tui-read
Pass
Audited by Gen Agent Trust Hub on Oct 7, 2026
Risk Level: SAFENO_CODEINDIRECT_PROMPT_INJECTION
Full Analysis
- [NO_CODE]: The skill consists entirely of markdown instructions and documentation for formatting text and JSON objects. It does not include any scripts, binaries, or commands to be executed on the host system.
- [INDIRECT_PROMPT_INJECTION]: The skill is designed to ingest and process a user-provided 'Input Model' to generate TUI renderings and specifications.
- Ingestion points: The 'Input Model' JSON (specifically the
props,state, andtypographyfields) inSKILL.mdrepresents the data entry surface. - Boundary markers: The skill uses clear, mandatory block headers such as
OUTPUT: TUI_RENDERandOUTPUT: COMPONENT_SPECto delimit agent output. - Capability inventory: No tools, subprocess calls, network operations, or file-writing capabilities are requested or defined in this skill.
- Sanitization: The instructions specify that error messages should be truncated to fit the TUI width, but no explicit sanitization or escaping logic for user-provided strings is mentioned.
Audit Metadata