agent-prompt-design
Pass
Audited by Gen Agent Trust Hub on Nov 2, 2026
Risk Level: SAFENO_CODE
Full Analysis
- [SAFE]: The skill consists entirely of Markdown text outlining prompt design principles and heuristics. There are no executable scripts, binaries, or automation instructions that could perform actions on a host system.
- [SAFE]: No network requests, external downloads, or remote code execution patterns were detected. References to companies like Anthropic and OpenAI, as well as academic papers, are for informational purposes and source attribution only.
- [SAFE]: No obfuscation, hardcoded credentials, or sensitive file path access was identified. The content is written in plain Japanese and English without hidden characters or encoded payloads.
- [SAFE]: The skill does not define any tools, permissions, or system-level configurations. It functions as a static guideline for human or agent review.
Audit Metadata