nano-banana-pro

Pass

Audited by Gen Agent Trust Hub on Feb 15, 2026

Risk Level: LOWCREDENTIALS_UNSAFEPROMPT_INJECTION
Full Analysis
  • [CREDENTIALS_UNSAFE] (LOW): The script allows passing the Gemini API key via a command-line argument (--api-key). This is a security anti-pattern as it can expose secrets in process listings (e.g., ps aux) and shell history files.\n
  • Evidence: get_api_key function in scripts/generate_image.py and usage instructions in SKILL.md.\n- [PROMPT_INJECTION] (LOW): The skill passes user-provided prompts directly to an external Image Generation API without sanitization. While the resulting image is simply saved to disk, an attacker could use this to attempt to bypass the underlying API's safety filters.\n
  • Evidence: contents = args.prompt in scripts/generate_image.py.\n- [INDIRECT_PROMPT_INJECTION] (LOW): The skill has an attack surface for indirect injection as it processes untrusted prompts and input images.\n
  • Ingestion points: args.prompt and args.input_image in scripts/generate_image.py.\n
  • Boundary markers: Absent in code; only soft guidance provided in SKILL.md templates.\n
  • Capability inventory: File system read (PILImage.open), File system write (image.save), and Network access (google-genai client).\n
  • Sanitization: None detected. Severity is LOW as the output (a PNG file) has limited influence on downstream automated decisions.
Audit Metadata
Risk Level
LOW
Analyzed
Feb 15, 2026, 09:46 PM