The Agent Skills Directory

[EXTERNAL_DOWNLOADS]: The skill instructs the user to install the @membranehq/cli package globally via npm. This is a known vendor resource provided by the skill author (membranedev) and is necessary for the skill to function.
[COMMAND_EXECUTION]: The skill relies on executing membrane CLI commands to perform tasks such as logging in, searching for connectors, and interacting with the Google Docs API. These commands are standard for the intended integration logic.
[PROMPT_INJECTION]: The skill has a surface for indirect prompt injection as it retrieves and processes content from external Google Documents. This is inherent to the skill's primary purpose.
Ingestion points: Data is ingested through actions like get-document or via the membrane request proxy functionality (SKILL.md).
Boundary markers: None explicitly defined in the CLI command descriptions.
Capability inventory: The skill can create, update, and delete document content via the membrane action run and membrane request commands.
Sanitization: No specific sanitization or filtering of document content is described in the documentation.

google-docs