The Agent Skills Directory

[PROMPT_INJECTION]: The skill interacts with the Median API, creating an indirect prompt injection surface where data from the external service might influence agent behavior.
Ingestion points: Data enters the agent's context through membrane action run and membrane request commands.
Boundary markers: There are no explicit delimiters or instructions provided to separate external content from internal prompts.
Capability inventory: The skill has the ability to execute platform-specific commands and perform network requests via the Membrane proxy.
Sanitization: No data sanitization or validation logic is specified for retrieved content.
[EXTERNAL_DOWNLOADS]: The skill utilizes the @membranehq/cli tool, which is an official package from the vendor for platform integration.
[COMMAND_EXECUTION]: The skill employs the membrane CLI for connection setup, user authentication, and executing service actions.

median