skills/jscraik/agent-skills/sora/Gen Agent Trust Hub

sora

Pass

Audited by Gen Agent Trust Hub on Apr 12, 2026

Risk Level: SAFE
Full Analysis
  • [SAFE]: The skill utilizes the official OpenAI Python SDK to communicate with OpenAI's video generation endpoints, which are well-known and trusted services.
  • [SAFE]: Credentials are managed securely via the OPENAI_API_KEY environment variable. The skill includes explicit warnings against hardcoding secrets or pasting keys into chat.
  • [SAFE]: File system access is scoped to legitimate operations, such as reading user-provided prompt files or reference images and writing generated video assets to local paths.
  • [EXTERNAL_DOWNLOADS]: The skill requires the openai package, which is a standard library from a well-known technology provider.
  • [COMMAND_EXECUTION]: Logic is implemented in a local Python script (scripts/sora.py) that avoids dangerous functions such as eval(), exec(), or arbitrary subprocess execution.
Audit Metadata
Risk Level
SAFE
Analyzed
Apr 12, 2026, 01:12 PM
Security Audit — agent-trust-hub — sora