The Agent Skills Directory

[COMMAND_EXECUTION]: The skill uses the membrane CLI tool to perform various operations, including authentication (membrane login), connecting to services (membrane connect), and executing API actions. These commands are part of the standard functional workflow for the vendor's platform.
[EXTERNAL_DOWNLOADS]: The skill requires the installation of the @membranehq/cli package via npm. This is an official vendor resource from 'membranedev' and is necessary for the skill's operation.
[SAFE]: The skill promotes secure development by advising against asking users for raw API keys. Instead, it utilizes the Membrane platform to handle OAuth flows and credential refreshes server-side, reducing the risk of local secret exposure.
[PROMPT_INJECTION]: As an integration skill that processes external data from WooCommerce (such as order details and customer info), it has an inherent surface for indirect prompt injection.
Ingestion points: External data enters the context via retrieval actions like list-orders and get-product in SKILL.md.
Boundary markers: Not explicitly defined in the CLI command examples.
Capability inventory: The skill includes commands to write or modify data (create-order, update-product) and execute generic requests via membrane request as seen in SKILL.md.
Sanitization: No explicit sanitization of the retrieved WooCommerce data is described, though the mediated nature of the CLI actions provides a layer of structure.

woocommerce