ClawHub
Back to skill

Security audit

GSearch - Free Google Search MCP

Security checks for vulnerabilities and agentic risk

Overview

The skill is a coherent Google Search MCP integration, with a notable but disclosed dependency and OAuth trust risk.

Install this only if you trust the @daanielcruz/gsearch-mcp package and are comfortable signing in with Google through a local MCP server. Review the Google OAuth consent screen, prefer a pinned or reviewed package version when available, and run it in a least-privileged environment if possible.

A.I.G

Vulnerability Patterns
  • Insecure DependenciesIntroduces malicious components through unsafe dependency sources
  • Skill Instruction HijackingAlters the agent's session goals or safety constraints when the skill loads
  • Agent Memory PoisoningWrites attacker-controlled rules into memory that affect later sessions
  • Remote Payload Retrieval and ExecutionFetches external code whose behavior can change after review
  • Embedded Malicious CodeShips malicious scripts inside the skill and executes them locally
Findings (1)

T08 · Insecure Dependencies

Warning
Location
SKILL.md:7
Finding

Unpinned Third-Party MCP Executable Creates a Supply-Chain Risk

Content
View full analysis
Remediation
View remediation

SkillSpector

Vulnerability Patterns
  • 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
  • Excessive AgencyUnrestricted Tool Access, Autonomous Decision Making, Scope Creep
Findings (1)

Rp1

Medium
Category
MCP Rug Pull
Confidence
95% confidence
Finding

The skill metadata declares use of Node tooling (npx) and installs an MCP package without any version pinning. This creates a supply-chain risk: future package updates or a compromised upstream release could change the executed code at install or runtime, and MCP servers generally run with the local user's privileges.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.