AI Video Generation
Pass
Audited by Gen Agent Trust Hub on Jun 6, 2026
Risk Level: SAFE
Full Analysis
- [EXTERNAL_DOWNLOADS]: The skill provides documentation for using various well-known AI video generation services including OpenAI, Google Vertex AI, Runway, Luma, Fal, Replicate, Vidu, and Tencent MPS. These are recognized as well-known technology services and their use for the skill's primary purpose is appropriate.
- [EXTERNAL_DOWNLOADS]: The documentation mentions standard open-source libraries (diffusers, transformers, accelerate) and models from reputable sources (Stability AI, Wan-Video, Tencent-Hunyuan) which are well-known in the AI research community.
- [COMMAND_EXECUTION]: The skill includes shell commands for environment setup and verification, such as checking for the existence of environment variables and creating local directories for workspace management (e.g.,
mkdir -p ~/video-generation). These operations are transparent, limited to the user's home directory, and perform standard configuration tasks. - [CREDENTIALS_UNSAFE]: The skill correctly handles sensitive credentials by referencing environment variables (e.g.,
OPENAI_API_KEY,RUNWAY_API_KEY) rather than hardcoding secrets. It includes a safe verification script that checks for the presence of these variables without revealing their values. - [DATA_EXFILTRATION]: Data transfer is limited to sending prompt text and reference media to the specific AI providers requested by the user. The skill explicitly identifies what data is sent externally and what remains local, adhering to privacy best practices.
Audit Metadata