The Agent Skills Directory

[EXTERNAL_DOWNLOADS]: The skill installs the @membranehq/cli package globally using NPM. This package is an official tool provided by the skill's vendor (membranedev) to facilitate communication with the Membrane platform.
[COMMAND_EXECUTION]: The skill utilizes several shell commands via the membrane CLI to authenticate (membrane login), manage connections (membrane connect), and execute API operations (membrane action run). These commands are essential for the skill's primary function of interacting with the E-conomic API.
[INDIRECT_PROMPT_INJECTION]: The skill processes data from an external source (E-conomic API), creating a surface where malicious instructions could be introduced if the data source is compromised.
Ingestion points: Data is retrieved through actions such as list-customers, list-booked-invoices, and get-product as described in SKILL.md.
Boundary markers: Absent. There are no explicit instructions to use delimiters or ignore embedded commands within the retrieved financial data.
Capability inventory: The skill has the ability to run arbitrary actions via membrane action run and create new actions via membrane action create as specified in SKILL.md.
Sanitization: Absent. The instructions do not include steps for sanitizing or validating the content of the data fetched from the external API before it is processed by the agent.

e-conomic