智慧旅行预订

• Outcome: Review
• Latest audit: May 29, 2026, 9:29 PM
• Version:
  1.0.0

Overview

This hotel booking skill appears incomplete and overstates real search and booking capabilities, but I found no evidence of secret theft, persistence, or destructive behavior.

Treat this as a prototype, not a working hotel booking tool. Do not rely on it for prices, availability, room details, or reservations until real provider integrations, dependencies, privacy disclosure, and explicit booking confirmation gates are added.

SkillSpector

By NVIDIA

Vulnerability Patterns

• Trigger Abuse: Overly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
• MCP Tool Poisoning: Hidden Instructions, Unicode Deception, Parameter Description Injection
• Prompt Injection: Instruction Override, Hidden Instructions, Exfiltration Commands
• Data Exfiltration: External Transmission, Env Variable Harvesting, File System Enumeration
• Privilege Escalation: Excessive Permissions, Sudo/Root Execution, Credential Access

Findings (2)

Tp4

High

• Category: MCP Tool Poisoning
• Confidence: 95% confidence
• Finding: The skill claims real multi-platform hotel aggregation, room querying, and booking support, but the analysis indicates there is no actual data-source integration and core functions return empty results. This is dangerous because downstream agents or users may trust fabricated completeness or operational capability, leading to deceptive outputs, incorrect travel decisions, or unsafe automation assumptions.

Vague Triggers

Medium

• Confidence: 89% confidence
• Finding: The trigger condition activates on generic hotel-search requests, which can cause the skill to run in situations where the user did not ask for cross-platform aggregation or where another narrower skill should apply. Over-broad invocation increases the chance of unintended data access, user confusion, and prompt-routing abuse in agentic systems.

VirusTotal

64/64 vendors flagged this skill as clean.