Back to skill

Security audit

Book Dog Trainer

Security checks for vulnerabilities and agentic risk

Overview

This skill is a small, disclosed dog-trainer booking helper, with privacy and trigger-scope caveats but no evidence of hidden or malicious behavior.

Install only if you are comfortable using Lokuli's external service to search and book dog-trainer appointments. Before completing a booking, confirm the provider, time, price if available, and exactly which contact details will be sent.

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
90% confidence
Finding

The trigger text is broad enough to activate on generic dog-trainer-related requests without clearly constraining scope to explicit booking intent. That can cause the skill to engage prematurely, leading users into an external booking workflow and possible data disclosure or unintended actions when they only wanted general information.

Content

No source excerpt is available for this finding.

Missing User Warnings

Medium
Category
Not specified by scanner
Confidence
96% confidence
Finding

The skill includes a booking flow that sends personal information such as name, email, and phone number to an external MCP endpoint, but it does not warn the user or require explicit informed consent at the skill description level. This creates a privacy and trust risk because users may not realize their contact data will be transmitted to a third-party service.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.