ClawHub
Back to skill

Security audit

Google Chat

Security checks for vulnerabilities and agentic risk

Overview

This skill provides disclosed read-only access to Google Chat through OOMOL, with no evidence of hidden persistence, destructive actions, or data exfiltration.

Install this only if you are comfortable letting an agent use your OOMOL-connected Google Chat account to read spaces and messages you request. Review OOMOL's CLI install and OAuth connection flow before first use, and be careful with prompts that ask the agent to retrieve sensitive workplace chats.

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 description says to use this skill for ANY Google Chat request and instead of calling the API directly, which creates an overly broad routing rule that can cause the agent to invoke this skill for nearly all Chat-related prompts without sufficient narrowing. In practice, this increases the chance of unnecessary tool use, unintended data access attempts, and expansion of the attack surface if a prompt merely mentions Google Chat in passing.

Static analysis

No suspicious patterns detected.