getting-started
Pass
Audited by Gen Agent Trust Hub on Aug 30, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill utilizes the
x-htmldirective to render table content, which is the standard implementation for this library but represents an injection surface if the underlying data contains untrusted content. - Ingestion points: The
local.datareactive object inSKILL.mdserves as the primary data source for the table. - Boundary markers: The skill does not define specific delimiters for separating data from instructions, relying on standard Alpine.js binding syntax.
- Capability inventory: The skill uses
x-htmlto inject rendered output fromFlexRenderinto the DOM. - Sanitization: Data sanitization is not explicitly implemented in the example code, as the primary focus is on library initialization and reactivity.
Audit Metadata