ClawHub
Back to skill

Security audit

Nano Banana Pro

Security checks for vulnerabilities and agentic risk

Overview

This is a straightforward image-generation/editing skill that uses a Gemini API key and optionally uploads a user-selected image to Google to produce an output image.

Install only if you are comfortable sending image prompts and any selected input images to Google's Gemini service. Avoid using private, regulated, or confidential images unless that is acceptable for your use case, and prefer GEMINI_API_KEY over pasting an API key directly into chat or command arguments.

SkillSpector

Vulnerability Patterns
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
  • MCP Least PrivilegeUnderdeclared Capability, Wildcard Permission, Missing Permission Declaration
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
Findings (4)

Lp3

Medium
Category
MCP Least Privilege
Confidence
89% confidence
Finding
The skill instructs use of an API key via --api-key or GEMINI_API_KEY, which means it can access sensitive environment-backed secrets, but the metadata shown does not declare permissions or clearly bound that capability. Undeclared secret access increases the chance of accidental exposure, misuse, or execution in contexts where users did not realize credentials would be consumed.

Vague Triggers

Medium
Confidence
84% confidence
Finding
The description says to use the skill for image create/modify requests generally, which is broad enough to match many ordinary user requests without a clear trigger boundary. Overbroad invocation can cause the agent to route prompts and possibly local images to this external skill unexpectedly, increasing privacy and data-handling risk.

Missing User Warnings

Medium
Confidence
96% confidence
Finding
The documentation states the skill uses Google's Nano Banana Pro API but does not clearly warn that user prompts and any input images are transmitted to an external Google service. This omission can lead to unintended disclosure of sensitive text, private files, or copyrighted/confidential images to a third party.

Missing User Warnings

Medium
Confidence
88% confidence
Finding
The script sends the user prompt and, when provided, the local input image to Google's external API, but it does not clearly warn users that potentially sensitive content will leave the local machine. In an image-editing skill, users may reasonably provide private photos or confidential visual material, so the lack of an explicit transmission/privacy notice creates a real data exposure risk even though the behavior is core to the feature.

Static analysis

No suspicious patterns detected.