ClawHub
Back to skill

Security audit

Subway Restaurant Agent

Security checks for vulnerabilities and agentic risk

Overview

This is a Markdown-only restaurant ordering workflow with disclosed Google Sheets logging, which is purpose-aligned but needs privacy-conscious setup.

Before installing, configure the Google Sheet with least-privilege access, avoid logging payment details or unnecessary customer notes, disclose order recordkeeping to customers where required, and set an internal retention policy for order and allergen-related data.

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
95% confidence
Finding

The skill explicitly instructs the agent to record all transactions to a connected Google Sheet, but provides no requirement to notify users, obtain consent, or limit what data is stored. In a WhatsApp ordering context, orders may contain personal data such as phone numbers, names, locations, allergen information, and purchase history, so silent external logging creates a meaningful privacy and data-governance risk.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.