luma-ai
Pass
Audited by Gen Agent Trust Hub on Jun 14, 2026
Risk Level: SAFECOMMAND_EXECUTIONEXTERNAL_DOWNLOADS
Full Analysis
- [COMMAND_EXECUTION]: The skill instructs the agent to use
curlandjqfor interacting with the official Luma AI API (api.lumalabs.ai). These commands are standard for API-based integrations. - [EXTERNAL_DOWNLOADS]: The skill includes steps to download generated video and image files from Luma AI's infrastructure once generation is completed.
- [DATA_EXFILTRATION]: User prompts and image URLs are transmitted to Luma AI's API endpoints. This behavior is consistent with the skill's primary purpose and uses a pre-configured environment variable for authorization.
Audit Metadata