The Agent Skills Directory

[EXTERNAL_DOWNLOADS]: The skill instructs the user to install the @membranehq/cli package globally via npm. This is an official tool from the vendor (membranedev) used for managing integrations.
[COMMAND_EXECUTION]: The skill uses the membrane CLI to perform operations such as searching for connectors, managing connections, and executing actions. These are standard operations for this platform integration.
[DATA_EXFILTRATION]: The skill follows secure patterns by recommending that agents let Membrane handle authentication server-side, explicitly stating that they should never ask the user for API keys or tokens.
[PROMPT_INJECTION]: The skill contains an ingestion surface for indirect prompt injection as it processes data from external PixieBrix actions and connection lists.
Ingestion points: Output from membrane action list, membrane connection list, and membrane action run commands (SKILL.md).
Boundary markers: None explicitly defined in the instructions.
Capability inventory: Shell command execution via the membrane CLI (SKILL.md).
Sanitization: No specific sanitization or escaping logic is described for the command-line outputs before they are processed by the agent.

pixiebrix