tui-keyboard
Pass
Audited by Gen Agent Trust Hub on Oct 7, 2026
Risk Level: SAFENO_CODE
Full Analysis
- [SAFE]: The skill provides structured instructions for generating pixel-precise ASCII Text User Interfaces (TUI) and associated design specifications in JSON format. It functions as a formatting template for UI design workflows.
- [NO_CODE]: The skill does not include or execute any scripts, binary files, or external code. Its operations are limited to text generation within defined output blocks.
- [INDIRECT_PROMPT_INJECTION]: The skill defines an input model for processing layout data. An analysis of the attack surface indicates no security risk:
- Ingestion points: Untrusted data enters the agent context via the JSON Input Model (SKILL.md).
- Boundary markers: Output is strictly delimited by mandatory blocks (TUI_RENDER, COMPONENT_SPEC, etc.).
- Capability inventory: None. The skill has no access to the file system, network, or shell environments.
- Sanitization: The rendering rules include constraints for text truncation and formatting to maintain UI stability.
Audit Metadata