qwen-image-2-pro
Pass
Audited by Gen Agent Trust Hub on Sep 2, 2026
Risk Level: SAFEEXTERNAL_DOWNLOADSCOMMAND_EXECUTION
Full Analysis
- [EXTERNAL_DOWNLOADS]: The skill references installation scripts and documentation from
raw.githubusercontent.com/inference-sh/skills/. This is a standard practice for this skill's ecosystem to manage dependencies. - [COMMAND_EXECUTION]: The skill provides examples using the
beltCLI tool andnpx skills addcommands. These are intended for setting up the environment and executing the primary function of the skill (image generation). - [INDIRECT_PROMPT_INJECTION]: The skill processes user-provided prompts to generate images. While prompts are interpolated into CLI and SDK calls, the risk is limited to the output of the image generation service itself, and there are no high-privilege tool capabilities that could be exploited via injection in this context.
Audit Metadata