The Agent Skills Directory

[COMMAND_EXECUTION]: The skill utilizes the Membrane CLI (membrane) to interact with Slite. These commands are used for session management, connection listing, and executing pre-defined actions.
[EXTERNAL_DOWNLOADS]: The instructions recommend installing the @membranehq/cli package from the npm registry. This is a vendor-owned resource required for the skill to operate.
[CREDENTIALS_UNSAFE]: The skill promotes a secure posture by explicitly advising against asking for or storing user API keys, delegating authentication to the Membrane server-side lifecycle.
[INDIRECT_PROMPT_INJECTION]: The skill processes Slite document data through its actions, creating a surface for indirect prompt injection from untrusted document content.
Ingestion points: Data returned from membrane action run (SKILL.md).
Boundary markers: None explicitly mentioned in the prompt instructions.
Capability inventory: Capability to execute CLI commands and generate new integration actions via membrane action create (SKILL.md).
Sanitization: No explicit sanitization of document content is performed before processing.

slite