The Agent Skills Directory

[COMMAND_EXECUTION]: The skill uses the membrane CLI to perform operations like searching, connecting, and running actions. These commands are restricted to the vendor's own platform utilities.
[EXTERNAL_DOWNLOADS]: The skill recommends installing the @membranehq/cli package from the npm registry. This is a vendor-owned package necessary for the skill's operation.
[SAFE]: The skill explicitly instructs the agent to let the platform handle authentication, avoiding the collection or storage of sensitive API keys or secrets within the agent's environment.
[PROMPT_INJECTION]: The skill identifies an indirect prompt injection surface as it processes data from external spreadsheets.
Ingestion points: Data returned from membrane action run and membrane request in SKILL.md.
Boundary markers: Absent.
Capability inventory: Subprocess execution via membrane CLI for API interactions.
Sanitization: Absent.

sheetdb