building-with-lobe-ui
Pass
Audited by Gen Agent Trust Hub on Sep 26, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: The skill serves as a technical reference and instructional guide for building user interfaces using the @lobehub/ui library. It emphasizes proper coding patterns and visual standards without introducing malicious capabilities.
- [EXTERNAL_DOWNLOADS]: The skill references various official LobeHub ecosystem packages (e.g., @lobehub/icons, @lobehub/charts) and standard public CDNs (unpkg, jsdelivr) for asset resolution. These are recognized vendor resources and well-known services.
- [INDIRECT_PROMPT_INJECTION]: The skill defines a structured workflow for processing UI requirements. It includes a dedicated evaluation framework (evaluator.md) designed to prevent generic or poor-quality output, effectively serving as a set of guardrails for the agent's code generation.
- [COMMAND_EXECUTION]: No dangerous shell commands, privilege escalation attempts, or unauthorized system access patterns were identified. The skill correctly advises against disabling security features, such as the sandbox attribute in the HtmlPreview component.
Audit Metadata