The Agent Skills Directory

[EXTERNAL_DOWNLOADS]: The skill requires the installation of the @membranehq/cli package from the npm registry. This is the official command-line tool for the vendor's platform.\n- [COMMAND_EXECUTION]: The skill uses shell commands via the membrane CLI for operations including authentication, service connection, and running pre-defined actions. These operations are intended for the skill's functionality.\n- [PROMPT_INJECTION]: The skill presents an attack surface for indirect prompt injection due to its interaction with external CRM data.\n
Ingestion points: Untrusted data enters the agent's context from various EspoCRM records (e.g., Leads, Tasks, Contacts) when the agent retrieves information using membrane action run.\n
Boundary markers: No explicit delimiters or system instructions are provided to the agent to treat the retrieved CRM content as untrusted data or to ignore embedded commands.\n
Capability inventory: The agent has the capability to execute shell commands (membrane CLI) that can modify data in the CRM or trigger new actions based on instructions it might find in the ingested data.\n
Sanitization: There is no indication of sanitization or validation of the content retrieved from the EspoCRM API before it is processed by the agent.

espocrm