Back to skill

Security audit

Workspace MCP免费版

Security checks across malware telemetry and agentic risk

Overview

This skill is a Google Workspace reader, but it asks users to install a third-party MCP package with broad Google data access and persistent local OAuth credentials without enough safety scoping.

Review before installing. Use this only on a trusted machine/account, confirm the Google OAuth consent scopes before approving, avoid shared or remote hosts unless you understand the token-copying risk, choose Drive download paths carefully, and remove or revoke the stored OAuth credentials when finished.

SkillSpector

By NVIDIA
Vulnerability Patterns
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
  • Excessive AgencyUnrestricted Tool Access, Autonomous Decision Making, Scope Creep
Findings (2)

Missing User Warnings

Medium
Confidence
91% confidence
Finding
The skill explicitly stores OAuth credentials in a local user directory and supports downloading Drive files to arbitrary local paths, but it does not present a clear safety warning about local persistence of sensitive data. In an agent environment, this can lead users to unknowingly expose mailbox, calendar, and document data on shared hosts or insecure filesystem locations.

Credential Access

High
Category
Privilege Escalation
Content
---
# Google Workspace MCP 免费版

通过 `@presto-ai/google-workspace-mcp` 以OAuth登录访问Google Workspace,无需在Google Cloud Console创建项目或下载client_secret.json。首次使用时弹出浏览器完成Google授权,凭证保存在 `~/.config/google-workspace-mcp/`.
免费版聚焦基础读取场景,提供邮件检索、日程查看、文件下载与文档表格文本提取能力。所有工具通过同一OAuth凭证访问,无需为每个服务单独配置.
## 输入格式
Confidence
93% confidence
Finding
secret.json

VirusTotal

64/64 vendors flagged this skill as clean.

View on VirusTotal

Static analysis

No suspicious patterns detected.