The Agent Skills Directory

[EXTERNAL_DOWNLOADS]: The skill instructs the user to install the @membranehq/cli package globally via npm. This is a vendor-provided tool required for the integration.
[COMMAND_EXECUTION]: The skill relies on the membrane command-line utility to perform authentication, manage connections, and execute actions on Thrivecart. It uses shell commands for core functionality, such as membrane login, membrane connection ensure, and membrane action run.
[INDIRECT_PROMPT_INJECTION]: The skill processes data retrieved from the Thrivecart API, creating a vulnerability surface where malicious instructions could be embedded in external data.
Ingestion points: External data enters the agent context via CLI action outputs (membrane action run) or direct API proxy requests (membrane request).
Boundary markers: The instructions do not define specific delimiters or "ignore" warnings for handling the content of Thrivecart responses.
Capability inventory: The agent has the ability to execute shell commands (via the Membrane CLI) and perform network operations to the Thrivecart and Membrane platforms.
Sanitization: There are no instructions provided for escaping, validating, or filtering the data received from the external service before it is processed.

thrivecart