The Agent Skills Directory

[EXTERNAL_DOWNLOADS]: The skill instructs the user to install the Membrane CLI (@membranehq/cli) from the official npm registry. This is a vendor-owned tool required for the skill to function.
[COMMAND_EXECUTION]: The agent uses the membrane command-line interface to perform authentication, search for API actions, and execute requests against the Centra platform.
[INDIRECT_PROMPT_INJECTION]: The skill ingests untrusted data from the Centra e-commerce platform which could contain malicious instructions.
Ingestion points: Data retrieved via membrane action run or membrane request (e.g., product descriptions, order notes, customer details).
Boundary markers: None provided in the prompt instructions to help the agent distinguish between data and instructions.
Capability inventory: The skill can perform state-changing operations like cancel-order, create-product, and update-customer via the CLI.
Sanitization: There is no explicit requirement for the agent to sanitize or validate the content of the data retrieved from the API.

centra