nano-banana-pro

Pass

Audited by Gen Agent Trust Hub on Aug 1, 2026

Risk Level: SAFE
Full Analysis
  • [PROMPT_INJECTION]: The skill maintains an indirect prompt injection surface by ingesting external data (user-defined prompts and local image files) for processing by an LLM.
  • Ingestion points: User prompts passed via the --prompt argument and image files loaded via --input-image in scripts/generate_image.py.
  • Boundary markers: Absent. The skill does not employ specific delimiters to isolate user data from instructions when calling the generative model.
  • Capability inventory: The script possesses the capability to read local files and write images to user-specified paths on the file system.
  • Sanitization: No explicit sanitization or filtering is performed on the input prompt text or image content before it is processed by the API.
Audit Metadata
Risk Level
SAFE
Analyzed
Aug 1, 2026, 08:32 AM
Security Audit — agent-trust-hub — nano-banana-pro