The Agent Skills Directory

[EXTERNAL_DOWNLOADS]: The skill requires the installation of the @membranehq/cli npm package. This is a vendor-owned resource used for the skill's primary functionality.
[COMMAND_EXECUTION]: Utilizes the membrane CLI to perform actions like searching for connectors, connecting accounts, and running API actions. All commands are standard for the Membrane platform.
[PROMPT_INJECTION]: The skill exhibits an indirect prompt injection surface as it processes external data from Freeagent. * Ingestion points: External data enters via commands like membrane action run list-invoices or membrane request which fetch data from the Freeagent API as documented in SKILL.md. * Boundary markers: The instructions do not specify explicit delimiters or warnings to ignore instructions embedded in the fetched data. * Capability inventory: The agent can perform write operations (create/update/delete) and arbitrary API requests via membrane action run and membrane request in SKILL.md. * Sanitization: There is no mention of sanitizing or escaping the data retrieved from Freeagent before the agent processes it.

freeagent