ClawHub
Back to skill

Security audit

Book Auto

Security checks for vulnerabilities and agentic risk

Overview

This skill is a straightforward auto-service booking helper that uses a disclosed Lokuli MCP endpoint and requires user approval before creating a booking.

Before installing, be aware that using the booking flow may send your ZIP code and, if you proceed, your name, email, and phone number to Lokuli or its booking providers. Confirm provider details, price, time, and contact information before approving a booking.

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
  • Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
  • Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
Findings (1)

Vague Triggers

Medium
Confidence
95% confidence
Finding
The trigger description is very broad, covering nearly any automotive-service-related request such as finding a mechanic or booking detailing. Overly broad activation can cause the skill to engage in contexts the user did not intend, increasing the chance of unnecessary data collection, unwanted third-party contact, or premature booking workflow initiation.

Static analysis

No suspicious patterns detected.