ClawHub
Back to skill

Security audit

Gmail

Security checks across malware telemetry and agentic risk

Overview

This Gmail skill is broad and powerful, but its Gmail access is disclosed, purpose-aligned, and includes confirmation rules for state-changing actions.

Install this only if you intend to let OOMOL-connected tooling read and manage your Gmail account. Review payloads carefully before approving any send, delete, trash, filter, forwarding, label, or settings change, and only run the first-time CLI install or auth flow if you trust OOMOL.

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
93% confidence
Finding
The skill declares it should be used for ANY Gmail-related request, which can override more context-specific handling and funnel both low-risk and high-risk operations through a broad-capability skill. Because this skill includes read, write, and destructive Gmail actions, an over-broad trigger increases the chance an agent invokes powerful mailbox operations when a narrower or safer path would be more appropriate.

VirusTotal

64/64 vendors flagged this skill as clean.

View on VirusTotal

Static analysis

No suspicious patterns detected.