ClawHub
Back to skill

Security audit

automotive-patent-valuation

Security checks for vulnerabilities and agentic risk

Overview

This skill is a disclosed Chinese automotive patent valuation framework that uses patent-search MCP tools when configured and does not show hidden execution, persistence, or destructive behavior.

Install only if you are comfortable connecting the agent to the required PatSnap/Zhihuiya MCP patent-data account. Treat its legal and business recommendations as decision support, not as a substitute for patent counsel or internal approval.

SkillSpector

Vulnerability Patterns
  • 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
  • Excessive AgencyUnrestricted Tool Access, Autonomous Decision Making, Scope Creep
Findings (1)

Natural-Language Policy Violations

Medium
Confidence
97% confidence
Finding
The description at L004 is written entirely in Chinese, and later instructions such as '每次分析必须输出以下表格' indicate the skill mandates a Chinese-oriented interaction/output pattern. Under the stated policy, forcing a specific language without user opt-in is a natural-language policy violation unless the locale constraint is explicitly justified.

Static analysis

No suspicious patterns detected.