The Agent Skills Directory

[EXTERNAL_DOWNLOADS]: The skill instructs the user to install the official @membranehq/cli package from npm, which is the verified tool provided by the vendor (Membrane) for managing connections and actions.
[COMMAND_EXECUTION]: The skill utilizes the membrane CLI to perform authenticated operations such as searching for actions and executing API requests. These commands are part of the intended functionality for the integration.
[PROMPT_INJECTION]: The skill processes data from Easy Project (e.g., issues and projects), which serves as an indirect prompt injection surface. Ingestion points: Data is retrieved from the Easy Project API via membrane action run and membrane request. Boundary markers: No explicit boundary markers are defined for external data. Capability inventory: The skill allows shell command execution via the membrane CLI and network requests via the vendor's proxy. Sanitization: No specific sanitization of external content is described, though the skill relies on the vendor's managed infrastructure.

easy-project