skills/wix/skills/wix-headless/Gen Agent Trust Hub

wix-headless

Pass

Audited by Gen Agent Trust Hub on Sep 19, 2026

Risk Level: SAFEEXTERNAL_DOWNLOADSREMOTE_CODE_EXECUTIONCOMMAND_EXECUTIONDATA_EXFILTRATIONINDIRECT_PROMPT_INJECTION
Full Analysis
  • [EXTERNAL_DOWNLOADS]: The skill downloads an environment initialization script from https://www.wix.com/skills/headless/entry/bootstrap.mjs.
  • [REMOTE_CODE_EXECUTION]: It executes the downloaded bootstrap.mjs script with the Node.js runtime to facilitate the Wix CLI authentication flow.
  • [COMMAND_EXECUTION]: It performs several administrative shell tasks including npx @wix/cli, npm install, and curl to setup Wix apps and release the site.
  • [DATA_EXFILTRATION]: The skill reads sensitive credentials from the .env file (such as WIX_WIX_CLIENT_SECRET) and transmits them to https://www.wixapis.com/oauth2/token. This is the standard OAuth procedure for the vendor's integration services.
  • [INDIRECT_PROMPT_INJECTION]:
  • Ingestion points: The skill accepts "user intent" text from the prompt to determine which business verticals to install (documented in SKILL.md and DISCOVERY.md).
  • Boundary markers: No specific delimiters are used to separate the user-provided intent from internal instructions.
  • Capability inventory: The skill uses Bash(curl), Bash(npx), and Bash(node) to perform site configuration and data seeding across all provided modules.
  • Sanitization: The skill does not explicitly describe validation or escaping of user intent before using it to drive API requests.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 19, 2026, 07:18 AM
Security Audit — agent-trust-hub — wix-headless