ClawHub
Back to skill

Security audit

Gmail Lead Desk

Security checks across malware telemetry and agentic risk

Overview

This is a disclosed Gmail workflow skill that uses AISA/Composio OAuth to read, draft, send after confirmation, and archive email, with no install-time code or hidden behavior found.

Install only if you are comfortable connecting Gmail through AISA/Composio with an API key. Use an account you are authorized to manage, protect AISA_API_KEY, avoid placing unnecessary customer data or secrets in natural-language prompt text, and carefully review every send, attachment, label, archive, or cleanup confirmation.

SkillSpector

By NVIDIA
Vulnerability Patterns
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
  • Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
  • Excessive AgencyUnrestricted Tool Access, Autonomous Decision Making, Scope Creep
Findings (1)

Missing User Warnings

Low
Confidence
82% confidence
Finding
The documentation repeatedly uses a real-looking email address as the `user_id` in API requests, which can normalize sending personally identifiable information to a third-party gateway without any minimization or privacy guidance. In a Gmail/OAuth integration context, `user_id` becomes a correlation handle across auth and execution flows, so encouraging use of an email address increases unnecessary exposure of personal data.

VirusTotal

64/64 vendors flagged this skill as clean.

View on VirusTotal

Static analysis

No suspicious patterns detected.