The Agent Skills Directory

[EXTERNAL_DOWNLOADS]: The skill instructs the user to install the Membrane CLI (@membranehq/cli) via npm. This is an official tool from the skill's vendor and is required for the integration logic.
[COMMAND_EXECUTION]: The agent uses the membrane command-line tool to perform administrative tasks, search for actions, and interact with the GetAccept API. These are standard operations for the skill's intended purpose.
[PROMPT_INJECTION]: The skill provides a surface for indirect prompt injection by processing data from an external source (GetAccept).
Ingestion points: External data (e.g., document details, contact information, templates) is brought into the agent's context through the output of membrane action run commands.
Boundary markers: None identified. There are no instructions for the agent to use delimiters or to treat external data as untrusted content.
Capability inventory: The agent has the ability to execute shell commands and create or poll for new actions via the membrane CLI.
Sanitization: No explicit sanitization, filtering, or escaping of the external data is performed before it is presented to the agent.

getaccept