The Agent Skills Directory

[COMMAND_EXECUTION]: The script scripts/vocab-check.js uses execSync to execute npm install at runtime. This command is used to dynamically install the kuromojin package into a local cache directory (~/.cache/meiseki/vocab-deps) if it is not already present on the system.
[DYNAMIC_EXECUTION]: The skill performs dynamic loading of code. In scripts/vocab-check.js, the script installs a dependency at runtime and then uses createRequire to load the module from a computed path in the user's home directory cache.
[EXTERNAL_DOWNLOADS]: The skill fetches several Node.js packages from the NPM registry (a well-known service). This includes the installation of textlint and associated rules via npx in the main workflow, and the kuromojin library via the vocabulary check script.
[INDIRECT_PROMPT_INJECTION]: The skill processes untrusted user-provided content which presents a potential injection surface.
Ingestion points: Arbitrary markdown files (<INPUT_MD>) are processed by the skill in SKILL.md (Steps 2 and 3).
Boundary markers: None identified. The content is passed directly to analysis tools without delimiters or warnings to ignore embedded instructions.
Capability inventory: The skill executes shell commands via npx and local Node.js scripts.
Sanitization: No explicit sanitization or validation of the input file content is performed before it is processed by the morphological analyzer.

yorisoi