qwen-image-2
Pass
Audited by Gen Agent Trust Hub on Apr 4, 2026
Risk Level: SAFECOMMAND_EXECUTIONEXTERNAL_DOWNLOADSPROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill uses the
infshCLI tool to interface with Alibaba image generation models. The execution scope is defined in the skill's frontmatter configuration.- [EXTERNAL_DOWNLOADS]: The instructions reference the installation of theinfshCLI and additional skills from the vendor's official GitHub repository and vianpxcommands.- [PROMPT_INJECTION]: The skill accepts user-provided text prompts and image URLs, which constitutes an indirect prompt injection surface typical for generative AI tools. - Ingestion points: User data enters via the
promptandreference_imagesparameters in the JSON input for theinfshcommand. - Boundary markers: The skill uses JSON formatting to structure the input data.
- Capability inventory: The primary capability is executing the
infshtool to run remote AI applications. - Sanitization: There is no explicit sanitization described for the user-supplied prompt text.
Audit Metadata