ClawHub
Back to skill

Security audit

Book Blowout

Security checks for vulnerabilities and agentic risk

Overview

This is a simple salon blowout booking skill; it uses an external booking endpoint and contact details in a way that matches its stated purpose, but users should confirm before sending personal information.

Before installing, understand that this skill can contact Lokuli to search salons and create a booking using your name, email, and phone number. Only proceed with a booking after reviewing the provider, time, and details, and confirm before sharing contact information.

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
Category
Not specified by scanner
Confidence
95% confidence
Finding

The trigger language is broad enough to activate on generic 'blowout' requests without sufficient disambiguation, which can cause the skill to run for unintended user intents. In a booking skill that can search providers and eventually collect or transmit booking details, mistaken activation increases the chance of unnecessary third-party data sharing or confusing the user into an unintended transaction flow.

Content

No source excerpt is available for this finding.

Missing User Warnings

Medium
Category
Not specified by scanner
Confidence
95% confidence
Finding

The skill documents transmission of customerName, customerEmail, and customerPhone to an external MCP endpoint for booking, but it does not instruct the agent to warn the user or obtain explicit consent before collecting and sending that personal data. In this context, the omission is more dangerous because the skill directly facilitates booking with a third party, making unintended privacy disclosure a realistic outcome.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.