ClawHub
Back to skill

Security audit

HK Insurance Data 香港保险数据

Security checks for vulnerabilities and agentic risk

Overview

This skill is a disclosed connector to a paid Hong Kong insurance data MCP API, with no executable files or hidden behavior found.

Before installing, understand that this skill sends queries to a third-party paid API and requires an API key. Treat the key as a secret, avoid pasting it into chats or code, and be cautious about letting an agent access your email client for verification unless you explicitly want that.

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

Static analysis

No suspicious patterns detected.