qwen-image-2
Pass
Audited by Gen Agent Trust Hub on Sep 2, 2026
Risk Level: SAFEEXTERNAL_DOWNLOADSCOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
- [EXTERNAL_DOWNLOADS]: The skill references installation guidelines hosted on GitHub (raw.githubusercontent.com) for setting up the required CLI environment.
- [COMMAND_EXECUTION]: The skill uses the
beltCLI tool to perform operations such as model execution, app searching, and authentication. - [INDIRECT_PROMPT_INJECTION]: The skill provides a surface for indirect prompt injection as it interpolates user-provided text prompts and external image URLs into commands sent to the Alibaba Qwen models; however, this is the intended primary purpose of the skill and follows standard practices for image generation tools.
Audit Metadata