qwen-image-2
Pass
Audited by Gen Agent Trust Hub on Mar 10, 2026
Risk Level: SAFE
Full Analysis
- [COMMAND_EXECUTION]: The skill utilizes the
infshCLI tool for image generation, model listing, and authentication. Command access is strictly restricted to the vendor-specificinfshbinary via theallowed-toolsconfiguration. - [EXTERNAL_DOWNLOADS]: The skill references resources and documentation from the official
inference.shdomain and demonstrates the use ofnpxto manage related vendor-provided skills. - [DATA_EXFILTRATION]: All network activity is directed to the vendor's infrastructure (
inference.sh) as required for the primary functionality of the skill. No unauthorized access to sensitive local files or data exfiltration to third-party domains was detected.
Audit Metadata