nanobanana-2-image-generation

Pass

Audited by Gen Agent Trust Hub on Mar 11, 2026

Risk Level: SAFEEXTERNAL_DOWNLOADSCOMMAND_EXECUTIONDATA_EXFILTRATIONPROMPT_INJECTION
Full Analysis
  • [EXTERNAL_DOWNLOADS]: The skill makes requests to Google's Generative Language API to perform image generation and editing tasks.
  • Evidence: scripts/nanobanana-cli.js uses the global fetch API to communicate with https://generativelanguage.googleapis.com/v1beta/models/.
  • [COMMAND_EXECUTION]: The skill uses a local Node.js script as a wrapper to execute generation workflows.
  • Evidence: scripts/nanobanana-cli.js is the primary execution tool for processing prompts and images.
  • [DATA_EXFILTRATION]: User-provided prompts and local reference images are sent to Google's infrastructure for processing.
  • Evidence: The CLI script reads local files via fs.readFileSync and includes their Base64-encoded content in the JSON payload sent to the API.
  • [PROMPT_INJECTION]: The CLI script includes logic to dynamically extract an output directory path from the user's natural language prompt.
  • Ingestion points: User prompt argument in scripts/nanobanana-cli.js.
  • Boundary markers: No explicit markers are used to isolate the path-extraction logic from adversarial prompt content.
  • Capability inventory: fs.mkdirSync and fs.writeFileSync are used in scripts/nanobanana-cli.js to create directories and write files based on inferred paths.
  • Sanitization: The script uses path.resolve and ignores strings that look like URLs, though it does not implement a strict whitelist of allowed directories.
Audit Metadata
Risk Level
SAFE
Analyzed
Mar 11, 2026, 09:29 AM