page-best-practice
Pass
Audited by Gen Agent Trust Hub on Mar 28, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: The skill is designed for automated frontend code generation and follows strict organizational patterns. It does not perform unauthorized network requests, access sensitive system files, or execute remote code.- [PROMPT_INJECTION]: The skill accepts user-defined page names and descriptions to generate scaffolding. This represents a potential surface for indirect prompt injection if descriptions are sourced from untrusted parties. However, in its intended use case as a developer tool, this risk is minimal.
- Ingestion points: User input for
pageNameanddescriptionvia the defined schema. - Boundary markers: None explicitly implemented to isolate the description from the core generation logic.
- Capability inventory: Capability to write new files to the
apps/web/src/pagesdirectory and read existing files in that same scope for analysis. - Sanitization: Input is validated using
references/schema.ts(Zod), ensuringpageNameadheres to PascalCase and basic string constraints.
Audit Metadata