The Agent Skills Directory

[COMMAND_EXECUTION]: The skill operates by instructing the agent to run membrane CLI commands for discovery, connection, and action execution. This standard workflow relies on the Membrane environment for secure execution.
[EXTERNAL_DOWNLOADS]: The instructions prompt the installation of the @membranehq/cli tool from NPM. This is an official utility provided by the skill's author (membranedev) and is a recognized vendor resource.
[PROMPT_INJECTION]: The description field in the skill's metadata incorrectly references CRM objects like 'Deals', 'Leads', and 'Pipelines'. This appears to be a documentation copy-paste error from a different skill template rather than a malicious attempt to deceive, but it results in a mismatch between stated metadata and actual event-management functionality.
[INDIRECT_PROMPT_INJECTION]: The skill ingests external data from Eventee, such as attendee registrations and participant details, using commands like membrane action run.
Ingestion points: Data enters the context via membrane action run and membrane request outputs (SKILL.md).
Boundary markers: None are specified in the instructions for the agent to use when processing these outputs.
Capability inventory: The agent can execute shell commands via the membrane CLI and perform network requests through the proxy.
Sanitization: There is no mention of validation or sanitization for data retrieved from the Eventee API before it is processed by the agent.

eventee