The Agent Skills Directory

[COMMAND_EXECUTION]: The skill instructs the agent to execute curl and jq commands to interact with the Luma API and process its responses.
[COMMAND_EXECUTION]: Provides troubleshooting instructions using a vendor-specific CLI tool zero doctor for checking environment variables and connectivity to API endpoints.
[EXTERNAL_DOWNLOADS]: Fetches data from Luma's official public API (public-api.luma.com) to manage event, guest, and calendar information.
[PROMPT_INJECTION]: The skill exhibits an indirect prompt injection surface by processing data from an external source (Luma API) that may contain untrusted content.
Ingestion points: API endpoints documented in SKILL.md such as /v1/event/get-guests and /v1/calendar/list-events return data fields (names, emails, descriptions) that can be populated by third parties.
Boundary markers: The instructions lack delimiters or warnings to treat ingested API data as untrusted.
Capability inventory: The skill utilizes curl for network requests and data retrieval.
Sanitization: No evidence of sanitization or validation of the content received from the API before it is processed by the agent context.

luma