nano-banana
Fail
Audited by Gen Agent Trust Hub on Mar 9, 2026
Risk Level: HIGHEXTERNAL_DOWNLOADSREMOTE_CODE_EXECUTIONCOMMAND_EXECUTIONCREDENTIALS_UNSAFEPROMPT_INJECTION
Full Analysis
- [EXTERNAL_DOWNLOADS]: The skill requires installing a global NPM package
@google/gemini-cliand an extension from an untrusted GitHub repository (https://github.com/gemini-cli-extensions/nanobanana). - [REMOTE_CODE_EXECUTION]: The process of installing the
nanobananaextension via a URL from an untrusted organization (gemini-cli-extensions) constitutes a remote code execution risk, as the downloaded code is executed in the local environment. - [COMMAND_EXECUTION]: The instructions mandate the use of the
--yoloflag for all commands, which is described as a method to 'auto-approve all tool actions' and bypass confirmation prompts. This explicitly instructs the agent to ignore safety guardrails. - [CREDENTIALS_UNSAFE]: Setup steps encourage users to export their
GEMINI_API_KEYas a plain-text environment variable, which can lead to credential leakage via shell history or other system logs. - [PROMPT_INJECTION]: The skill includes instructions like 'REQUIRED for all image generation requests' and 'ALWAYS use this skill,' attempting to override the agent's decision-making and force it into using these insecure tools.
Recommendations
- AI detected serious security threats
Audit Metadata