Back to skill

Security audit

UTravel

Security checks for vulnerabilities and agentic risk

Overview

UTravel is a travel-planning skill whose profile storage is disclosed and aligned with personalization, though users should understand what preferences are saved.

Before installing, be aware that the skill intends to remember travel preferences and user attributes for future recommendations. Use it only if you are comfortable with that personalization, and prefer an implementation that asks before saving, lets you review or delete stored preferences, and treats age or accessibility-related details carefully.

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
  • 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
  • Excessive AgencyUnrestricted Tool Access, Autonomous Decision Making, Scope Creep
Findings (1)

Missing User Warnings

Medium
Category
Not specified by scanner
Confidence
96% confidence
Finding

The skill explicitly states that it will store user profile attributes such as user type, travel style, preferences, and accommodation preferences for future personalization, but the specification does not present a clear user-facing notice, consent mechanism, retention policy, or deletion controls. Because these data points can reveal behavioral preferences and potentially sensitive inferences about age group or accessibility needs, silent persistence creates a privacy risk and can lead to unauthorized profiling or misuse if the stored data is later exposed or repurposed.

Content

No source excerpt is available for this finding.