dbs-diagnosis
Pass
Audited by Gen Agent Trust Hub on Mar 20, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: The skill consists entirely of natural language instructions designed to establish a specific business consultancy persona and logical framework. It does not include any executable code or scripts.- [DATA_EXPOSURE]: The skill references a local knowledge base file (dbskill/知识库/推文挖掘_01_商业本体论.md) to inform its responses. This is a standard implementation for local data-augmented agents and does not pose a security risk.- [PROMPT_INJECTION]: The skill contains internal rules and behavioral constraints (e.g., 'non-negotiable axioms') used to define the AI's diagnostic logic. These are persona-shaping directives and do not attempt to bypass or override the platform's underlying safety filters.
Audit Metadata