stable-diffusion
Pass
Audited by Gen Agent Trust Hub on Jun 23, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: No malicious patterns such as prompt injection, data exfiltration, or obfuscation were detected. The skill's content is consistent with its stated purpose of enabling local image generation.
- [EXTERNAL_DOWNLOADS]: The skill references model weights hosted on Hugging Face (e.g., runwayml/stable-diffusion-v1-5, stabilityai/stable-diffusion-xl-base-1.0). These are well-known, official repositories for the models described.
- [COMMAND_EXECUTION]: The skill provides installation instructions using standard package management (pip install) for established machine learning libraries (diffusers, transformers, accelerate, torch).
Audit Metadata