The Agent Skills Directory

[COMMAND_EXECUTION]: The script scripts/imiva_mcp.py uses subprocess.Popen to execute the npx command. This is used to run the official IMIVA e-commerce client and is the standard way this skill interacts with the underlying tools.
[EXTERNAL_DOWNLOADS]: The skill uses npx -y to download and run the @infimind/ecom-content-cli package from the NPM registry at runtime. This package is the official tool provided by the vendor for the IMIVA platform.
[DATA_EXFILTRATION]: The skill transmits product data and an authentication token to https://imiva.ecpro.com. This communication is the primary function of the skill and targets the vendor's official domain.
[PROMPT_INJECTION]: The skill ingests untrusted product data (images and text) which could be used for indirect prompt injection attacks.
Ingestion points: Arguments passed to create_product_main_image_task and other tools via the scripts/imiva_mcp.py helper.
Boundary markers: None identified in the Python wrapper script; the skill relies on the agent to correctly format parameters.
Capability inventory: Command execution via subprocess.Popen and network access to the vendor's API.
Sanitization: No explicit content sanitization or validation is performed within the Python wrapper script.

ai-ecommerce-expert-new-product-launch-content