nano-banana-2
Pass
Audited by Gen Agent Trust Hub on Aug 31, 2026
Risk Level: SAFEEXTERNAL_DOWNLOADSCOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
- [EXTERNAL_DOWNLOADS]: The skill references a CLI installation guide hosted on the inference-sh GitHub repository and suggests installing the belt-sh/cli package.
- [COMMAND_EXECUTION]: The skill uses the belt command-line utility for model inference, account authentication, and sample generation.
- [INDIRECT_PROMPT_INJECTION]: The skill ingests user-supplied text prompts and image URLs which are passed to the inference platform. The use of JSON structures for inputs provides boundary markers for the data entering the agent context.
Audit Metadata