tui-input

HIGH W007: Insecure credential handling detected in skill instructions.

• Insecure credential handling detected (high risk: 1.00). The prompt instructs the agent to read the input model (including modelValue/value) and render field contents verbatim into TUI_RENDER, COMPONENT_SPEC, and PENCIL/PENCIL_BATCH_DESIGN outputs (examples even show an email value), so any secret supplied in the model would be emitted by the LLM unless explicitly masked (only password type is handled specially).