The Agent Skills Directory

[SAFE]: The skill consists entirely of natural language instructions designed to guide an AI agent in linguistic refinement. It does not include any scripts, binaries, or configuration files.
[REMOTE_CODE_EXECUTION]: The instructions explicitly forbid downloading or installing external content at runtime, stating: "Never install or download another skill at runtime."
[DATA_EXFILTRATION]: No network operations, sensitive file path access, or credential harvesting patterns were identified. The skill's scope is limited to processing text within the agent's provided context.
[PROMPT_INJECTION]: The instructions do not contain patterns intended to bypass safety filters or override the underlying agent's core programming. The language is focused on task-specific constraints for Korean translation.
[DYNAMIC_CONTEXT_INJECTION]: No shell command execution patterns (using the !command syntax) were found in the skill metadata or body.

translating-korean