ClawHub
Back to skill

Security audit

Gemini Google Search

Security checks across malware telemetry and agentic risk

Overview

This is a disclosed Gemini/Google search helper that uses a Gemini API key and sends user queries to Gemini as expected.

Install this only if you are comfortable sending search queries to Google's Gemini API and using Gemini quota or billing. Prefer a least-privileged API key and an explicit 1Password field when using 1Password-backed credentials.

SkillSpector

By NVIDIA
Vulnerability Patterns
  • MCP Least PrivilegeUnderdeclared Capability, Wildcard Permission, Missing Permission Declaration
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
  • Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
Findings (1)

Lp3

Medium
Category
MCP Least Privilege
Confidence
93% confidence
Finding
The skill documentation instructs use of shell execution and access to environment/1Password-backed credentials, but it does not declare permissions to reflect those capabilities. That mismatch weakens security review and policy enforcement because an agent may invoke code with access to secrets or external services without explicit user-visible authorization boundaries.

VirusTotal

66/66 vendors flagged this skill as clean.

View on VirusTotal

Static analysis

No suspicious patterns detected.