tui-uni-modules-setting
Pass
Audited by Gen Agent Trust Hub on Oct 7, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill is designed to process user-provided JSON structures (Input Model) to generate UI specifications. This creates a potential surface where malicious instructions could be embedded in the input properties.
- Ingestion points: The
Input Modelsection defines where untrusted JSON data enters the agent context (e.g.,props,state,modelValue). - Boundary markers: The skill mandates specific output blocks (
TUI_RENDER,COMPONENT_SPEC, etc.), which provides some structure, but it lacks explicit instructions for the agent to ignore or sanitize embedded commands within the input data. - Capability inventory: The skill does not define any dangerous capabilities such as file system writing, network requests, or shell command execution.
- Sanitization: There is no evidence of sanitization or filtering logic for the input data provided in the instructions.
Audit Metadata