The Agent Skills Directory

[INDIRECT_PROMPT_INJECTION]: The skill is designed to ingest and process data from SuiteDash, which is an external source capable of containing untrusted content.
Ingestion points: Data returned from the SuiteDash API via membrane action run and membrane request is processed by the agent (SKILL.md).
Boundary markers: The instructions do not define clear delimiters or specific instructions for the agent to ignore or isolate instructions potentially embedded in the retrieved data.
Capability inventory: The skill provides the agent with capabilities to execute shell commands (membrane) and make arbitrary network requests through the Membrane proxy (SKILL.md).
Sanitization: No explicit sanitization or validation steps are prescribed for the external data before ingestion.
[EXTERNAL_DOWNLOADS]: The skill instructions include downloading external packages to set up the environment.
Evidence: The skill directs the user or agent to install the Membrane CLI using npm install -g @membranehq/cli@latest (SKILL.md).
[COMMAND_EXECUTION]: The skill operates primarily by executing commands through the Membrane CLI.
Evidence: Usage of membrane login, membrane connection, membrane action, and membrane request to interact with the service (SKILL.md).

suitedash