ClawHub
Back to skill

Security audit

corespeed-nanobanana

Security checks across malware telemetry and agentic risk

Overview

This skill appears to be a normal Gemini image and text generation helper, with expected external API use and local file outputs.

Install only if you trust the configured Corespeed gateway and the API token account it uses. Do not send confidential prompts or private images unless you are comfortable with them being processed by the external Gemini gateway, and consider pinning dependencies in stricter environments.

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
92% confidence
Finding
The skill declares operational requirements and clearly uses environment variables, reads local input images, and writes generated output files, but it does not declare permissions for those capabilities. Missing permission declarations reduce transparency and can bypass user or platform expectations about what the skill may access, especially because it handles local files and secrets used to reach an external service.

Missing User Warnings

Medium
Confidence
95% confidence
Finding
The skill sends prompts and potentially user-supplied images to the Corespeed AI Gateway and downstream Gemini models, but the user-facing description does not prominently warn that this data leaves the local environment. This creates a privacy and data-handling risk because users may provide sensitive text or images without informed consent about third-party processing.

VirusTotal

65/65 vendors flagged this skill as clean.

View on VirusTotal

Static analysis

No suspicious patterns detected.