ClawHub
Back to skill

Security audit

Gmail 1.0.6

Security checks across malware telemetry and agentic risk

Overview

This Gmail skill is coherent, but it gives an agent sensitive email access and mailbox-changing powers without clear confirmation guardrails.

Review before installing. Use only if you trust Maton with access to the connected Gmail account, and configure your agent to ask for explicit confirmation before reading sensitive threads or performing any send, draft-send, label change, trash/delete, or connection-deletion action.

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

Medium
Confidence
82% confidence
Finding
The skill documents state-changing operations like sending mail, trashing messages, sending drafts, and deleting connections without emphasizing confirmation, user intent validation, or reversibility. In an agent setting, that increases the risk of accidental destructive or privacy-impacting actions being taken on behalf of the user.

VirusTotal

66/66 vendors flagged this skill as clean.

View on VirusTotal

Static analysis

Detected: suspicious.exposed_resource_identifier

Example code exposes a concrete connection_id instead of a placeholder.

Critical
Code
suspicious.exposed_resource_identifier
Location
SKILL.md:103