json-render-ui
Pass
Audited by Gen Agent Trust Hub on Jul 30, 2026
Risk Level: SAFE
Full Analysis
- [EXTERNAL_DOWNLOADS]: The skill's HTML template fetches frontend libraries (Tailwind CSS, Preact, and HTM) from well-known services (cdn.tailwindcss.com and esm.sh). This is a standard practice for rendering web-based artifacts and does not introduce security risks.
- [DATA_EXFILTRATION]: The skill operates entirely within the generated artifact. There are no mechanisms for data exfiltration, network requests to untrusted domains, or access to sensitive local environment variables or files.
- [COMMAND_EXECUTION]: The skill does not contain any instructions or scripts that execute shell commands or spawn subprocesses. The generation process is limited to producing structured JSON data.
- [PROMPT_INJECTION]: Instructions in the skill are focused on ensuring structural integrity and following a specific component schema. No patterns attempting to bypass safety filters or reveal system prompts were identified.
- [DATA_BINDING_SECURITY]: The skill implements an indirect prompt injection surface by processing user input into a UI; however, it effectively mitigates this risk. It uses a constrained JSON schema (UITree) and a renderer based on Preact/HTM which provides automatic output encoding and sanitization, preventing unauthorized code execution from user-controlled content.
Audit Metadata