Back to skill

Security audit

Book Smog

Security checks for vulnerabilities and agentic risk

Overview

This skill is a narrow smog-check booking helper that uses a disclosed external MCP service and requires user confirmation before creating a booking.

Installers should expect this skill to contact Lokuli's MCP service when searching or booking smog appointments. Use it for appointment-finding or booking tasks, and avoid sending name, email, or phone details until you have selected a provider and approved the booking step.

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
  • Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
  • Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
Findings (1)

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
92% confidence
Finding

The trigger condition explicitly says it should activate on 'any smog-related request,' which is broader than the concrete booking use case and can cause the skill to run for informational, regulatory, or unrelated diagnostic queries. That increases the chance of inappropriate invocation, unnecessary data collection, and premature progression into booking/search flows against an external MCP service.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.