ClawHub
Back to skill

Security audit

Google Meet

Security checks for vulnerabilities and agentic risk

Overview

The skill is a coherent Google Meet connector, but one meeting-ending action is treated as safe to run directly.

Review before installing. The skill appears purpose-built for Google Meet through OOMOL, but users should require explicit confirmation before any action that creates, updates, or ends a meeting, especially `end_active_conference` until it is correctly tagged and scoped.

SkillSpector

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
90% confidence
Finding
The instruction to use this skill for ANY Google Meet request is overly broad and can cause an agent to invoke the skill reflexively whenever Google Meet is mentioned, even when the user's intent is informational, comparative, or better served by another tool. Because the skill includes both read and write capabilities, broad routing increases the chance of unnecessary connector access and, in ambiguous cases, accidental state-changing operations after weak or inferred confirmation.

Static analysis

No suspicious patterns detected.