idea
Pass
Audited by Gen Agent Trust Hub on Apr 1, 2026
Risk Level: SAFENO_CODE
Full Analysis
- [SAFE]: The skill consists of plain-text instructions in Korean designed to guide an AI agent in brainstorming UI/UX improvements.
- [NO_CODE]: There are no scripts, executables, or code blocks present in the skill that could be leveraged for malicious activity.
- [PROMPT_INJECTION]: The content does not contain any phrases attempting to override the agent's safety guidelines, bypass constraints, or reveal system prompts.
- [DATA_EXFILTRATION]: No network operations (curl, wget, fetch) or sensitive file path references (credentials, SSH keys, environment variables) were detected.
- [EXTERNAL_DOWNLOADS]: The skill does not reference or download any external packages or remote scripts.
Audit Metadata