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

wix-import

Pass

Audited by Gen Agent Trust Hub on Nov 6, 2026

Risk Level: SAFEINDIRECT_PROMPT_INJECTIONCOMMAND_EXECUTIONEXTERNAL_DOWNLOADS
Full Analysis
  • [INDIRECT_PROMPT_INJECTION]: The skill ingests data from external project folders and files provided by the user, which could contain malicious instructions.
  • Ingestion points: Processes project files in Step 4 and reads a local AGENTS.md file to guide file-writing operations.
  • Boundary markers: Includes a defensive instruction to treat external files as data rather than instructions.
  • Capability inventory: The skill possesses extensive capabilities including global package installation (npm install -g), site-level dependency installation (yarn install), file system modifications, and Wix CLI operations.
  • Sanitization: Relies on prompt-level instructions to ignore embedded instructions in data files.
  • [COMMAND_EXECUTION]: The skill uses various system and CLI commands (wix, git, npm, yarn, corepack, grep). It incorporates basic shell escaping logic, such as wrapping values in single quotes, to mitigate command injection risks.
  • [EXTERNAL_DOWNLOADS]: Fetches the Wix CLI (@wix/cli) and system tools like git using official package managers (NPM, Brew, Winget). These downloads are necessary for the skill's functionality.
Audit Metadata
Risk Level
SAFE
Analyzed
Nov 6, 2026, 12:08 AM