, process lists, or careful credential handling during execution.
Content: No source excerpt is available for this finding.

Natural-Language Policy Violations

Low

Category: Not specified by scanner
Confidence: 75% confidence
Finding: The display name is presented primarily in Chinese, which may impose a language preference without stating that users can choose their preferred language. The policy calls for flagging language or locale constraints unless the skill offers user choice or clearly documents a justified regional restriction.
Content: No source excerpt is available for this finding.

Vague Triggers

Low

Category: Not specified by scanner
Confidence: 84% confidence
Finding: This is a manifest file, so vague-trigger review applies. The default prompt says to use the skill to analyze a CNIPA office action and prepare a response draft, but it does not define explicit activation phrases, scope boundaries, or exclusion conditions, which can make invocation criteria ambiguous in orchestration systems that rely on natural-language matching.
Content: No source excerpt is available for this finding.

Natural-Language Policy Violations

Low

Category: Not specified by scanner
Confidence: 94% confidence
Finding: This file contains a full operational instruction in Chinese describing fallback behavior, while the rest of the document is primarily in English. That creates a language-policy issue because it forces comprehension of a specific language without explicit user opt-in or justification.
Content: No source excerpt is available for this finding.

Natural-Language Policy Violations

Low

Category: Not specified by scanner
Confidence: 88% confidence
Finding: The phrase 技术三要素 appears in an otherwise English description without translation or opt-in. This may impose a language requirement on users who do not read Chinese, which conflicts with the requirement not to force a specific language without user choice or clear justification.
Content: No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.