qwen-image-2
Pass
Audited by Gen Agent Trust Hub on May 19, 2026
Risk Level: SAFECOMMAND_EXECUTIONEXTERNAL_DOWNLOADS
Full Analysis
- [SAFE]: The skill provides standard documentation for integrating the Qwen-Image model into the inference-sh ecosystem. No malicious code or obfuscation techniques were identified.
- [COMMAND_EXECUTION]: The skill uses the 'belt' CLI tool for authenticating and running image generation applications. These commands are consistent with the platform's intended use and are clearly documented for the user.
- [EXTERNAL_DOWNLOADS]: Links to installation scripts and documentation are hosted on the vendor's official GitHub organization (inference-sh). These are trusted resources within the scope of this skill's development.
- [PROMPT_INJECTION]: The skill handles untrusted data through generation prompts and image URLs (Category 8 surface).
- Ingestion points: 'prompt' and 'reference_images' in SKILL.md
- Boundary markers: Not explicitly specified in command examples
- Capability inventory: Execution of the 'belt' CLI tool
- Sanitization: Managed by the CLI tool and the upstream inference-sh API platform.
Audit Metadata