ClawHub
Back to skill

Security audit

Lokuli Booking

Security checks for vulnerabilities and agentic risk

Overview

This skill is a straightforward local-service search and booking guide, with disclosed third-party booking and payment flow and explicit user confirmation before booking.

Install only if you want your agent to use Lokuli for local service searches and bookings. Confirm provider, price, time, and contact details before any booking or payment link is created, and do not use it for generic advice unless you intend to search for or schedule a real service.

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 (2)

Vague Triggers

Medium
Confidence
96% confidence
Finding
The skill description is written broadly enough to trigger on a very wide range of local-service requests, which can cause the agent to activate this external booking workflow in situations where the user may only be seeking general advice, recommendations, or informational help. Because the skill reaches a third-party booking/payment flow and may collect personal data, overbroad activation increases the chance of unintended data sharing, unnecessary tool use, and confusion about user intent.

Autonomous Decision Making

Medium
Category
Excessive Agency
Content
## 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
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.

Static analysis

No suspicious patterns detected.