The Agent Skills Directory

[COMMAND_EXECUTION]: The Python script scripts/imiva_mcp.py uses subprocess.Popen to execute the npx command. This is used to launch the vendor's official command-line interface for the IMIVA platform. The command and package name are hardcoded constants within the script, preventing user-controlled command injection.
[EXTERNAL_DOWNLOADS]: The skill downloads the @infimind/ecom-content-cli package from the NPM registry using npx -y. This is a standard and well-known method for executing JavaScript-based tools and is necessary for the skill's primary function of interacting with the IMIVA e-commerce API.
[INDIRECT_PROMPT_INJECTION]: The skill includes an attack surface for indirect prompt injection because it processes external product descriptions and task parameters.
Ingestion points: Data enters via the subjectDescriptions and arguments parameters in scripts/imiva_mcp.py.
Boundary markers: The skill uses structured JSON payloads which naturally act as delimiters, although no explicit "ignore instructions" warnings are present in the provided script logic.
Capability inventory: The skill has the ability to execute shell commands (via subprocess) and perform network operations (via the CLI tool).
Sanitization: Inputs are parsed using json.loads in load_args, ensuring they are valid JSON objects before being passed to the MCP tool.

ai-ecommerce-expert-brand-content-consistency