nano-banana
Pass
Audited by Gen Agent Trust Hub on Sep 2, 2026
Risk Level: SAFEEXTERNAL_DOWNLOADSINDIRECT_PROMPT_INJECTION
Full Analysis
- [EXTERNAL_DOWNLOADS]: The skill provides links to installation guides and documentation hosted on
github.com/inference-shand theinference.shdomain. These resources are for the setup of the legitimatebeltCLI tool used by the skill. - [INDIRECT_PROMPT_INJECTION]: The skill involves ingesting user-provided prompts and external image URLs to be processed by an AI model. This ingestion point represents a surface where untrusted data enters the agent's context, although the functionality is restricted to image generation parameters.
Audit Metadata