write-korean-essay
Warn
Audited by Gen Agent Trust Hub on Aug 27, 2026
Risk Level: MEDIUMCOMMAND_EXECUTIONDYNAMIC_EXECUTION
Full Analysis
- [COMMAND_EXECUTION]: The skill instructs the agent to execute shell commands using
uv runto perform linting and outlining tasks on generated essay files. - [DYNAMIC_EXECUTION]: The instructions define a dynamic path variable
CORE_SKILL_DIRpointing to a sibling directory (natural-korean) and execute scripts (lint.py,outline.py) from that location. Because these scripts are not provided within the skill package, they constitute an external, unverifiable execution dependency.
Audit Metadata