ClawHub
Back to skill

Security audit

Google Meet

Security checks across malware telemetry and agentic risk

Overview

This is a disclosed Google Meet integration that uses Maton-managed OAuth; it can access sensitive meeting data, but the behavior is aligned with its stated purpose.

Install only if you trust Maton to broker OAuth access to your Google Meet account. Keep MATON_API_KEY private, avoid printing it in shared logs, select the intended connection when multiple Google accounts are available, and retrieve participants, recordings, or transcripts only when the user has a legitimate need and appropriate consent.

SkillSpector

By NVIDIA
Vulnerability Patterns
  • Excessive AgencyUnrestricted Tool Access, Autonomous Decision Making, Scope Creep
  • 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
Findings (2)

Vague Triggers

Medium
Confidence
82% confidence
Finding
The skill description says to use this skill whenever users want to interact with Google Meet, which is a broad invocation trigger without guardrails around sensitive actions. In a skill that can create spaces, end active conferences, and access participant, recording, and transcript data, vague routing increases the chance the agent invokes it without sufficient user confirmation or privacy review.

Missing User Warnings

Medium
Confidence
86% confidence
Finding
The documentation advertises access to meeting records, participants, recordings, and transcripts but does not place a clear privacy warning at the point of capability description. Because these data types can contain sensitive personal and organizational information, lack of a prominent warning may lead to over-collection or disclosure without informed user approval.

VirusTotal

65/65 vendors flagged this skill as clean.

View on VirusTotal

Static analysis

No suspicious patterns detected.