Back to skill

Security audit

Book Pet Grooming

Security checks for vulnerabilities and agentic risk

Overview

This skill is a straightforward pet-grooming booking helper, but users should know it sends booking contact details to Lokuli when making an appointment.

Before installing, understand that booking through this skill may send your name, email, phone number, selected service, provider, and time slot to Lokuli. Confirm details before asking the agent to create a booking, and avoid providing more contact information than needed.

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
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)

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
92% confidence
Finding

The manifest says the skill triggers on specific examples and also on "any pet-grooming service request," which is an open-ended activation condition. This lacks clear constraints or exclusion examples, increasing the chance of unintended invocation for general discussion about pet grooming rather than booking intent.

Content

No source excerpt is available for this finding.

Missing User Warnings

Medium
Category
Not specified by scanner
Confidence
95% confidence
Finding

The skill includes a booking flow that transmits personal contact information to an external MCP endpoint but does not instruct the agent to warn the user, obtain consent, or minimize collected data first. In this context, the omission creates a meaningful privacy risk because users may not realize their name, email, and phone number will be sent to a third-party service.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.