tui-npm-setting
Pass
Audited by Gen Agent Trust Hub on Oct 7, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: The skill serves a purely declarative purpose, transforming JSON-based input models into visual ASCII representations and design instructions for external tools.
- [INDIRECT_PROMPT_INJECTION]: The skill possesses a potential attack surface for indirect prompt injection as it processes external input data to generate UI renders and specifications.
- Ingestion points: The skill ingests untrusted data through the 'Input Model' JSON (specifically the
props,state, anderrorfields). - Boundary markers: No explicit boundary markers or instructions to disregard embedded commands in the input data are defined in the rendering rules.
- Capability inventory: The skill lacks any operational capabilities; it does not request tool access for network operations, file system writes, or command execution.
- Sanitization: The skill implements layout-based sanitization (truncation to width, stable placeholders for loading states) but does not specifically filter for malicious instructions. Given the lack of execution tools, the risk is minimal.
Audit Metadata