The Agent Skills Directory

[COMMAND_EXECUTION]: The skill utilizes the membrane CLI to interact with Workbooks CRM. This is the primary intended function of the skill and relies on the vendor's own command-line interface.
[EXTERNAL_DOWNLOADS]: The instructions include installing the @membranehq/cli package via npm. This is an official package from the skill's author/vendor and is required for the skill to function.
[DATA_EXFILTRATION]: The skill implements a secure approach to data handling by using a proxy (membrane request) that manages authentication headers server-side, preventing the need to expose or handle raw API keys within the local environment.
[PROMPT_INJECTION]: As the skill retrieves and processes data from an external CRM, it is theoretically susceptible to indirect prompt injection if malicious instructions are stored within CRM records.
Ingestion points: Results from membrane action run and membrane request commands in SKILL.md.
Boundary markers: None explicitly defined in the prompt templates.
Capability inventory: Execution of shell commands via the membrane CLI.
Sanitization: No explicit sanitization or escaping of CRM data is described in the provided instructions.

workbooks-crm