The Agent Skills Directory

[COMMAND_EXECUTION]: The script scripts/imiva_mcp.py utilizes subprocess.Popen to execute shell commands. It specifically wraps the npx utility to run external packages.
[EXTERNAL_DOWNLOADS]: The skill configuration in SKILL.md and references/mcp-config.example.json relies on npx -y @infimind/ecom-content-cli@latest. This command fetches the latest version of the package from the NPM registry every time it is invoked.
[REMOTE_CODE_EXECUTION]: The use of npx -y to download and immediately execute a remote package constitutes remote code execution. This allows logic defined in the @infimind/ecom-content-cli package to run on the local host with the permissions of the user.
[INDIRECT_PROMPT_INJECTION]: The skill possesses an indirect prompt injection surface as it ingests untrusted data.
Ingestion points: The create_color_change_task tool takes objectDescription and image paths from the user or external sources.
Boundary markers: There are no explicit delimiters or instructions to ignore embedded commands in the processed metadata.
Capability inventory: The skill has the capability to execute shell commands via subprocess.Popen in scripts/imiva_mcp.py.
Sanitization: The Python wrapper script passes user arguments directly into the JSON-RPC payload without visible sanitization or validation.

ai-ecommerce-expert-product-color-change