The Agent Skills Directory

[EXTERNAL_DOWNLOADS]: The skill uses npx to dynamically fetch and execute the @infimind/ecom-content-cli package from the public npm registry. This is the intended mechanism for interacting with the IMIVA MCP service.
[COMMAND_EXECUTION]: The helper script scripts/imiva_mcp.py utilizes subprocess.Popen to run the npx command. This execution is scoped to the package required for the skill's functionality and is used to facilitate JSON-RPC communication between the agent and the MCP server.
[DATA_EXPOSURE]: The skill relies on an MCP_TOKEN for authentication, which is correctly managed via environment variables rather than being hardcoded in the source files.
[INDIRECT_PROMPT_INJECTION]: The skill processes user-supplied prompts and media URLs to generate video content. While this creates an attack surface where malicious instructions could be embedded in metadata or content, the skill operates through a structured MCP interface which typically includes its own validation and safety guardrails.

ai-ecommerce-expert-seedance-2-ecommerce-video