The Agent Skills Directory

[EXTERNAL_DOWNLOADS]: The skill installs the @membranehq/cli package using npm. This is an official tool provided by the vendor to interact with their platform and is necessary for the skill's functionality.
[COMMAND_EXECUTION]: The skill provides instructions for executing membrane CLI commands to authenticate the user, list connections, and run actions. These commands are localized to the integration's logic.
[PROMPT_INJECTION]: The skill possesses a surface for indirect prompt injection because it ingests and processes data from the Okay platform through action outputs and search results.
Ingestion points: Outputs from membrane action list, membrane action get, and membrane action run commands found in SKILL.md.
Boundary markers: No explicit markers or warnings to ignore embedded instructions are provided in the command examples.
Capability inventory: The skill can execute actions (membrane action run) and create new ones (membrane action create), allowing for data manipulation and network interaction within the scope of the Okay integration.
Sanitization: No sanitization or validation logic is specified for the data returned from the external API.

okay