qwen-image-2-pro
Pass
Audited by Gen Agent Trust Hub on Sep 14, 2026
Risk Level: SAFEEXTERNAL_DOWNLOADSINDIRECT_PROMPT_INJECTION
Full Analysis
- [EXTERNAL_DOWNLOADS]: The skill references and provides links to download installation guidelines and documentation from the inference-sh organization's public GitHub repository and official website.
- [INDIRECT_PROMPT_INJECTION]: The skill establishes an attack surface by ingesting user-provided text as prompts for image generation.
- Ingestion points: User-supplied strings passed to the
promptparameter in CLI commands and Python SDK calls within SKILL.md. - Boundary markers: None identified; instructions do not explicitly advise the agent to use delimiters or ignore instructions embedded within the image prompt.
- Capability inventory: The skill uses the Bash tool to execute the
beltCLI, which performs network operations to reach the inference.sh API. - Sanitization: No explicit sanitization or validation of the prompt content is described in the skill instructions.
Audit Metadata