The Agent Skills Directory

[SAFE]: The skill consists entirely of markdown documentation and code examples intended for developer reference. It provides information on the uni-app framework's project structure, lifecycle, and component usage.
[CREDENTIALS_UNSAFE]: Example configurations for manifest.json and networking headers use standard placeholders (e.g., "appid": "wx...", "Authorization": "Bearer token"). There are no hardcoded secrets or sensitive credentials in the skill.
[DATA_EXFILTRATION]: Although the skill documents APIs for network requests (uni.request) and file system operations (uni.getFileSystemManager), these are presented as framework capabilities for the developer to implement. No automated or hidden exfiltration logic exists within the skill itself.
[OBFUSCATION]: No techniques such as Base64 encoding of commands, zero-width characters, or homoglyph attacks were found in the provided files.
[COMMAND_EXECUTION]: The skill does not include any scripts or instructions that trigger arbitrary shell commands or use dynamic context injection patterns.

uni-app