qwen-image-pro
Pass
Audited by Gen Agent Trust Hub on Mar 8, 2026
Risk Level: SAFE
Full Analysis
- [EXTERNAL_DOWNLOADS]: The skill references the 'inferencesh' Python library and the '@agent-tools' skill package. Both are official resources provided by the vendor (inference.sh) for platform integration.
- [COMMAND_EXECUTION]: Usage of the 'infsh' CLI tool is explicitly restricted within the 'allowed-tools' metadata, ensuring the agent only executes authorized vendor-specific commands.
- [DATA_EXFILTRATION]: Network communication is directed solely to the vendor's API domains (inference.sh) for the purpose of image generation and authentication, which is consistent with the skill's stated functionality.
Audit Metadata