writing-korean-clearly
Pass
Audited by Gen Agent Trust Hub on Aug 31, 2026
Risk Level: SAFENO_CODE
Full Analysis
- [PROMPT_INJECTION]: The skill provides instructions for adjusting Korean prose style. These instructions are confined to linguistic preferences and do not contain attempts to subvert agent safety protocols or ignore system boundaries.
- [DATA_EXFILTRATION]: No commands for network communication or local sensitive file access were identified.
- [OBFUSCATION]: The content is plain-text markdown with no evidence of encoding, zero-width characters, or homoglyph substitution.
- [REMOTE_CODE_EXECUTION]: The skill contains no package installation commands or remote script execution patterns.
- [NO_CODE]: This skill consists entirely of natural language instructions and contains no scripts or executable code.
Audit Metadata