The Agent Skills Directory

[EXTERNAL_DOWNLOADS]: The skill instructs the installation of the @membranehq/cli package via npm. This is a vendor-provided tool required for the skill to communicate with the Membrane platform and Yonder API.
[COMMAND_EXECUTION]: The skill relies on executing membrane CLI commands to manage authentication, connections, and action execution. This is the primary mechanism for the skill's functionality.
[PROMPT_INJECTION]: The skill identifies a surface for indirect prompt injection due to its processing of external data.
Ingestion points: The skill ingests data from Yonder documents, collections, and action outputs via membrane action run and membrane action list (SKILL.md).
Boundary markers: There are no explicit delimiters or instructions provided to the agent to distinguish between its instructions and potentially malicious content embedded within the Yonder data it retrieves.
Capability inventory: The skill possesses the ability to execute shell commands (via the CLI), run existing actions, and dynamically create new actions based on descriptions (membrane action create), which provides a pathway for ingested instructions to influence system state.
Sanitization: The instructions do not define any sanitization, filtering, or validation steps for data retrieved from external Yonder sources before processing.

yonder