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

nano-banana-2

Pass

Audited by Gen Agent Trust Hub on Apr 14, 2026

Risk Level: SAFEPROMPT_INJECTIONCOMMAND_EXECUTIONEXTERNAL_DOWNLOADS
Full Analysis
  • [COMMAND_EXECUTION]: The skill utilizes the infsh command-line tool to interact with the inference.sh platform. This tool is explicitly listed in the allowed-tools configuration and is used for platform authentication and application execution.
  • [EXTERNAL_DOWNLOADS]: The documentation provides a link to a CLI installation guide hosted on a public GitHub repository (https://raw.githubusercontent.com/inference-sh/skills/refs/heads/main/cli-install.md). This is a standard method for distributing setup instructions.
  • [PROMPT_INJECTION]: The skill takes user-supplied text and images as input for generative tasks, which represents an attack surface for indirect prompt injection.
  • Ingestion points: The prompt and images parameters in the skill's input schema.
  • Boundary markers: No explicit delimiters or instructions are used to separate user input from system prompts.
  • Capability inventory: The skill uses the infsh CLI and the inferencesh Python SDK to perform actions.
  • Sanitization: No input validation or sanitization is described in the skill instructions.
Audit Metadata
Risk Level
SAFE
Analyzed
Apr 14, 2026, 11:26 PM