ClawHub
Back to skill

Security audit

Gmail Draft Send

Security checks for vulnerabilities and agentic risk

Overview

The skill is narrowly aimed at sending Gmail drafts, but it tells the agent to send immediately without requiring a recipient/subject preview or explicit user confirmation.

Review this skill before installing if you use Gmail drafts for sensitive messages. It should only be used in workflows that already verify the draft ID, recipients, subject, and content, and that require clear user approval before sending.

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
93% confidence
Finding

The skill directs the agent to send an existing Gmail draft immediately, but provides no explicit user confirmation, preview, or irreversible-action warning before execution. Because sending email is an external side effect that cannot be undone, an agent could transmit sensitive, incorrect, or attacker-influenced content if the draft ID is wrong or the draft contents were manipulated upstream.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.