The Agent Skills Directory

[SAFE]: The skill's instructions and operations were analyzed across all ten threat categories, and no security issues or malicious patterns were found.
[COMMAND_EXECUTION]: The skill requires running standard development commands such as npx vite and npx vite build. These are well-known commands used for building and serving web applications and are appropriate for the skill's stated purpose.
[EXTERNAL_DOWNLOADS]: The skill specifies the installation of vite as a development dependency. Vite is a trusted and widely-used open-source build tool from the official npm registry.
[PROMPT_INJECTION]: The skill processes external data (user game files) which presents a potential surface for indirect prompt injection.
Ingestion points: Reads content from existing index.html and script files in the game directory.
Boundary markers: Not explicitly defined; the agent processes code directly from source files.
Capability inventory: File system write operations to reorganize the project and subprocess execution via npx for verification.
Sanitization: No explicit sanitization of extracted code is mentioned, which is standard for local development tools designed to refactor existing user code.

convert-to-vite