nano-banana-2
Pass
Audited by Gen Agent Trust Hub on Mar 7, 2026
Risk Level: SAFECOMMAND_EXECUTIONEXTERNAL_DOWNLOADSPROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill executes the
infshcommand-line interface to interact with the inference.sh API for image generation and editing tasks. This is the core intended functionality of the skill.- [EXTERNAL_DOWNLOADS]: The documentation references the installation of theinfshCLI tool and theinferenceshPython SDK. These resources are hosted on standard package registries and are associated with the official service provider.- [PROMPT_INJECTION]: The skill processes a user-suppliedpromptthrough the Gemini model. This represents an indirect prompt injection surface, where malicious instructions embedded in the input data could potentially influence the image generation process, though this is a standard characteristic of generative AI tools.
Audit Metadata