The Agent Skills Directory

[EXTERNAL_DOWNLOADS]: Recommends the installation and use of the @membranehq/cli package from the public NPM registry. This is the official command-line tool provided by the vendor (membranedev) for managing connections and API actions.
[COMMAND_EXECUTION]: Instructs the agent to execute shell commands using the membrane CLI to authenticate users, manage cloud-based connections, and run remote actions or proxy requests to the Fountain API.
[INDIRECT_PROMPT_INJECTION]: The skill possesses a vulnerability surface for indirect prompt injection because it retrieves and acts upon external data from Fountain screenplay documents.
Ingestion points: Screenplay content, project records, and metadata retrieved via membrane action run and membrane request commands (found in SKILL.md).
Boundary markers: Absent; the instructions do not include specific delimiters or instructions to ignore embedded commands within the retrieved data.
Capability inventory: The skill enables the agent to perform write operations and arbitrary API requests (membrane action run, membrane request).
Sanitization: Absent; there are no requirements for sanitizing or validating retrieved data before it is processed or used to determine subsequent agent actions.

fountain