Back to skill

Security audit

Book Catering

Security checks for vulnerabilities and agentic risk

Overview

This catering-booking skill is purpose-aligned but needs review because it can send customer contact details to an external booking service and lacks clear confirmation boundaries.

Review this skill before installing. It appears to do what it claims, but users should confirm that they want Lokuli to receive their contact details and should explicitly approve any booking before it is created.

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 skill instructs use of an external MCP endpoint for search and booking and includes example transmission of customer name, email, and phone number, but provides no user-facing warning or consent step. This creates a real risk of sending personal contact data to a third-party service or creating bookings without the user clearly understanding that external processing will occur.

Content

No source excerpt is available for this finding.

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
95% confidence
Finding

The trigger description is broad enough to activate on vague catering-related requests without clearly constraining when the skill should engage. In a booking skill that can initiate external searches and eventual reservations, overbroad activation increases the chance of unintended tool use, mistaken booking workflows, or premature collection/transmission of user data.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.