The Agent Skills Directory

[EXTERNAL_DOWNLOADS]: The skill requires the installation of the @membranehq/cli global npm package. This tool is provided by the authoring organization to facilitate secure authentication and API interaction.
[COMMAND_EXECUTION]: The skill relies on various CLI commands, such as membrane login, membrane connect, and membrane action run, to perform its tasks. These commands are part of the intended workflow of the platform.
[PROMPT_INJECTION]: The skill contains a metadata discrepancy and maintains an indirect prompt injection surface.
Metadata issue: The description incorrectly lists CRM objects like 'Leads' and 'Deals' as manageable entities, which does not align with Talend's primary function as a data integration and ETL platform.
Ingestion points: Data from Talend actions is brought into the agent's context through the output of the membrane action run and membrane action list commands.
Boundary markers: The skill does not provide specific boundary markers or 'ignore' instructions to help the agent distinguish between its instructions and the data retrieved from external actions.
Capability inventory: The agent has the capability to execute shell commands and create new actions via the CLI.
Sanitization: There is no mention of sanitization or filtering for the data retrieved from external sources before it is interpreted by the agent.

talend