ClawHub
Back to skill

Security audit

Gmail Sender

Security checks for vulnerabilities and agentic risk

Overview

This is a small Gmail email-sending skill whose network and credential use are expected for its stated purpose, with a privacy-warning gap users should understand.

Before installing, use a dedicated least-privilege Gmail account or app password where possible, avoid sending secrets or regulated data unless your policy allows Google/Gmail handling, and be aware that scheduled cron use can send messages automatically after you configure it.

A.I.G

Vulnerability Patterns
  • Skill Instruction HijackingAlters the agent's session goals or safety constraints when the skill loads
  • Agent Memory PoisoningWrites attacker-controlled rules into memory that affect later sessions
  • Remote Payload Retrieval and ExecutionFetches external code whose behavior can change after review
  • Embedded Malicious CodeShips malicious scripts inside the skill and executes them locally
  • Unauthorized Access and Privilege EscalationObtains permissions beyond the task's legitimate needs

SkillSpector

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
Category
Not specified by scanner
Confidence
92% confidence
Finding

The skill instructs users to send email via Gmail SMTP but does not clearly warn that message bodies, recipient addresses, subject lines, and sender/account metadata will be transmitted to Google and may be logged or retained under Google’s service policies. In a reusable automation skill, this omission can cause users to unknowingly route sensitive alerts, reports, or personal data to a third party, making the issue a genuine information disclosure risk through insufficient transparency rather than an implementation flaw.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.