qwen-image-2
Pass
Audited by Gen Agent Trust Hub on Sep 8, 2026
Risk Level: SAFEEXTERNAL_DOWNLOADSCOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
- [EXTERNAL_DOWNLOADS]: The skill directs users to the official
inference-shGitHub repository for installation documentation and additional skill modules using standardnpxcommands. - [COMMAND_EXECUTION]: The skill utilizes the
beltcommand-line interface via theBashtool to interact with Alibaba's image generation models. - [INDIRECT_PROMPT_INJECTION]: The skill processes user-supplied text for image generation and editing, which is passed to the CLI within a JSON structure.
- Ingestion points: User prompts and negative prompts used in command examples (e.g., in
SKILL.md). - Boundary markers: Input strings are encapsulated within JSON objects.
- Capability inventory: The skill is scoped to execute the
beltCLI tool for remote image processing. - Sanitization: Relies on the agent's shell execution safety and the underlying CLI's internal input handling.
Audit Metadata