Skills
Navigate
skills/magentosh/superpowers/nano-banana-2/Gen Agent Trust Hub

nano-banana-2

Pass

Audited by Gen Agent Trust Hub on Aug 28, 2026

Risk Level: SAFEEXTERNAL_DOWNLOADSCOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
  • [EXTERNAL_DOWNLOADS]: The skill references installation instructions and additional skills from the inference-sh organization on GitHub. These are standard dependencies for the platform's ecosystem.
  • [COMMAND_EXECUTION]: The skill uses the belt CLI tool to execute remote image generation tasks. These commands are restricted to the google/gemini-3-1-flash-image-preview application as defined in the examples.
  • [INDIRECT_PROMPT_INJECTION]: The skill processes user-supplied data, such as text prompts and remote image URLs, which are sent to an external model.
  • Ingestion points: User-provided prompt and images fields in the belt app run command.
  • Boundary markers: None identified in the instruction templates.
  • Capability inventory: The skill uses Bash(belt *) to run remote inference apps.
  • Sanitization: No explicit sanitization of input strings is mentioned before they are passed to the CLI.
Audit Metadata
Risk Level
SAFE
Analyzed
Aug 28, 2026, 01:13 PM
Security Audit — agent-trust-hub — nano-banana-2