The Agent Skills Directory

[EXTERNAL_DOWNLOADS]: Installs the @membranehq/cli package from the npm registry. This is an official tool provided by the skill author to manage the integration environment and authentication.
[COMMAND_EXECUTION]: Executes shell commands using the membrane CLI and npm to install dependencies, perform authentication (membrane login), and manage data connections (membrane connection ensure).
[INDIRECT_PROMPT_INJECTION]: The skill processes external data retrieved from Baserow (such as row content and table metadata), which represents a potential attack surface for instructions embedded in that data.
Ingestion points: Data is ingested through actions like list-rows, get-row, and raw API requests via membrane request (SKILL.md).
Boundary markers: The instructions do not define specific delimiters or warnings to the agent regarding potential instructions embedded in the retrieved data.
Capability inventory: The skill has the capability to execute shell commands and perform network operations through the Membrane CLI.
Sanitization: There is no mention of sanitization, filtering, or validation of the content retrieved from the external Baserow database before it is processed by the agent.

baserow