ui-state-architecture
Pass
Audited by Gen Agent Trust Hub on Aug 13, 2026
Risk Level: SAFENO_CODE
Full Analysis
- [SAFE]: The skill is entirely educational and architectural in nature, providing best practices for state ownership in agent UIs. It does not contain any executable logic or suspicious commands.
- [DATA_EXFILTRATION]: No exfiltration vectors were identified. The guide explicitly recommends security best practices, such as enforcing authorization on the server side for durable state and avoiding the transmission of raw third-party content to the model context.
- [NO_CODE]: The skill contains only Markdown documentation and illustrative code snippets (TypeScript/React) intended as examples for developers. It does not include standalone scripts, installation commands, or external dependencies.
Audit Metadata