ClawHub
Back to skill

Security audit

Macau Clinic AI System

Security checks for vulnerabilities and agentic risk

Overview

This non-executable clinic-planning skill is coherent, but it promotes AI handling of patient records and messaging workflows without clear privacy, consent, or compliance safeguards.

Review before installing or using this skill in a real clinic. It should only be used with explicit patient consent, compliant AI and messaging vendors, secure storage, access controls, retention/deletion policies, and local healthcare privacy/legal review. Avoid sending identifiable clinical details through general chat or AI services unless the deployment has been assessed and approved.

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
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • 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
Confidence
95% confidence
Finding
The skill proposes recording clinical conversations, transcribing them, and automatically generating medical records, but provides no warning or safeguards for handling highly sensitive health data. In a medical context, this can lead users to process protected patient information through AI systems without consent controls, retention limits, security requirements, or regulatory/privacy review.

Missing User Warnings

Medium
Confidence
93% confidence
Finding
The skill recommends WhatsApp/WeChat appointment workflows and AI auto-replies without warning that patient names, appointment details, and potentially health-related information may be transmitted through third-party messaging platforms. In a clinic setting, this creates significant privacy and compliance risk because users may deploy consumer messaging integrations for protected health information without verifying security, consent, data residency, or platform suitability.

Static analysis

No suspicious patterns detected.