ClawHub
Back to skill

Security audit

Book local services

Security checks for vulnerabilities and agentic risk

Overview

This skill coherently helps users search for and book local services through Lokuli, with external booking and contact-info sharing disclosed in the workflow and confirmation required before booking.

Before installing, be aware that this skill contacts Lokuli to search providers and may send your name, email, phone number, location, selected provider, service, and time slot when you approve a booking. Confirm pricing, provider, time, and contact details before allowing a booking or cart to be 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
Confidence
95% confidence
Finding
The skill description is broad enough to trigger on many generic local-service requests, which increases the chance of unintended activation in contexts where the user did not actually intend to invoke this booking workflow. Because the skill can progress toward searching providers and collecting user details, overbroad activation raises privacy and transaction-risk concerns even if the booking step itself requires confirmation.

Missing User Warnings

Medium
Confidence
98% confidence
Finding
The workflow instructs the agent to collect and transmit personal contact information (name, email, phone) to an external MCP service for booking, but it does not warn the user about this data sharing before collection. In a real-world booking context, silent transmission of PII to a third party creates meaningful privacy and consent risks.

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.