Security audit
AI Medical Device Global Compliance（AI医疗器械全球合规）
Security checks for vulnerabilities and agentic risk
Overview
This skill is a local AI medical-device compliance guide with an optional CLI, and I found no hidden network access, data collection, persistence, or credential handling.
This appears safe to install from a security perspective. Treat the regulatory content and cost/timeline estimates as reference material, not legal or regulatory advice, and verify important submissions against current FDA, EU, and NMPA sources before acting.
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.