The Agent Skills Directory

[SAFE]: The skill's primary function is style and terminology analysis, which is conducted locally using markdown files in the references directory.
[EXTERNAL_DOWNLOADS]: Reference files include links to trusted entities such as the National Institute of Korean Language (korean.go.kr), Sejong University, and Kakao Enterprise. These links are for informational policy reference and do not involve executable content.
[PROMPT_INJECTION]: The skill represents a surface for indirect prompt injection as it processes untrusted external documents.
Ingestion points: Document content loaded via the Read tool or provided in the conversation context.
Boundary markers: Absent; there are no specific instructions for the agent to ignore commands within the analyzed text.
Capability inventory: The skill uses the Write and Edit tools to modify files based on its analysis.
Sanitization: No validation of document content is performed prior to processing. Note: This risk is considered safe/low given the specific utility of the skill.
[SAFE]: No obfuscation, persistence mechanisms, or privilege escalation techniques were identified in the instruction set or examples.

style-guide