The Agent Skills Directory

[EXTERNAL_DOWNLOADS]: The skill instructs users to install the @membranehq/cli package globally via npm. This is the official command-line interface provided by the skill author for managing integrations.
[COMMAND_EXECUTION]: The skill utilizes several terminal commands through the membrane CLI to authenticate (membrane login), manage connections (membrane connection ensure), and execute CRM actions (membrane action run). These commands are necessary for the skill's primary functionality of interacting with the Vtiger API.
[INDIRECT_PROMPT_INJECTION]: The skill possesses a data ingestion surface as it retrieves content from Vtiger modules such as Leads, Comments, and Emails, which could potentially contain untrusted instructions.
Ingestion points: External data is brought into the agent context via membrane action run (Query Records, Retrieve Record) and membrane request as described in SKILL.md.
Boundary markers: The instructions do not specify explicit delimiters or warnings to ignore instructions embedded within the CRM data.
Capability inventory: The skill has the ability to write to the file system (via CLI output redirection if the user chooses), make network requests (membrane request), and modify CRM data (create-record, update-record, delete-record).
Sanitization: No specific sanitization or filtering logic is mentioned for the content retrieved from the CRM.

vtiger