Back to skill

Security audit

Super Auto Body

Security checks for vulnerabilities and agentic risk

Overview

This skill is for auto-body booking, but it can send personal contact details to an external service and create bookings without clearly requiring user confirmation.

Review this skill before installing if you are comfortable with an external Lokuli MCP service receiving booking details. Use it only when you intend to search or book auto-body services, and confirm the exact provider, time, name, email, and phone number before allowing a booking request to 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)

Missing User Warnings

High
Category
Not specified by scanner
Confidence
97% confidence
Finding

The booking example shows collection and transmission of personal data including name, email, and phone number to an external Lokuli endpoint, but the skill documentation does not warn users or require explicit consent before sharing that information. In a booking context, this increases privacy and compliance risk because an agent may send sensitive contact details to a third party without the user's informed approval.

Content

No source excerpt is available for this finding.

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
96% confidence
Finding

The skill description includes broad trigger phrasing such as 'find auto-body near me' and 'any related service,' plus a large amount of irrelevant keyword-like text. This can cause overmatching in agent skill selection, leading the skill to activate on ambiguous user requests and route users into an external booking workflow they did not clearly intend.

Content

No source excerpt is available for this finding.