The Agent Skills Directory

[SAFE]: The skill consists entirely of natural language instructions and documentation. It does not include any executable scripts, binaries, or shell commands that would run on the host system.
[SAFE]: Network activity is limited to documentation links and asset images hosted on the author's official GitHub repository, which is consistent with the skill's purpose and distribution.
[SAFE]: Data access is restricted to reading a local reference file (../i18n/references/locale-knowledge.md) for cultural context. This file is part of the skill's own ecosystem and does not involve access to sensitive user files, environment variables, or credentials.
[SAFE]: Although the skill processes untrusted user input (words and sentences for definition), it lacks any tools or capabilities (such as file writing or command execution) that could be exploited via indirect prompt injection.

define