ClawHub
Back to skill

Security audit

Lokuli Service Booking

Security checks for vulnerabilities and agentic risk

Overview

This is a coherent service-booking skill, but users should understand that booking requires sharing contact, location, and payment-flow data with external services.

Before installing, be aware that this skill connects to Lokuli's external MCP service and may use your ZIP code, service request, selected time, name, email, and phone to create a real-world booking and payment checkout. Only proceed when you intend to search or book a local service, and confirm details before any booking is created.

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
  • Excessive AgencyUnrestricted Tool Access, Autonomous Decision Making, Scope Creep
  • 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
Findings (3)

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
90% confidence
Finding

The trigger description is broad enough to activate on many generic local-service requests, which can cause the agent to route users into an external booking workflow when they may only want information or recommendations. In this skill, unintended invocation is more dangerous because it can lead to collection and transmission of location and personal contact data to a third-party booking and payment stack.

Content

No source excerpt is available for this finding.

Missing User Warnings

Medium
Category
Not specified by scanner
Confidence
95% confidence
Finding

The workflow and rules describe collecting name, email, phone, ZIP code, and generating a Stripe checkout, but they do not clearly warn the user that this data will be sent to external providers. In a real-world booking context, lack of transparent disclosure undermines informed consent and increases privacy and data-sharing risk.

Content

No source excerpt is available for this finding.

Autonomous Decision Making

Medium
Category
Excessive Agency
Confidence
75% confidence
Finding

Skill enables autonomous high-impact decisions without human-in-the-loop verification. Critical operations (destructive commands, financial transactions, data deletion) should require explicit user confirmation.

Content

Scanner excerpt · SKILL.md (reported line 190)May include surrounding context.

md
## Rules

- **Never book without confirmation** — Always get explicit approval
- **Show pricing upfront** — Use get_pricing_estimates if needed
- **Collect required info** — Name, email, phone before booking
- **Default to user's ZIP** — If known from context

Static analysis

No suspicious patterns detected.