Security audit

医械注册工程师·全球通关枢纽

Security checks for vulnerabilities and agentic risk

Overview

This is a disclosed, document-only medical-device regulatory reference skill with no executable code or hidden data access.

Installers should treat this as a regulatory reference aid, not legal or formal RA advice. Because some triggers are generic, confirm the conversation is actually about medical-device registration before relying on the skill, and verify time-sensitive regulatory links against the official source before filing or submitting anything.

SkillSpector

Vulnerability Patterns

Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
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

Findings (1)

Vague Triggers

Medium

Confidence: 77% confidence
Finding: The trigger list contains broad terms such as '标签', '设计开发', '验证', and '投诉' that can appear in many unrelated conversations, causing the skill to activate outside its intended medical-device-regulatory context. Over-broad auto-activation can route irrelevant user queries into this skill, leading to incorrect domain-specific guidance, reduced user control, and possible disclosure of conversation content to an unnecessary skill context.

Static analysis

No suspicious patterns detected.