nanobanana-prompt-writer
Pass
Audited by Gen Agent Trust Hub on Mar 1, 2026
Risk Level: SAFENO_CODE
Full Analysis
- [SAFE]: No malicious behavior or security vulnerabilities were identified. The skill serves as a guide for generating prompts for the Nano Banana (Gemini) image generation models.
- [NO_CODE]: The skill is composed strictly of Markdown documentation and templates.
- Evidence: All files (SKILL.md, resources/references.md, resources/templates.md) are Markdown text files with no executable components.
- [EXTERNAL_DOWNLOADS]: References to external resources are restricted to trusted official documentation.
- Evidence: The URLs point to ai.google.dev and dev.to/googleai, which are official developer portals for Google AI.
- [DATA_EXFILTRATION]: The skill lacks any code or instructions to access the file system or perform network requests.
- Evidence: Analysis of the workflow and principles shows it only generates text responses for the user within the chat interface.
Audit Metadata