pp-luma
Pass
Audited by Gen Agent Trust Hub on Jul 14, 2026
Risk Level: SAFEEXTERNAL_DOWNLOADSDATA_EXFILTRATIONPROMPT_INJECTION
Full Analysis
- [EXTERNAL_DOWNLOADS]: The skill provides instructions for installing the
luma-pp-cliandluma-pp-mcptools. Installation methods includego installfromgithub.com/mvanhorn/printing-press-libraryandnpxfrom@mvanhorn/printing-press-library. These resources are associated with the project vendor, mvanhorn. - [DATA_EXFILTRATION]: The CLI tool includes a
--deliverflag with support forwebhook:<url>. This capability allows command output to be automatically POSTed to an external URL, providing a mechanism for data to leave the agent environment. - [PROMPT_INJECTION]: The skill identifies a surface for indirect prompt injection due to its handling of external API data. Ingestion points: Data is fetched from
api.luma.com(event details, descriptions, and community information) using theevents list,events get, andcalendarscommands. Boundary markers: There are no explicit delimiters or instructions provided to the agent to distinguish between the fetched data and its internal instructions. Capability inventory: The skill allows file writing (--outandfile:<path>) and network requests (webhook:<url>), and it utilizes theRead Bashtool to execute the CLI. Sanitization: No validation or escaping of the content retrieved from the external API is mentioned in the skill definition.
Audit Metadata