The Agent Skills Directory

[COMMAND_EXECUTION]: The skill executes tree . /f via pwsh to map the existing wiki structure and identify where to place new content.
[PROMPT_INJECTION]: The skill is susceptible to indirect prompt injection because it processes content from local documentation to plan new wiki pages.
Ingestion points: Reads all files located under 設計文件, 功能需求, and 標準規範 directories.
Boundary markers: No explicit delimiters or instructions are used to separate the content of these files from the agent's instructions.
Capability inventory: The skill can execute shell commands (tree), read files, write new markdown and .order files, and perform git commit operations.
Sanitization: There is no evidence of sanitization or filtering applied to the documentation content before it is used to plan or write the wiki page.

create-new-wiki-page