The Agent Skills Directory

[COMMAND_EXECUTION]: The script scripts/vocab-check.js uses execSync to execute shell commands for installing the kuromojin package from the npm registry if it is not already present in the user's cache.
[DYNAMIC_EXECUTION]: The script scripts/vocab-check.js dynamically loads the kuromojin library at runtime from a computed file path (~/.cache/meiseki/vocab-deps/node_modules/kuromojin) using the createRequire function.
[INDIRECT_PROMPT_INJECTION]: The skill's primary function is to ingest and process untrusted user documents (<INPUT_MD>), which could contain adversarial instructions intended to influence the agent's behavior.
Ingestion points: The SKILL.md workflow reads untrusted document content in Step 2 (via textlint) and Step 3 (via vocab-check.js).
Boundary markers: The instructions do not use explicit delimiters or "ignore embedded instructions" warnings to isolate the document content from the agent's operational logic.
Capability inventory: The skill has the ability to execute shell commands (execSync in scripts/vocab-check.js) and perform file system operations.
Sanitization: No validation or escaping of the input document's content is performed before processing.

yorisoi