The Agent Skills Directory

[EXTERNAL_DOWNLOADS]: The skill instructs the agent to install the official @membranehq/cli package from the npm registry to interact with the Membrane platform.
[COMMAND_EXECUTION]: The skill utilizes the Membrane CLI to perform various operations including user authentication (membrane login), establishing service connections (membrane connect), and executing deployment tasks (membrane action run).
[COMMAND_EXECUTION]: Includes functionality for the dynamic creation of actions based on natural language descriptions (membrane action create), which are then built and executed within the Membrane environment.
[PROMPT_INJECTION]: The skill exhibits an attack surface for indirect prompt injection via data ingested from the Porter platform.
Ingestion points: Data is ingested from Porter Job Outputs and Account records as described in SKILL.md.
Boundary markers: The skill does not define specific delimiters or instructions to ignore embedded commands in the data retrieved from the external platform.
Capability inventory: The skill maintains the capability to execute actions on the Porter infrastructure using the membrane action run command.
Sanitization: No explicit sanitization or validation of the ingested external data is mentioned in the skill instructions.

porter