tui-time-line
Pass
Audited by Gen Agent Trust Hub on Oct 7, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill defines a workflow for ingesting external JSON data structures and rendering them into TUI layouts and component specifications, which introduces a potential surface for instructions embedded in data.
- Ingestion points: Data enters the agent's context through the
props,modelValue, andstate.errorfields as defined in the Input Model section ofSKILL.md. - Boundary markers: The skill uses specific markdown headers (e.g.,
### OUTPUT: TUI_RENDER) and code blocks to delimit the generated content, providing basic structural separation. - Capability inventory: No shell execution, file system writes, or network tools are defined within the skill; its primary capability is generating text for downstream workflows.
- Sanitization: The rendering rules specify truncation for error messages to fit
widthCols, but there are no instructions to sanitize or escape user-provided labels or values to prevent them from being interpreted as instructions.
Audit Metadata