The Agent Skills Directory

[EXTERNAL_DOWNLOADS]: The skill instructs the user to install the Membrane CLI tool using the package @membranehq/cli. This is a standard installation of a tool provided by the skill's author to facilitate integration.
[COMMAND_EXECUTION]: The skill utilizes several CLI commands (e.g., membrane login, membrane connect, membrane action run) to interact with the Mentionlytics API. These commands are part of the intended functionality for managing monitoring data and automating workflows.
[PROMPT_INJECTION]: The skill processes external data such as social media mentions and web posts which could contain indirect prompt injections.
Ingestion points: Data enters the context through membrane action run and membrane request when fetching posts or reports from Mentionlytics.
Boundary markers: None explicitly defined in the provided documentation.
Capability inventory: The skill can perform network operations via membrane request and execute predefined actions via membrane action run.
Sanitization: No explicit sanitization or filtering of the fetched content is described in the skill instructions.

mentionlytics