frontend-design
Pass
Audited by Gen Agent Trust Hub on Mar 26, 2026
Risk Level: SAFEPROMPT_INJECTIONEXTERNAL_DOWNLOADS
Full Analysis
- [PROMPT_INJECTION]: The skill processes untrusted user requirements to generate and modify frontend code, which creates a surface for indirect prompt injection.
- Ingestion points: Processes user-supplied requirements for components, pages, and applications as described in the
SKILL.mdcore logic. - Boundary markers: There are no explicit delimiters or 'ignore previous instructions' markers defined for the data interpolation.
- Capability inventory: The skill is linked to capabilities for source code modification (
self-modifying-code) and writing configuration to data files (files-as-database). - Sanitization: No input validation or sanitization routines are specified for the ingested requirements.
- [EXTERNAL_DOWNLOADS]: The implementation guidelines suggest fetching typography assets from Google Fonts, which is a well-known service.
Audit Metadata