ClawHub
Back to skill

Security audit

好啦体检方案 MCP

Security checks for vulnerabilities and agentic risk

Overview

This skill is a disclosed remote MCP connector for corporate health-check quotes, clinic lookup, FAQs, and business follow-up; the main caution is intentional collection of business contact details for inquiries.

Install only if you are comfortable sending quote inputs, clinic queries, and any corporate inquiry details you provide to Haola's remote MCP service. Do not submit a contact name or phone number unless the business wants follow-up, and use logged-in account features only when you intend to create or manage reservations, orders, or patient-related records.

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
  • 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 (2)

Missing User Warnings

Medium
Category
Not specified by scanner
Confidence
95% confidence
Finding

The skill explicitly instructs collection of company name, contact person, and phone number for corporate inquiries, but provides no user-facing notice about what data will be collected, why it is needed, how it will be used, or how long it will be retained. In a business-lead generation context, this creates a privacy and consent gap that can lead to unauthorized collection or unexpected downstream use of personal/business contact data.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Low
Category
Not specified by scanner
Confidence
83% confidence
Finding

The operational instructions, usage guidance, and examples are presented only in Chinese, which can impose a language constraint without user opt-in. The file does not state that the skill is region-specific or offer an alternative language path beyond the metadata display_name_en.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.