wix-cli-site-plugin
Pass
Audited by Gen Agent Trust Hub on Mar 3, 2026
Risk Level: SAFEPROMPT_INJECTION
Full Analysis
- [PROMPT_INJECTION]: The skill defines patterns for components that ingest and render data from external or user-controlled sources, creating a potential indirect prompt injection surface. * Ingestion points: Data enters the agent context through
this.getAttribute()in.tsxfiles,widget.getProp()in.panel.tsxfiles, anditems.query()results inEXAMPLES.md. * Boundary markers: None present; the templates do not suggest the use of delimiters to isolate untrusted data or provide warnings to ignore embedded instructions. * Capability inventory: The generated code has access to Wix SDK modules and performs direct DOM manipulation viainnerHTML. * Sanitization: Absent; example code directly interpolates variables likedisplayName,badgeText, anditem.titleinto HTML strings without escaping or sanitization.
Audit Metadata