The Agent Skills Directory

[COMMAND_EXECUTION]: Instructions provide several commands to interact with the SignPath API through the Membrane CLI tool.
[EXTERNAL_DOWNLOADS]: The skill requires the installation of the @membranehq/cli package from the official NPM registry.
[DATA_EXFILTRATION]: The skill utilizes a managed authentication flow (membrane connect), which is a secure method for handling service connections without exposing API keys.
[PROMPT_INJECTION]: The skill identifies a potential surface for indirect prompt injection as it accepts natural language input for action discovery and creation.
Ingestion points: User-provided queries and descriptions used as arguments for the membrane action list and membrane action create commands in SKILL.md.
Boundary markers: No explicit delimiters or instructions are provided to the model to treat these inputs as untrusted.
Capability inventory: The skill possesses the ability to execute API actions on the SignPath platform using the membrane action run command.
Sanitization: The skill relies on the downstream Membrane platform for any necessary input sanitization or validation.

signpath