nano-banana-2
Pass
Audited by Gen Agent Trust Hub on Mar 11, 2026
Risk Level: SAFECOMMAND_EXECUTIONEXTERNAL_DOWNLOADS
Full Analysis
- [COMMAND_EXECUTION]: The skill uses the
infshcommand-line tool to perform inference on the Inference.sh platform. The commands are structured correctly to pass user prompts and parameters to the API. - [EXTERNAL_DOWNLOADS]: The documentation references the installation of the
infshCLI tool and additional skills from theinference-shorganization. These are official tools required for the skill's operation. - [PROMPT_INJECTION]: The skill processes user-supplied prompts for image generation. This represents a standard input surface for AI models, and safety is managed by the remote service provider's model filters.
Audit Metadata