tui-alert-tips
Pass
Audited by Gen Agent Trust Hub on Oct 7, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTIONNO_CODE
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill is designed to process external JSON data (Input Model) to generate ASCII TUI and design specifications. This creates a surface where malicious instructions could be embedded in the input data to influence the agent's behavior during rendering.
- Ingestion points: The skill processes a JSON
Input Model(width, props, state, style) defined inSKILL.md. - Boundary markers: The skill uses mandatory output headers (e.g.,
OUTPUT: TUI_RENDER) as delimiters for its responses. - Capability inventory: The skill itself contains no executable code, subprocess calls, or network operations; it is purely instructional.
- Sanitization: There is no evidence of input validation or sanitization instructions to handle potentially malicious strings within the input properties.
- [NO_CODE]: The skill consists exclusively of markdown instructions, JSON schemas, and ASCII examples. It does not include any scripts, binaries, or automated installation steps.
Audit Metadata