Security audit
Security checks for vulnerabilities and agentic risk
This is a markdown-only travel planning skill with no evidence of hidden execution, persistence, data exfiltration, or destructive behavior.
Reasonable to install for travel planning assistance. Users should still confirm current visa, entry, flight, hotel, cancellation, and pricing details with official providers before making bookings or sharing document information.
The skill description is broad enough to trigger on a wide range of generic travel-planning and management requests, which can cause over-invocation and unintended delegation. In an agent system, this increases the chance the skill is selected outside its narrowly intended scope, exposing users to incorrect actions, unnecessary data sharing, or unsafe downstream booking/document workflows.
The usage examples are phrased as broad natural-language requests without qualifiers, so they reinforce permissive matching for many travel-related prompts. This can bias routing toward this skill even when the user only needs general advice, making accidental activation and inappropriate handling more likely.
This markdown skill file presents all guidance in Chinese and does not indicate that the user can choose another language or that the skill is intentionally limited to a Chinese-speaking audience. Under the stated policy, forcing a specific language without user opt-in is a natural-language policy concern.
This markdown skill forces a specific language for all users through its headings and guidance, but it does not indicate that Chinese is optional or that the skill is intended only for a Chinese-speaking audience. The policy requires either user opt-in for language/locale constraints or clear documentation justifying the constraint.
The entire skill content is written in Chinese, with no indication that the user can choose another language or that the skill is intentionally limited to Chinese-speaking users. Under the policy, forcing a specific language without user opt-in is a natural-language policy concern.
No suspicious patterns detected.
