Security audit
Security checks for vulnerabilities and agentic risk
This is a straightforward travel route planning skill with expected external travel/search lookups and no evidence of hidden execution, persistence, credential access, or destructive behavior.
Installers should treat this as a normal travel-planning helper. Before using live travel/search integrations, avoid sharing unnecessary personal details and confirm before taking any real booking or purchase action.
The skill description is broadly phrased and could activate on many ordinary travel-planning requests without clear boundaries on when it should or should not be used. Over-broad invocation increases the chance of unnecessary tool use and unintended sharing of user itinerary details with downstream services.
This section instructs the agent to use travel and web_search tools to retrieve flights, hotels, weather, and traffic data, but it does not disclose that user itinerary information may be transmitted to external services. That creates a privacy and consent risk, especially when destinations, dates, and travel preferences may reveal sensitive personal plans.
The integration section says the skill obtains flight, hotel, ticket, and transport information from another skill and external search, but it omits any warning about third-party access or handling of travel-related personal data. In the travel context, booking-related queries can expose location history, future movements, and budget/preferences, making the omission materially relevant.
The entire skill file is written in Chinese and presents all guidance exclusively in that language, with no indication that the user can choose another language or that the skill is intended only for Chinese-speaking users. This creates a natural-language locale policy concern because it effectively imposes a language choice without opt-in or justification.
This code file contains user-facing documentation and output strings exclusively in Chinese, including the script description and usage expectations. That can violate a language/locale policy when no user opt-in or explicit region-specific justification is provided.
The skill description and instructions are entirely in Chinese, which effectively imposes a language/locale on the user without any opt-in or stated regional justification. This can violate language-choice policy when the skill is intended for general use rather than a clearly documented Chinese-only audience.
No suspicious patterns detected.
