The Agent Skills Directory

[SAFE]: The skill instructs the agent to adjust its communication style and provide more context. It does not perform network operations, execute shell commands, or access sensitive system files.
[INDIRECT_PROMPT_INJECTION]: The skill utilizes local files (GLOSSARY.md and GLOSSARY-MAP.md) to inform its response style and terminology. While these are external data sources, they represent standard project documentation and are processed within the agent's context for formatting purposes, presenting no significant risk.

wait-what