ai-ecommerce-expert-product-demo-video

Pass

Audited by Gen Agent Trust Hub on Aug 25, 2026

Risk Level: SAFEEXTERNAL_DOWNLOADSCOMMAND_EXECUTION
Full Analysis
  • [COMMAND_EXECUTION]: The helper script scripts/imiva_mcp.py utilizes subprocess.Popen to launch the Model Context Protocol (MCP) server. The command is executed using a list-based argument structure [npx, "-y", "@infimind/ecom-content-cli@latest"] with a hardcoded package name, which prevents shell injection vulnerabilities.
  • [EXTERNAL_DOWNLOADS]: The skill dynamically fetches and executes the @infimind/ecom-content-cli package from the official NPM registry using npx at runtime. This package is the designated client for the IMIVA e-commerce platform utilized by this skill.
  • [CREDENTIALS_SAFE]: The documentation and code correctly advise against hardcoding sensitive information. It instructs users to provide the MCP_TOKEN via environment variables, ensuring that authentication secrets are handled outside of the skill's source code.
  • [REMOTE_CODE_EXECUTION]: While the skill executes remote code by downloading a Node.js package, this code is limited to the official vendor resource required for the skill's primary functionality (e-commerce video production).
Audit Metadata
Risk Level
SAFE
Analyzed
Aug 25, 2026, 08:01 AM
Security Audit — agent-trust-hub — ai-ecommerce-expert-product-demo-video