The Agent Skills Directory

[EXTERNAL_DOWNLOADS]: The skill instructs the installation of the @membranehq/cli package from the NPM registry. This is a vendor-owned package used to facilitate the connection between the agent and the CRM platform.
[COMMAND_EXECUTION]: Employs the membrane command-line utility to perform integration tasks such as searching for connectors, establishing connections, and executing CRM actions. These commands are restricted to the functionality provided by the Membrane platform.
[PROMPT_INJECTION]: The skill has an attack surface for indirect prompt injection as it retrieves data from an external CRM which may contain untrusted content.
Ingestion points: Untrusted data enters the agent context through actions that list people, companies, deals, projects, and tasks as defined in SKILL.md.
Boundary markers: There are no explicit delimiters or instructions provided to the agent to treat data from CentralStationCRM as untrusted or to ignore embedded instructions.
Capability inventory: The skill possesses capabilities to create, update, and delete data within the CRM, as well as the ability to make arbitrary HTTP requests via the membrane request command.
Sanitization: No specific sanitization, validation, or filtering of the content retrieved from the CRM API is mentioned.

centralstationcrm