ClawHub
Back to skill

Security audit

Book Yoga

Security checks for vulnerabilities and agentic risk

Overview

This is a simple yoga search and booking skill for Lokuli, with expected external booking data use but some consent and trigger-scope caveats.

Before installing, understand that booking through this skill may send your name, email, phone number, location or ZIP code, and selected time slot to Lokuli. Use it when you actually want Lokuli-powered yoga search or booking, and confirm the provider, time, and 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)

Missing User Warnings

High
Confidence
97% confidence
Finding
The create_booking example shows transmission of customer name, email, and phone number to an external MCP endpoint, but the skill description does not warn that personal data will be sent off-platform. This is dangerous because users may provide sensitive contact information without informed consent, creating privacy, compliance, and trust risks if data is shared unexpectedly.

Vague Triggers

Medium
Confidence
95% confidence
Finding
The trigger text is broad enough to activate on loosely related requests such as any yoga service request, which can cause the agent to invoke this skill when the user did not clearly ask to use Lokuli or make a booking. In a booking flow, over-triggering is risky because it can move a user from general information seeking into an external transaction context and may lead to unintended disclosure of location or booking details.

Static analysis

No suspicious patterns detected.