qwen-image-2
Pass
Audited by Gen Agent Trust Hub on Mar 11, 2026
Risk Level: SAFECOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
- [SAFE]: The skill follows security best practices for image generation wrappers. No evidence of obfuscation, credential theft, or persistence was found.\n- [COMMAND_EXECUTION]: The skill utilizes the
infshcommand-line tool, which is the official CLI for the inference.sh platform. This usage is restricted and consistent with the skill's stated purpose of interfacing with the Alibaba Qwen-Image API.\n- [PROMPT_INJECTION]: The skill processes user-supplied strings in thepromptfield to generate images. This is the core functionality of the skill and does not present a risk of system-level compromise or behavioral override.
Audit Metadata