korean-report-style
Pass
Audited by Gen Agent Trust Hub on Nov 2, 2026
Risk Level: SAFE
Full Analysis
- [COMMAND_EXECUTION]: The skill includes Python utility scripts (
assets/lint.py,assets/structure.py,assets/parity.py,assets/morph.py) designed to be executed by the agent to analyze local documents. These scripts perform text processing, regex matching, and morphological analysis. They do not exhibit dangerous behaviors such as privilege escalation or network exfiltration. - [INDIRECT_PROMPT_INJECTION]: The skill is designed to process user-provided Korean text for stylistic editing. While this involves processing untrusted data, the skill's logic is constrained to linguistic linting and structural verification based on predefined rules, which mitigates the risk of executing malicious instructions embedded in the processed documents.
- [EXTERNAL_DOWNLOADS]: The morphological analysis script (
assets/morph.py) optionally utilizeskiwipiepy, a standard and well-known Korean natural language processing library. The skill does not attempt to download or execute code from untrusted remote sources.
Audit Metadata