design-spatial
Pass
Audited by Gen Agent Trust Hub on Oct 24, 2026
Risk Level: SAFEDYNAMIC_EXECUTIONINDIRECT_PROMPT_INJECTIONCOMMAND_EXECUTION
Full Analysis
- [DYNAMIC_EXECUTION]: The skill includes a local JavaScript utility,
scripts/layout-audit.js, intended for execution within a browser environment via thebrowser_evaluatecommand. This script performs geometric analysis of DOM elements and CSS properties to provide objective layout metrics. - [INDIRECT_PROMPT_INJECTION]: The skill facilitates the analysis of external web content, which presents a surface for indirect prompt injection. Ingestion points: The
__auditfunction inscripts/layout-audit.jsreads DOM nodes and computed styles. Boundary markers: Audit findings are returned to the agent context as a structured JSON object. Capability inventory: The skill utilizesbrowser_evaluateandbrowser_take_screenshot. Sanitization: The script extracts numeric and structural metrics, which are not directly executed as instructions, mitigating the risk of untrusted content influencing the agent's behavior. - [COMMAND_EXECUTION]: The instructions suggest using local static servers, such as
python3 -m http.serverandnpx serve, for rendering and testing UI components during development.
Audit Metadata