AI医疗助手

• Outcome: Pass
• Latest audit: Jun 11, 2026 at 5:19 AM UTC
• Version:
  1.0.0

Overview

This is a prompt-only Chinese medical assistant skill with clean scans; its main risk is broad health advice, not hidden code or data access.

Install only if you want a Chinese-language medical information assistant. Do not rely on it for diagnosis, prescribing, dosage changes, emergencies, or medication adjustments without a licensed clinician, and be cautious about sharing personal medical details with any connected tools or model provider.

SkillSpector

By NVIDIA

Vulnerability Patterns

• Trigger Abuse: Overly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
• MCP Tool Poisoning: Hidden Instructions, Unicode Deception, Parameter Description Injection
• Prompt Injection: Instruction Override, Hidden Instructions, Exfiltration Commands
• Data Exfiltration: External Transmission, Env Variable Harvesting, File System Enumeration
• Privilege Escalation: Excessive Permissions, Sudo/Root Execution, Credential Access

Findings (2)

Vague Triggers

Medium

• Confidence: 91% confidence
• Finding: The skill defines broad medical capabilities but does not specify clear trigger phrases, invocation boundaries, or when it should decline activation. In a routing system, that can cause accidental invocation on generic health-related prompts, exposing users to unscoped medical guidance and increasing the chance of inappropriate reliance in sensitive contexts.

Natural-Language Policy Violations

Medium

• Confidence: 84% confidence
• Finding: The skill content is effectively Chinese-only without stating locale restrictions or offering language selection, which can create misunderstandings for users or orchestrators operating in other languages. In a medical context, language mismatch increases the risk of incorrect symptom interpretation, medication misunderstanding, and unsafe advice delivery.

VirusTotal

64/64 vendors flagged this skill as clean.