Security audit

Medical Device Data Export Compliance（医械数据出海合规）

Security checks for vulnerabilities and agentic risk

Overview

This skill is a disclosed compliance guide with a small local Python helper, and I did not find hidden network, credential, persistence, or destructive behavior.

Installers should understand that this skill can be used with optional local Python commands, but those commands appear limited to local, stdout-only compliance triage. Treat the legal/regulatory outputs as a starting point and verify current requirements with official sources or counsel before relying on them for regulated data transfers.

SkillSpector

Vulnerability Patterns

MCP Least PrivilegeUnderdeclared Capability, Wildcard Permission, Missing Permission Declaration
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)

Lp3

Medium

Category: MCP Least Privilege
Confidence: 95% confidence
Finding: The skill advertises executable local tooling via `python tools/data_export_toolkit.py ...` and states it can output checklists and perform path/threshold calculations, which implies shell execution and likely file read/write behavior, yet no permissions are declared. This creates a capability/expectation mismatch: users or the hosting platform may execute the skill without appropriate sandboxing or informed consent, increasing the risk of unintended local file access or command execution if the referenced tool is modified, expanded, or behaves unsafely.

Static analysis

No suspicious patterns detected.