ClawHub
Back to skill

Security audit

Lokuli Booking

Security checks for vulnerabilities and agentic risk

Overview

This skill is a coherent service-booking helper that can share contact details and create payment checkout links, but it requires user confirmation before booking.

Install only if you are comfortable using Lokuli's external MCP service to search providers, share booking contact details, and generate Stripe checkout links. Review provider, service, time, and price before approving any booking or completing payment.

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
  • 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
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
Findings (4)

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
97% confidence
Finding

The trigger phrase 'any local service request' is overly broad and can cause the skill to activate for a wide range of user intents beyond narrowly scoped booking tasks. In a skill that can initiate real-world service bookings and payment flows, over-triggering increases the chance of unintended data sharing, confusing delegation, or the user being pushed into an external transaction path without sufficiently clear consent.

Content

No source excerpt is available for this finding.

Missing User Warnings

Medium
Category
Not specified by scanner
Confidence
97% confidence
Finding

The skill states that create_booking returns a Stripe checkout URL for payment, but the workflow does not explicitly warn that this initiates a payment flow that may result in real-world charges. In the context of booking real services, failing to foreground payment implications can mislead users and increase the risk of accidental financial commitment.

Content

No source excerpt is available for this finding.

Missing User Warnings

Medium
Category
Not specified by scanner
Confidence
97% confidence
Finding

The skill states that create_booking returns a Stripe checkout URL for payment, but the workflow does not explicitly warn that this initiates a payment flow that may result in real-world charges. In the context of booking real services, failing to foreground payment implications can mislead users and increase the risk of accidental financial commitment.

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.