json-render-generative-ui

Pass

Audited by Gen Agent Trust Hub on Mar 18, 2026

Risk Level: SAFEEXTERNAL_DOWNLOADSPROMPT_INJECTION
Full Analysis
  • [EXTERNAL_DOWNLOADS]: The skill requires installation of various @json-render/* packages from npm for core functionality and cross-platform rendering implementations.
  • [PROMPT_INJECTION]: The framework renders UI components based on AI-generated JSON specifications, which introduces a surface for indirect prompt injection where malicious data could attempt to influence the agent.
  • Ingestion points: The Renderer component in SKILL.md ingests a spec object generated dynamically by an LLM based on user prompts.
  • Boundary markers: The framework uses a defineCatalog system to enforce structural constraints and guardrails on the AI-generated components.
  • Capability inventory: The system allows components to trigger named actions such as navigate, export_report, and refresh_data.
  • Sanitization: The framework employs Zod for strict schema validation to ensure that AI-generated JSON adheres to defined component properties and types.
Audit Metadata
Risk Level
SAFE
Analyzed
Mar 18, 2026, 12:27 PM