ClawHub
Back to skill

Security audit

Google Docs

Security checks across malware telemetry and agentic risk

Overview

This is a disclosed Google Docs integration that can read and modify documents through Maton-managed OAuth, with no evidence of hidden or unrelated behavior.

Install this only if you are comfortable letting your agent access Google Docs through Maton. Use the narrowest intended connection, confirm document IDs and account selection before use, and review any create, update, delete, or connection-management action before it runs.

SkillSpector

By NVIDIA
Vulnerability Patterns
  • Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
  • 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)

Vague Triggers

Medium
Confidence
83% confidence
Finding
The instruction to use this skill for "ANY Google Docs request" is overly broad and can cause automatic routing of many tasks to a powerful connector with read, write, and destructive operations. In an agent setting, broad trigger conditions increase the chance of unintended invocation and unnecessary exposure of document data or state-changing capabilities.

VirusTotal

64/64 vendors flagged this skill as clean.

View on VirusTotal

Static analysis

No suspicious patterns detected.