sora
Pass
Audited by Gen Agent Trust Hub on Jun 15, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: The skill implements a standard wrapper for the OpenAI Sora API. It uses a bundled Python script (
scripts/sora.py) to manage API requests and file operations. - [COMMAND_EXECUTION]: The skill utilizes a local Python CLI tool to execute video generation and management tasks. The commands are well-defined and use the official OpenAI SDK.
- [EXTERNAL_DOWNLOADS]: The skill allows users to download generated video assets, thumbnails, and spritesheets from OpenAI's official API endpoints.
- [DATA_EXFILTRATION]: The skill transmits user-provided prompts and media assets to OpenAI for processing. This is the primary purpose of the skill and uses well-known, trusted API endpoints.
- [PROMPT_INJECTION]: The skill includes instructions for the agent to augment and structure user prompts before sending them to the Sora API. This is a legitimate feature for improving video generation quality and does not represent a security risk to the agent itself.
Audit Metadata