The Agent Skills Directory

[EXTERNAL_DOWNLOADS]: The skill instructs the user to install the @membranehq/cli package globally via npm and suggests using npx @membranehq/cli@latest to discover actions. These resources are provided by the skill's author to facilitate interaction with the Membrane platform.
[COMMAND_EXECUTION]: The instructions guide the agent to execute various membrane CLI commands, including membrane login, membrane connect, and membrane action run. These commands are used to authenticate with the platform and perform operations on Sellsy data.
[PROMPT_INJECTION]: The skill has an indirect prompt injection surface as it processes data retrieved from the external Sellsy API (e.g., deal names, person details, or task descriptions).
Ingestion points: Data returned to the agent from commands like membrane action run or membrane request (SKILL.md).
Boundary markers: The provided instructions do not include specific delimiters or instructions for the agent to ignore embedded commands within the Sellsy data.
Capability inventory: The agent can execute CLI commands to fetch data and perform write operations (e.g., creating tasks or updating deals) via membrane action run (SKILL.md).
Sanitization: There is no mention of sanitizing or validating the data retrieved from Sellsy before it is used in subsequent prompts or actions.

sellsy