Back to skill

Security audit

奢华邮轮体验

Security checks for vulnerabilities and agentic risk

Overview

This skill appears to be a disclosed remote MCP integration for searching luxury cruise products, with no local code, persistence, or hidden installation behavior found.

Install only if you are comfortable sending cruise search queries to the listed CruiseSkillBridge/olavacations remote MCP gateway. Avoid including secrets, payment details, passport data, or confidential personal information in prompts or filters unless the publisher provides clear privacy and retention terms.

Vulnerability Patterns
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • 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
Confidence
95% confidence
Finding
The skill instructs users or agents to send POST requests containing input data to an external endpoint, but it does not clearly warn that user-provided content will leave the local trust boundary. Even though the example uses httpbin and claims the URL may later be replaced by a gateway, the documentation normalizes external transmission without disclosure, consent guidance, or data-handling constraints, creating a real risk of unintended data exfiltration.

Static analysis

No suspicious patterns detected.