The Agent Skills Directory

[COMMAND_EXECUTION]: The skill uses a Python helper script to execute the official IMIVA CLI tool via subprocess.Popen to generate ecommerce assets. Evidence: subprocess.Popen([npx, "-y", PACKAGE], ...) in scripts/imiva_mcp.py.- [EXTERNAL_DOWNLOADS]: The skill downloads the official IMIVA ecommerce CLI package from the public NPM registry at runtime. Evidence: Uses npx -y @infimind/ecom-content-cli@latest to fetch the tool.- [REMOTE_CODE_EXECUTION]: The skill executes the downloaded NPM package as its primary method of operation. This is the official tool provided for the service. Evidence: The package is executed via npx immediately after retrieval.- [INDIRECT_PROMPT_INJECTION]: The skill possesses an attack surface for indirect prompt injection through data ingested from the IMIVA API. 1. Ingestion points: Data is fetched via get_user_products and get_user_tasks. 2. Boundary markers: The skill does not define specific delimiters for API-sourced content. 3. Capability inventory: The skill has command execution rights via subprocess.Popen. 4. Sanitization: Data is processed as JSON but lacks specific safety filtering for LLM interpolation.

ai-ecommerce-expert-product-asset-production-line