soia-meta-prompt-clarity
Pass
Audited by Gen Agent Trust Hub on Aug 6, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: The skill focuses on natural language processing and prompt engineering. It includes explicit instructions to respect safety boundaries and provides a dedicated 'Mode C' workflow to disambiguate requests that might be misflagged by safety filters, rather than attempting to bypass them.
- [SAFE]: The skill defines clear input delimitation ('输入定界') using Markdown code blocks and quotes to ensure that data being processed is not interpreted as instructions by the agent.
- [SAFE]: External installation and dispatch instructions refer to the official vendor ecosystem ('soia-team'). These are standard administrative commands provided for user setup and do not represent unauthorized remote code execution.
- [SAFE]: The skill requires explicit user authorization before performing any high-risk actions such as file writing, deletion, or external tool dispatch.
Audit Metadata