The Agent Skills Directory

[EXTERNAL_DOWNLOADS]: The skill instructs the installation of the @membranehq/cli package from the public npm registry. This is a vendor-provided tool used for authentication and API management.
[COMMAND_EXECUTION]: The skill relies on executing various shell commands using the membrane CLI to manage connections, list actions, and run API requests against EspoCRM.
[INDIRECT_PROMPT_INJECTION]: The skill ingests data from an external CRM system, creating a vulnerability surface for indirect prompt injection attacks.
Ingestion points: CRM entities such as Leads, Tasks, Opportunities, and Accounts are retrieved from EspoCRM and processed in the agent context (e.g., in SKILL.md examples and via membrane action run).
Boundary markers: The instructions do not specify the use of delimiters or provide warnings to the agent to ignore instructions embedded within the retrieved CRM data.
Capability inventory: The skill has the capability to perform network requests and modify CRM data through membrane action run and membrane request commands.
Sanitization: There is no evidence of data sanitization or validation protocols for content retrieved from the CRM before it is presented to the agent.

espocrm