requirements-refiner
Pass
Audited by Gen Agent Trust Hub on Apr 28, 2026
Risk Level: SAFEPROMPT_INJECTION
Full Analysis
- [SAFE]: The skill demonstrates safe practices, including explicit requirements for data sources and warnings for professional advice in sensitive domains. It operates within its scope of allowed tools (WebSearch, WebFetch, Read, Write) to generate documentation.
- [PROMPT_INJECTION]: The skill possesses a surface for indirect prompt injection by ingesting untrusted data such as PRD documents and user-provided descriptions. This input guides subsequent tool use (WebSearch, WebFetch) without explicit sanitization.
- Ingestion points: User descriptions and PRD/planning documents (SKILL.md, Section 2).
- Boundary markers: None explicitly defined for ingested content.
- Capability inventory: WebSearch, WebFetch, Read, and Write tools.
- Sanitization: No specific sanitization or validation logic described for external documents.
Audit Metadata