nano-banana-prompting
Pass
Audited by Gen Agent Trust Hub on Mar 29, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: The skill follows a benign interactive workflow to assist users in prompt engineering for image generation. It uses the AskUserQuestion tool to gather requirements and generates a text-based prompt as output.
- [SAFE]: No sensitive data access, unauthorized network operations, or external code dependencies were found. The skill operates within the context of text and image descriptions.
- [SAFE]: The skill includes a reference guide (references/guide.md) containing legitimate photography and artistic techniques to improve prompt quality, with no evidence of obfuscation or malicious instructions.
- [SAFE]: While the skill ingests untrusted user input (existing prompts and descriptions), its functionality is limited to generating formatted text for subsequent image generation, which is consistent with its primary purpose and does not present an exploitable vulnerability surface.
Audit Metadata