The Agent Skills Directory

[EXTERNAL_DOWNLOADS]: The skill installs the @membranehq/cli package from npm and uses npx to execute it. This is the official tool for the Membrane platform, provided by the skill's authoring organization.
[COMMAND_EXECUTION]: The skill utilizes the membrane command-line interface to manage authentication (membrane login), established connections (membrane connect), and execute machine learning workflow actions (membrane action run).
[PROMPT_INJECTION]: The skill possesses a surface for indirect prompt injection through the ingestion of external data.
Ingestion points: Untrusted data enters the agent context via the output of the membrane action run command (SKILL.md).
Boundary markers: No explicit delimiters or boundary markers are defined in the instructions to separate external content from agent instructions.
Capability inventory: The skill has the ability to list connections, search for actions, and run arbitrary actions on the Cnvrg.io platform (SKILL.md).
Sanitization: No specific sanitization or validation steps are outlined for processing the data received from external API actions.

cnvrgio