The Agent Skills Directory

[EXTERNAL_DOWNLOADS]: The skill requires the installation of the @membranehq/cli package from the npm registry and uses npx to execute vendor-provided tools. These resources are owned by the skill author.- [COMMAND_EXECUTION]: The skill utilizes the membrane CLI to perform operations such as searching for connectors, managing connections, and executing API actions. This is the intended primary functionality for interacting with the Rokt platform.- [PROMPT_INJECTION]: The skill exhibits an indirect prompt injection surface as it processes output from external API calls and tool executions.
Ingestion points: Output from membrane action run, membrane action list, and membrane request commands (SKILL.md).
Boundary markers: No specific delimiters or instructions to ignore embedded content were identified.
Capability inventory: The agent can execute shell commands and perform network requests via the membrane CLI.
Sanitization: No explicit sanitization or validation logic is defined for the external data being processed.- [SAFE]: The skill demonstrates safe credential management by delegating authentication to the Membrane platform and explicitly instructing the user not to handle API keys directly.

rokt