brd-interviewer
Pass
Audited by Gen Agent Trust Hub on Mar 7, 2026
Risk Level: SAFEPROMPT_INJECTION
Full Analysis
- [PROMPT_INJECTION]: The skill has an indirect prompt injection surface (Category 8) because it processes stakeholder input and incorporates it into a business requirement document.
- Ingestion points: The skill captures user input at Phase 0 ('原始意图') and uses it as the foundational requirement for the document.
- Boundary markers: The instructions do not specify the use of delimiters or instructions to ignore potential commands within the user-provided 'raw intent'.
- Capability inventory: The skill is authorized to generate and save Markdown files to the local project directory.
- Sanitization: There is no explicit mechanism described to sanitize or validate the user's business idea before processing it through the interview logic or writing it to the final BRD document.
Audit Metadata