qwen-image-2
Pass
Audited by Gen Agent Trust Hub on Sep 8, 2026
Risk Level: SAFEEXTERNAL_DOWNLOADSCOMMAND_EXECUTION
Full Analysis
- [EXTERNAL_DOWNLOADS]: The skill references documentation and installation scripts from
inference.sh(e.g.,https://raw.githubusercontent.com/inference-sh/skills/refs/heads/main/cli-install.md). Asinference.shis the provider of the service the skill is designed to interact with, these are considered trusted, well-known service resources and do not escalate the verdict. - [COMMAND_EXECUTION]: The skill documents the use of the
beltCLI tool for generating images. These commands are illustrative of the skill's primary purpose and use the standardbelt app runsyntax for interfacing with the Alibaba Qwen-Image API. - [SAFE]: No obfuscation, credential exfiltration, prompt injection, or suspicious persistence mechanisms were detected. The use of external images in examples points to standard image-to-image or multi-reference image generation workflows.
Audit Metadata