The Agent Skills Directory

[EXTERNAL_DOWNLOADS]: The skill instructs the installation of the @membranehq/cli package from the official NPM registry. This is a vendor-owned tool required for the skill to interact with the Membrane platform and its managed integrations.
[COMMAND_EXECUTION]: The agent is instructed to execute several membrane CLI commands to handle authentication (membrane login), connection establishment (membrane connection ensure), and action discovery/execution (membrane action run). These commands are the intended mechanism for the integration.
[INDIRECT_PROMPT_INJECTION]: The skill processes data fetched from external Microsoft Dynamics 365 records (such as Accounts, Leads, and Opportunities). This creates a standard surface for indirect prompt injection, where malicious content stored within the CRM could attempt to influence the agent's behavior.
Ingestion points: Data retrieved through membrane action run and membrane request commands (found in SKILL.md).
Boundary markers: None explicitly defined in the prompt instructions to isolate retrieved CRM data.
Capability inventory: The skill has the capability to perform follow-up API requests and command executions based on the data it processes.
Sanitization: No specific data sanitization or filtering logic is provided for the retrieved external content.

dynamics-crm