The Agent Skills Directory

[EXTERNAL_DOWNLOADS]: The skill instructs the installation of the @membranehq/cli package via NPM. This is a vendor-owned resource (matching the author 'membranedev') and is used as the primary interface for the skill's functionality.
[COMMAND_EXECUTION]: The skill uses the membrane CLI to perform operations like logging in, creating connections, and running actions. These are standard operations for this platform integration.
[DATA_EXFILTRATION]: The skill explicitly advises against asking users for API keys or tokens, directing them to use membrane connect instead. This prevents local exposure of sensitive credentials and ensures they are managed securely by the Membrane platform.
[INDIRECT_PROMPT_INJECTION]: The skill possesses a surface for indirect prompt injection as it processes data from OneTrust actions (membrane action run) and action discovery (membrane action list).
Ingestion points: Data returned from external OneTrust API calls via Membrane actions.
Boundary markers: None explicitly defined in the prompt instructions.
Capability inventory: The skill can execute actions, create new actions based on descriptions, and manage network connections.
Sanitization: No explicit sanitization of tool output is described in the instructions.

onetrust