nano-banana2

Fail

Audited by Gen Agent Trust Hub on May 18, 2026

Risk Level: HIGHCREDENTIALS_UNSAFECOMMAND_EXECUTION
Full Analysis
  • [CREDENTIALS_UNSAFE]: The scripts scripts/img2img.py and scripts/nano_banana2.py both contain a hardcoded Google Gemini API key (AIzaSyBn_AbjUeM4ZRcOOihp4Jdkt4sRdo--Kak). Storing API keys in plain text within scripts is a high-risk practice as it allows unauthorized access to the service and potential cost or quota abuse.\n- [COMMAND_EXECUTION]: The execution logic in SKILL.md invokes Python scripts using shell commands that interpolate the user's prompt into a quoted string (e.g., --prompt \"用户的图片描述\"). This method is vulnerable to shell command injection if a user provides a prompt containing shell metacharacters (such as backticks, semicolons, or dollar signs), which could lead to arbitrary code execution on the host machine.
Recommendations
  • AI detected serious security threats
Audit Metadata
Risk Level
HIGH
Analyzed
May 18, 2026, 09:35 AM
Security Audit — agent-trust-hub — nano-banana2