ClawHub
Back to skill

Security audit

Book Alignment

Security checks for vulnerabilities and agentic risk

Overview

This skill is a simple appointment-booking helper that discloses its external booking endpoint and expected contact fields, with no hidden code or persistence found.

Before installing, understand that searches and bookings go through Lokuli's external MCP service. Confirm the provider, time, and any personal contact details before creating 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
  • 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)

Vague Triggers

Medium
Confidence
94% confidence
Finding
The trigger scope is broad and ambiguous, using phrases like 'any alignment service request' without clear user-intent boundaries or confirmation requirements. This can cause the skill to activate on loosely related requests and route users into an external booking workflow unexpectedly, increasing the chance of unauthorized data sharing or unintended actions.

Missing User Warnings

Medium
Confidence
96% confidence
Finding
The booking flow collects and transmits personal contact information including name, email, and phone number to a third-party MCP endpoint, but the skill provides no user warning, consent language, or data-handling notice. In a booking context this makes accidental disclosure of sensitive personal data more likely, especially if the skill is auto-invoked from an ambiguous trigger.

Static analysis

No suspicious patterns detected.