Google Workspace Automation

• Outcome: Pass
• Latest audit: May 28, 2026, 10:11 AM
• Version:
  0.1.0

Overview

This skill is a local Google Workspace automation planner that reads a user-supplied JSON file and writes a plan, with no evidence of hidden execution, credential use, network access, or persistence.

Install if you are comfortable with a local planning helper that reads a JSON requirements file and writes a generated plan. Use a dedicated project/output directory, do not point input at sensitive files, and avoid output paths where overwriting would matter.

SkillSpector

By NVIDIA

Vulnerability Patterns

• MCP Least Privilege: Underdeclared Capability, Wildcard Permission, Missing Permission Declaration
• Prompt Injection: Instruction Override, Hidden Instructions, Exfiltration Commands
• Data Exfiltration: External Transmission, Env Variable Harvesting, File System Enumeration
• Privilege Escalation: Excessive Permissions, Sudo/Root Execution, Credential Access
• Supply Chain: Unpinned Dependencies, External Script Fetching, Obfuscated Code

Findings (1)

Lp3

Medium

• Category: MCP Least Privilege
• Confidence: 88% confidence
• Finding: The skill instructs use of local bundled resources (`scripts/plan_workspace_automation.py` and `references/workspace-guide.md`), which implies file read capability and likely file write/output generation, but it does not explicitly declare any permissions. Undeclared capabilities weaken transparency and policy enforcement, making it easier for a caller to invoke a skill with broader filesystem access than expected and reducing auditability for an automation tool that already handles sensitive Google Workspace workflows.

VirusTotal

66/66 vendors flagged this skill as clean.