The Agent Skills Directory

[EXTERNAL_DOWNLOADS]: The skill instructs the user to install the @membranehq/cli package from the NPM registry. This tool is the official command-line interface for the Membrane platform, which acts as a proxy for the Nectar CRM API.
[COMMAND_EXECUTION]: The skill utilizes the membrane command-line tool to perform operations such as logging in, connecting to services, and executing actions. It also supports the dynamic creation of new actions on the Membrane platform based on natural language descriptions provided by the user.
[PROMPT_INJECTION]: The skill processes data retrieved from Nectar CRM, including contact notes, activity descriptions, and deal information. This constitutes an indirect prompt injection attack surface where malicious content stored in the CRM could attempt to manipulate the agent's logic.
Ingestion points: Data returned from membrane action run commands, specifically fields like notes and descriptions from CRM records.
Boundary markers: No specific delimiters or instructions to ignore embedded commands are present in the skill definition.
Capability inventory: The agent can execute shell commands via the membrane CLI and create/run custom integration logic on the Membrane platform.
Sanitization: The instructions do not describe any sanitization or filtering of the data fetched from the CRM before it is processed by the agent.

nectar-crm