Security audit
Security checks for vulnerabilities and agentic risk
This is a route and travel review skill that uses disclosed map, route, POI, and weather data through a stated dependency without evidence of hidden execution, persistence, or data theft.
Before installing, be aware that useful results require sharing route or travel details such as origin, destination, timing, preferences, and potentially weather or POI context with the dependent map-service skill. Avoid providing unnecessary personal details, and request another language if Chinese output is not desired.
The skill is written as a direct instruction to the agent in Chinese and all examples/output formats are specified in Chinese, with no indication that the user may choose another language. This creates a language-policy concern because it implicitly constrains responses to a specific language without user opt-in.
The skill asks users for route planning and travel-evaluation inputs that inherently involve sensitive contextual data such as origin, destination, itinerary timing, and weather/POI lookups via another skill, but it does not clearly warn users about that data dependency in the user-facing flow. This can lead to uninformed disclosure of location and travel context to a downstream service, creating a privacy-transparency issue even if no direct exfiltration logic is present.
No suspicious patterns detected.
