The Agent Skills Directory

[EXTERNAL_DOWNLOADS]: The skill requires the installation of the @membranehq/cli package via npm. This is a global installation of the official CLI tool provided by the vendor (Membrane) to facilitate the integration.
[COMMAND_EXECUTION]: The skill's primary functionality is delivered through the execution of membrane CLI commands. These commands manage user sessions, connect to external services, and execute actions like listing organizations or creating projects in Simplicate.
[PROMPT_INJECTION]: The skill has a potential surface for indirect prompt injection as it processes external data from the Simplicate API and user-provided input.
Ingestion points: Untrusted data enters the agent context via the output of membrane action list and membrane action run commands, as well as via the --intent and --input arguments.
Boundary markers: The provided command templates do not include specific delimiters or instructions to ignore embedded commands in the data retrieved from the API.
Capability inventory: The agent has the capability to execute CLI commands and interact with the Simplicate platform, which includes creating and updating records.
Sanitization: There is no explicit evidence of sanitization or validation of the external API content before it is processed by the agent within the skill's instructions.

simplicate