The Agent Skills Directory

[COMMAND_EXECUTION]: The skill uses find and git log to identify missing or outdated translation files. These operations are restricted to specific documentation subdirectories within the repository.
[PROMPT_INJECTION]: The skill possesses a surface for indirect prompt injection (Category 8) because it processes untrusted content from documentation files.
Ingestion points: Reads the full content of English markdown files from docs/en/specifications, docs/en/issue, and docs/en/policy during the translation phase.
Boundary markers: Absent; the skill does not instruct the agent to use delimiters or ignore instructions embedded within the source documentation.
Capability inventory: The skill can execute shell commands (find, git) and perform file write operations to the docs/ko/ directory.
Sanitization: There is no validation or sanitization of the documentation content before it is parsed and translated by the agent.

sync-translations