The Agent Skills Directory

[EXTERNAL_DOWNLOADS]: The skill instructs the user to install the official Membrane CLI (@membranehq/cli) from the public NPM registry. This is a standard procedure for using the vendor's platform tools.
[COMMAND_EXECUTION]: The skill uses the membrane CLI to perform administrative tasks, manage connections, and execute API actions. These commands are scoped to the project's integration needs and utilize the platform's built-in security features.
[DATA_EXFILTRATION]: Data is retrieved from and sent to Vectara endpoints via the Membrane proxy. This behavior is consistent with the skill's stated purpose of search and retrieval and does not involve unauthorized data movement.
[INDIRECT_PROMPT_INJECTION]: The skill processes unstructured data retrieved from Vectara, which presents a potential surface for indirect prompt injection.
Ingestion points: Data enters the context through membrane action run and membrane request outputs (e.g., search results).
Boundary markers: None explicitly defined in the provided instructions; relies on standard agent behavior.
Capability inventory: The skill has the capability to execute shell commands via the membrane CLI and make network requests.
Sanitization: The skill relies on the underlying agent's safety guardrails and the Membrane platform's request handling.

vectara