tui-empty
Pass
Audited by Gen Agent Trust Hub on Oct 7, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: The skill serves as a template for generating TUI rendering and design specs (Pencil MCP). No evidence of command execution, data exfiltration, or persistence mechanisms was found.
- [INDIRECT_PROMPT_INJECTION]: The skill defines an ingestion surface for untrusted data via a JSON input model. This model is processed to generate output for downstream tools like the Pencil MCP.
- Ingestion points: Untrusted data enters via the
Input Model(JSON) defined inSKILL.md. - Boundary markers: The skill uses strict output blocks (
TUI_RENDER,COMPONENT_SPEC, etc.) to delimit output. - Capability inventory: The skill generates design specs for tools but does not invoke subprocesses, file writes, or network operations directly.
- Sanitization: The skill follows structured JSON schemas for specifications, reducing the risk of schema confusion.
Audit Metadata