skills/wix/skills/rp-target-wix/Gen Agent Trust Hub

rp-target-wix

Pass

Audited by Gen Agent Trust Hub on Aug 25, 2026

Risk Level: SAFEPROMPT_INJECTIONCOMMAND_EXECUTIONEXTERNAL_DOWNLOADS
Full Analysis
  • [PROMPT_INJECTION]: The skill exposes a surface for indirect prompt injection through functions that ingest untrusted external data.\n
  • Ingestion points: The convertHtmlToRichContent and importMedia functions in lib/wix-writers.js accept arbitrary HTML and source URLs from external systems.\n
  • Boundary markers: The skill does not implement delimiters or boundary markers to isolate external data from agent instructions.\n
  • Capability inventory: The skill has extensive write capabilities to Wix API entities, including Blog, CMS, Members, Stores, and Contacts, and can trigger remote media imports.\n
  • Sanitization: External input is not sanitized or filtered before being processed and sent to the Wix API surface.\n- [COMMAND_EXECUTION]: The documentation in SKILL.md provides explicit shell instructions for installing and configuring ngrok using brew. This is intended to create a public tunnel to facilitate local media import during the migration process.\n- [EXTERNAL_DOWNLOADS]: The skill performs network operations to Wix's official API domains (wixapis.com) to manage site content and verify API contracts. It also initiates server-side fetches of media from external URLs provided during the import process.
Audit Metadata
Risk Level
SAFE
Analyzed
Aug 25, 2026, 09:22 AM
Security Audit — agent-trust-hub — rp-target-wix