Security audit

Hutian Opc Patent Search

Security checks for vulnerabilities and agentic risk

Overview

This is a mostly documentation-only China IP workflow skill, but it needs review because it gives broad legal filing guidance involving sensitive identity and source-code materials with limited privacy and scope controls.

Review this carefully before installing. Use it only as informational China IP workflow guidance, verify all filing rules and fees against official sources or a qualified professional, and do not paste full ID cards, business licenses, source code, secrets, signatures, or sealed documents into chat unless you have a secure, approved handling process.

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

Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
MCP Tool PoisoningHidden Instructions, Unicode Deception, Parameter Description Injection
Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code

Findings (14)

Intent-Code Divergence

High

Category: Not specified by scanner
Confidence: 98% confidence
Finding: The guide says it was automatically generated by the skill while also instructing users to attest that AI was not used to generate code, documents, or filing materials. This contradiction creates a concrete compliance and integrity risk: users may be encouraged to submit false certifications or rely on AI-produced content in a workflow that the guide itself claims forbids AI-generated materials.
Content: No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium

Category: Not specified by scanner
Confidence: 95% confidence
Finding: The skill description and primary heading are entirely in Chinese, and the document does not state that users may interact in other languages or choose their preferred locale. Because this file is the skill's user-facing specification, it effectively imposes a Chinese-language interaction model without documented opt-in or justification as a region-specific-only tool.
Content: No source excerpt is available for this finding.

Description-Behavior Mismatch

Medium

Category: Not specified by scanner
Confidence: 97% confidence
Finding: The skill is scoped as a patent novelty/prior-art search tool, but the guide expands into trademark registrability, copyright registration, and software copyright filing workflows. This scope creep can mislead users into relying on the skill for legal-regulatory workflows it may not be designed to handle, increasing the chance of incorrect guidance, unauthorized processing of sensitive materials, and unsafe operational decisions.
Content: No source excerpt is available for this finding.

Missing User Warnings

Medium

Category: Not specified by scanner
Confidence: 94% confidence
Finding: The guide instructs handling of highly sensitive identity and application materials, including身份证、营业执照、签字/盖章文件、授权委托书等, without any visible privacy, retention, consent, or secure-handling warning. If users follow this workflow, they may expose personal and corporate documents to unnecessary collection, insecure storage, or over-sharing through the skill.
Content: No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium

Category: Not specified by scanner
Confidence: 88% confidence
Finding: The entire skill file is written as a Chinese-only guide and does not indicate that users may choose another language or locale. Under the policy rule for natural-language constraints, forcing a specific language without user opt-in can be a violation unless the locale restriction is clearly documented and justified.
Content: No source excerpt is available for this finding.

Description-Behavior Mismatch

Medium

Category: Not specified by scanner
Confidence: 95% confidence
Finding: The file materially exceeds the declared skill scope of novelty search and patent retrieval by providing post-grant maintenance, compliance, licensing, transfer, and commercialization guidance. In an agent setting, this scope drift can cause users or downstream agents to rely on unreviewed legal/operational advice outside the skill’s stated purpose, increasing the chance of inappropriate automation or mistaken authority.
Content: No source excerpt is available for this finding.

Description-Behavior Mismatch

Medium

Category: Not specified by scanner
Confidence: 95% confidence
Finding: The document includes extensive trademark and software-copyright maintenance content that is outside the manifest’s patent/technical novelty-search focus. This broadening is risky because the agent may answer with domain-misaligned legal guidance, creating overreach and user confusion about what has actually been vetted for this skill.
Content: No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium

Category: Not specified by scanner
Confidence: 91% confidence
Finding: The document is entirely in Chinese and provides no indication of language selection or user opt-in. While not a direct code-execution issue, forced language can cause users to misunderstand compliance steps, especially where identity, declarations, and legal attestations are involved, leading to user harm or incorrect submission behavior.
Content: No source excerpt is available for this finding.

Description-Behavior Mismatch

Medium

Category: Not specified by scanner
Confidence: 97% confidence
Finding: The file substantially expands the skill beyond its declared scope of technical novelty search and patent retrieval by providing a full software copyright registration manual. This scope drift is risky because users may rely on the skill for regulated legal/compliance guidance it was not represented or necessarily designed to provide, increasing the chance of incorrect advice and unsafe downstream handling of sensitive materials.
Content: No source excerpt is available for this finding.

Missing User Warnings

Medium

Category: Not specified by scanner
Confidence: 95% confidence
Finding: The manual instructs users to collect and submit highly sensitive identity documents such as ID cards, business licenses, and authorization materials, but provides no privacy, retention, redaction, or secure-handling warning. In a skill context, this can normalize unnecessary disclosure of personal and corporate identity data and increase the risk of oversharing, identity theft, or improper storage/transmission.
Content: No source excerpt is available for this finding.

Natural-Language Policy Violations

Low

Category: Not specified by scanner
Confidence: 91% confidence
Finding: The README presents all user-facing instructions and descriptions in Chinese only, which can constitute a language/locale policy issue when no user opt-in or alternative language is provided. There is no indication that the skill is intentionally restricted to Chinese-speaking users or a China-specific compliance context.
Content: No source excerpt is available for this finding.

Natural-Language Policy Violations

Low

Category: Not specified by scanner
Confidence: 84% confidence
Finding: This markdown file is entirely framed around Chinese legal procedures, Chinese institutions, and Chinese-language operation guidance, but it does not explicitly state that the skill is limited to China-related matters or offer users a language/locale choice. Under the policy rule, forcing a specific language or locale without opt-in can be a natural-language policy violation unless the constraint is clearly documented and justified.
Content: No source excerpt is available for this finding.

Natural-Language Policy Violations

Low

Category: Not specified by scanner
Confidence: 88% confidence
Content: No source excerpt is available for this finding.

Intent-Code Divergence

Low

Category: Not specified by scanner
Confidence: 87% confidence
Finding: The statement that the manual was generated by the novelty-search skill misrepresents provenance and scope, implying that maintenance and operations guidance belongs to this skill. While not directly exploit code, this can mislead users and orchestrators into assigning undue trust to out-of-scope legal content.
Content: No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.