ClawHub
Back to skill

Security audit

Book Transmission

Security checks for vulnerabilities and agentic risk

Overview

This skill is a small booking integration, but it can send contact details to an external service and create bookings without clear consent instructions.

Review this skill before installing. It appears focused on transmission-service booking and does not show malicious code, but users should expect their name, email, and phone number to be sent to Lokuli or a downstream provider when creating a booking. The skill should ideally require a clear confirmation before sharing contact details or submitting an appointment.

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 includes a create_booking action that sends customer name, email, and phone number to an external MCP service, but it does not instruct the agent to warn the user or obtain explicit consent before transmitting that personal data. This is dangerous because users may not realize their contact details are being shared with a third party, creating privacy, compliance, and trust risks.

Vague Triggers

Medium
Confidence
92% confidence
Finding
The trigger text is broad enough that the skill may activate for generic 'transmission' requests without clear user intent, increasing the chance of unintended use of an external booking workflow. In this skill, unintended invocation is more risky because it can lead the agent into searching third-party services and progressing toward booking actions that may involve personal data handling.

Static analysis

No suspicious patterns detected.