Back to skill

Security audit

Subway Agent Lite

Security checks for vulnerabilities and agentic risk

Overview

This is a small disclosed ordering-demo skill; its only notable consideration is that order logs may go to Google Sheets.

Before installing, confirm what customer/order fields will be written to Google Sheets and ensure the sheet is access-controlled. Avoid logging unnecessary personal details unless users and shop operators understand that storage path.

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
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 advertises direct logging to Google Sheets but does not disclose to users that order data may be transmitted to an external third-party service. Even for basic restaurant orders, this can expose personal or sensitive information such as names, contact details, and order history without informed consent or clear data-handling expectations.

Content

No source excerpt is available for this finding.