ClawHub
Back to skill

Security audit

Book Cake

Security checks for vulnerabilities and agentic risk

Overview

This skill is purpose-aligned for cake booking, but it can send personal contact details to a third-party booking service and create bookings without clearly requiring user confirmation.

Review this skill before installing. It appears to do what it says, but you should only use it when you are comfortable sending cake search, booking details, and customer contact information to Lokuli, and the agent should confirm before creating any booking or sharing personal details.

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
  • Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
  • Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
Findings (2)

Missing User Warnings

High
Confidence
97% confidence
Finding
The skill describes collecting and transmitting customer name, email, and phone number to an external Lokuli booking endpoint but does not warn the user that their personal data will leave the current system. This creates a meaningful privacy and consent risk, especially because the skill is designed to perform a real booking transaction with a third-party service.

Vague Triggers

Medium
Confidence
94% confidence
Finding
The trigger language is broad enough to activate on generic cake-related requests such as finding or booking cake, which can cause the skill to engage in situations where the user did not clearly intend to use this external booking workflow. Because the skill connects to a third-party MCP service and can progress toward booking actions, over-triggering increases the chance of unnecessary data sharing or unintended transactional actions.

Static analysis

No suspicious patterns detected.