The Agent Skills Directory

[COMMAND_EXECUTION]: The skill instructs the agent to execute shell commands using the Membrane CLI (membrane login, membrane connect, membrane action run) to manage identity data and workflows within SailPoint.
[EXTERNAL_DOWNLOADS]: Installs the @membranehq/cli package from the official NPM registry, which is a verified tool from the skill's vendor (membranedev).
[DATA_EXFILTRATION]: While the skill accesses and manages sensitive SailPoint identity data, it uses the Membrane platform to handle the authentication lifecycle server-side, preventing local exposure of API keys or tokens.
[PROMPT_INJECTION]: The skill presents an indirect prompt injection surface as it processes user-provided natural language descriptions to search for or dynamically create actions via the membrane action create command. It also ingests data from external SailPoint API responses.
Ingestion points: Data returned from SailPoint actions and user-provided strings for action discovery and creation.
Boundary markers: Not explicitly defined in the instructions.
Capability inventory: The skill can execute actions that interact with the SailPoint API and build new actions based on descriptions.
Sanitization: Relies on the Membrane platform's internal handling of action generation and execution.

sailpoint