The Agent Skills Directory

[EXTERNAL_DOWNLOADS]: The skill instructs the installation of the @membranehq/cli package, which is the official command-line interface for the vendor's platform.- [COMMAND_EXECUTION]: Employs the membrane CLI to manage authentication, list actions, and execute requests against the Productive.io API.- [PROMPT_INJECTION]: The skill exhibits an indirect prompt injection surface as it ingests data from external Productive.io API endpoints and possesses capabilities to write data back to the service. Ingestion points: Results from membrane action run and membrane request commands. Boundary markers: None specified in the instructions. Capability inventory: membrane action run for executing pre-defined actions and membrane request for arbitrary API calls. Sanitization: No explicit sanitization or validation of the retrieved external content is described before it enters the agent context.

productiveio