qwen-image-2-pro
Pass
Audited by Gen Agent Trust Hub on Mar 25, 2026
Risk Level: SAFE
Full Analysis
- [COMMAND_EXECUTION]: The skill utilizes the
infshCLI tool to perform image generation. This tool is explicitly restricted in theallowed-toolsconfiguration, ensuring the agent operates within a defined scope. - [EXTERNAL_DOWNLOADS]: The documentation references the vendor's official CLI installation guide and the
inferenceshPython SDK. These resources are part of the service provider's standard ecosystem. - [DATA_EXFILTRATION]: No unauthorized data access or exfiltration patterns were detected. Network operations are limited to interacting with the legitimate API endpoints of the image generation service.
- [SAFE]: Analysis of the instructions and examples revealed no evidence of prompt injection, obfuscation, or persistence mechanisms. The skill's behavior aligns with its described purpose of generating images via the Qwen model.
Audit Metadata