The Agent Skills Directory

[EXTERNAL_DOWNLOADS]: The skill instructs the agent to install the @membranehq/cli package globally via npm. This is a vendor-provided package required for the skill to communicate with the Membrane platform.
[COMMAND_EXECUTION]: The instructions guide the agent to perform actions using the membrane CLI, such as authentication, connection setup, and running specific Dbt Cloud integration tasks.
[PROMPT_INJECTION]: The skill provides an interface to retrieve and process data from Dbt Cloud, which presents an indirect prompt injection surface.
Ingestion points: Untrusted data enters the agent context through the output of the membrane action run command (SKILL.md).
Boundary markers: No specific delimiters or instructions are used to distinguish external data from the agent's core instructions.
Capability inventory: The agent possesses the capability to execute shell commands via the CLI (SKILL.md).
Sanitization: No explicit sanitization or validation of the data retrieved from the external API is mentioned in the skill instructions.

dbt-cloud