ClawHub
Back to skill

Security audit

Naver Shopping Search

Security checks for vulnerabilities and agentic risk

Overview

The skill performs a straightforward Naver Shopping API search using disclosed Naver API credentials and shows no hidden, destructive, or persistent behavior.

Install this only if you are comfortable providing Naver Search API credentials in the environment used by the agent. The main practical issue is that the documented command path is user-specific, so it may need adjustment after installation.

A.I.G

Vulnerability Patterns
  • 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
  • Unauthorized Access and Privilege EscalationObtains permissions beyond the task's legitimate needs

SkillSpector

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)

Undeclared Tool Scope

Medium
Category
MCP Least Privilege
Confidence
95% confidence
Finding

The skill invokes a local Python script that uses environment variables for API credentials and makes outbound network requests, but the manifest declares no explicit tool scope or permissions. This creates a mismatch between declared and actual capabilities, which can lead to overbroad execution, poor reviewability, and accidental exposure of secrets or unintended network access in environments that rely on manifest-level constraints.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.