ClawHub
Back to skill

Security audit

Gemini Image Simple

Security checks across malware telemetry and agentic risk

Overview

This skill appears to do what it claims: it sends prompts and optional images to Google's Gemini API and saves the generated image locally.

Install only if you are comfortable sending prompts, selected input images, and related request data to Google's Gemini API under your API key. Use a key intended for this purpose, monitor quota or billing, and avoid submitting confidential, regulated, or private images unless that external processing is acceptable.

SkillSpector

By NVIDIA
Vulnerability Patterns
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • MCP Least PrivilegeUnderdeclared Capability, Wildcard Permission, Missing Permission Declaration
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
  • Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
Findings (2)

Lp3

Medium
Category
MCP Least Privilege
Confidence
93% confidence
Finding
The skill requires an API key and performs network calls, but the skill metadata declares only an environment requirement and does not explicitly surface the effective capabilities/permissions. This creates a transparency and review gap: users or hosting systems may not realize the skill can transmit prompts and image data externally, increasing the chance of unintended data exposure.

Missing User Warnings

Medium
Confidence
97% confidence
Finding
The documentation explains how to generate and edit images but does not clearly warn that prompts and uploaded input images are sent to Google's Gemini API over the network. Users may unknowingly submit sensitive text or private images to a third party, leading to confidentiality and compliance risks in locked-down or privacy-sensitive environments.

VirusTotal

66/66 vendors flagged this skill as clean.

View on VirusTotal

Static analysis

No suspicious patterns detected.