The Agent Skills Directory

[EXTERNAL_DOWNLOADS]: The skill instructs the user to install the @membranehq/cli package from the NPM registry. This package is an official tool provided by the vendor (membranedev) to interact with their platform.
[COMMAND_EXECUTION]: The skill facilitates the execution of shell commands through the membrane CLI. These commands are used for user authentication, connecting to Overledger, searching for actions, and running integration logic.
[INDIRECT_PROMPT_INJECTION]: The skill possesses an attack surface for indirect prompt injection as it processes natural language inputs to discover or generate functional actions.
Ingestion points: Untrusted data enters the context via the --intent parameter in membrane action list and the DESCRIPTION positional argument in membrane action create (SKILL.md).
Boundary markers: No explicit delimiters or instructions to ignore embedded commands are present in the command examples.
Capability inventory: The skill allows the execution of arbitrary actions (membrane action run) and the creation of new server-side logic (membrane action create).
Sanitization: There is no client-side sanitization or validation of the input strings documented within the skill; sanitization is assumed to be handled by the Membrane platform server-side.

overledger