nano-banana

Pass

Audited by Gen Agent Trust Hub on Jul 22, 2026

Risk Level: SAFEEXTERNAL_DOWNLOADSCOMMAND_EXECUTION
Full Analysis
  • [EXTERNAL_DOWNLOADS]: The skill references and fetches content from vendor-controlled sources, including installation instructions from the inference-sh GitHub repository and documentation/images from the inference.sh domain.
  • [COMMAND_EXECUTION]: The skill utilizes the belt CLI tool to run image generation applications and uses npx skills add to install the necessary toolsets and related capabilities from the same author (infsh-skills). These are standard operational commands for this platform.
  • [DATA_EXFILTRATION]: Network operations are limited to the intended functionality of the skill, which involves sending user-provided prompts to the inference.sh API for image generation. No access to sensitive local files or credentials was detected.
Audit Metadata
Risk Level
SAFE
Analyzed
Jul 22, 2026, 11:51 AM
Security Audit — agent-trust-hub — nano-banana