nano-banana-2

Pass

Audited by Gen Agent Trust Hub on Aug 7, 2026

Risk Level: SAFE
Full Analysis
  • [EXTERNAL_DOWNLOADS]: Fetches installation guidelines and skill components from the vendor's official GitHub repository (inference-sh).
  • [COMMAND_EXECUTION]: Utilizes the belt CLI tool for model interaction. The skill's execution environment is restricted to this specific tool via the allowed-tools configuration.
  • [PROMPT_INJECTION]: Processes user-provided text prompts and images for generative tasks. This represents a standard surface for indirect prompt injection common to generative AI tools, but uses structured JSON for input delivery.
  • Ingestion points: User-provided prompt and images parameters in SKILL.md examples.
  • Boundary markers: Uses JSON structure (--input '{"prompt": ...}') to delimit user input from command parameters.
  • Capability inventory: Uses the belt command for remote model execution.
  • Sanitization: None explicitly defined in the instructions; relies on the underlying CLI and model provider's safety filters.
Audit Metadata
Risk Level
SAFE
Analyzed
Aug 7, 2026, 06:32 PM
Security Audit — agent-trust-hub — nano-banana-2