Security audit

National Standard Monitor Skill

Security checks across malware telemetry and agentic risk

Overview

This skill does what it claims: it checks China national standard updates from the official site and stores reports or PDFs in a user-chosen directory.

Install this if you want automated tracking and optional downloads of national standards. Use a dedicated working directory because the skill will create or update JSON metadata, reports, snapshots, and PDF files there, and downloads may contact openstd.samr.gov.cn repeatedly with built-in pauses.

SkillSpector

By NVIDIA

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 (2)

Lp3

Medium

Category: MCP Least Privilege
Confidence: 92% confidence
Finding: The skill instructs the agent to run a Python script that performs network access and reads/writes local files, but the metadata declares no corresponding permissions. This mismatch weakens policy enforcement and user visibility, making it easier for a skill to perform filesystem and network operations without clear consent boundaries.

Missing User Warnings

Low

Confidence: 81% confidence
Finding: The skill states that it will automatically create and update local files such as JSON metadata and downloaded PDFs, but it does not clearly warn the user about filesystem modifications at the point of use. Even if the writes are expected for the feature, implicit file creation can surprise users and cause unintended changes in sensitive or shared directories.

VirusTotal

65/65 vendors flagged this skill as clean.

View on VirusTotal

Static analysis

No suspicious patterns detected.