ClawHub
Back to skill

Security audit

Book Pool Service

Security checks for vulnerabilities and agentic risk

Overview

This is a straightforward pool-service booking skill that contacts Lokuli and uses customer contact details when creating a booking.

Before installing, be comfortable with the agent contacting Lokuli and sending customer contact details when creating a booking. Ask the agent to confirm the provider, service, time slot, and contact information before it calls create_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
Category
Not specified by scanner
Confidence
96% confidence
Finding

The booking flow collects and transmits personal contact information including name, email, and phone number to an external MCP endpoint, but the skill provides no user-facing warning, consent step, or disclosure that this data will be shared with Lokuli. In a booking context, this makes accidental over-collection and third-party disclosure of PII more likely, especially if the skill is auto-invoked from a broad trigger.

Content

No source excerpt is available for this finding.

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
95% confidence
Finding

The manifest description includes broad trigger language such as handling any 'pool-service service request,' which can cause the skill to activate in situations broader than a narrowly scoped booking intent. Overbroad activation increases the chance that the agent will invoke this skill unnecessarily and begin a workflow that searches for providers or solicits booking details when the user did not clearly intend to use this third-party service.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.