The Agent Skills Directory

[COMMAND_EXECUTION]: The skill utilizes the membrane CLI to interact with TeamGantt. It performs operations such as listing connections, searching for available actions, and running project-related actions like task management.
[EXTERNAL_DOWNLOADS]: The instructions direct users to install the @membranehq/cli package from npm. This is the official tool provided by the vendor (membranedev) for the platform the skill is designed to work with.
[PROMPT_INJECTION]: The skill possesses a surface for indirect prompt injection because it retrieves and processes project data from TeamGantt, such as task names and comments, which could potentially contain malicious instructions.
Ingestion points: Data is ingested via TeamGantt API responses through membrane action run and membrane request commands.
Boundary markers: The instructions do not specify any delimiters or safety warnings for the agent to use when processing external data.
Capability inventory: The agent can perform a variety of actions including reading and writing data to TeamGantt and executing CLI commands.
Sanitization: There are no explicit sanitization steps described to validate or filter data retrieved from TeamGantt records.

teamgantt