wix-readme
Pass
Audited by Gen Agent Trust Hub on Nov 11, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTIONDYNAMIC_EXECUTIONEXTERNAL_DOWNLOADSCOMMAND_EXECUTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill is designed to ingest and act upon data from external sources, including Wix documentation and remote skill files, which can influence subsequent tool calls and logic.
- Ingestion points: Data is retrieved via tools such as
ReadFullDocsArticle,SearchWixRESTDocumentation, and site context retrieval. - Boundary markers: The instructions do not define specific delimiters or "ignore embedded instructions" warnings for the agent to use when processing retrieved documentation.
- Capability inventory: The skill has access to high-capability tools including
ExecuteWixAPI(arbitrary JavaScript execution for API orchestration) andUploadHeadlessWebsiteFiles(network upload and site deployment). - Sanitization: No explicit validation or sanitization of content retrieved from documentation URLs is specified before the content is used to model API requests.
- [DYNAMIC_EXECUTION]: The skill employs the
ExecuteWixAPItool, which takes a JavaScript function as an argument to perform chained API calls, pagination, and data transformations at runtime. - [EXTERNAL_DOWNLOADS]: The skill references downloading and installing the
@wix/clipackage and additional Wix skills from the vendor's official GitHub repositories and domains (e.g., wix.com). - [COMMAND_EXECUTION]: The instructions guide the agent on using shell commands via the Wix CLI (
npx @wix/cli) to manage account authentication, build Astro-based projects, and release site updates.
Audit Metadata