The Agent Skills Directory

[EXTERNAL_DOWNLOADS]: The skill guides the installation of the @membranehq/cli tool from the npm registry. This is a legitimate utility from the vendor (Membrane) used for authentication and API interaction.
[COMMAND_EXECUTION]: The skill executes membrane CLI commands to manage Easy Project data. These commands are necessary for the skill's primary functionality.
[PROMPT_INJECTION]: The skill has a surface for indirect prompt injection. • Ingestion points: Data from Easy Project is ingested into the agent context via membrane CLI outputs (SKILL.md). • Boundary markers: No explicit markers or "ignore instructions" warnings are present. • Capability inventory: The membrane action run and membrane request commands allow for state-changing operations and network requests (SKILL.md). • Sanitization: No explicit sanitization or validation of external content is described.

easy-project