The Agent Skills Directory

[COMMAND_EXECUTION]: The script scripts/_lib.js utilizes execFileSync to run npm root -g. This is used to programmatically determine the location of globally installed Node.js packages on the host system.
[COMMAND_EXECUTION]: SKILL.md contains a shell script template that executes Node.js code via stdin (`node --input-type=module
<<'JS'). This allows the agent to execute a block of JavaScript directly to interface with the lck-analytics` library.
[EXTERNAL_DOWNLOADS]: The skill instructions in SKILL.md direct the user to perform a global installation of the lck-analytics package using npm install -g. This introduces an external dependency that is downloaded and executed on the local machine.
[PROMPT_INJECTION]: The skill exhibits an indirect prompt injection surface (Category 8) by ingesting data from external sources.
Ingestion points: Data is fetched from Riot Games' live stats APIs (feed.lolesports.com) and processed from local Oracle-style CSV files via scripts/sync-oracle.js.
Boundary markers: No explicit delimiters or instructions to ignore embedded commands are present in the processing scripts.
Capability inventory: The skill possesses the ability to execute shell commands (execFileSync), write to the file system (writeJson), and perform network operations via the lck-analytics package.
Sanitization: Data is parsed as JSON or CSV, but no specific sanitization or filtering of the content for natural language instructions is implemented before processing.

lck-analytics