ClawHub
Back to skill

Security audit

Store Management

Security checks across malware telemetry and agentic risk

Overview

This is a transparent Mobazha store-management guide that uses authenticated MCP tools and asks for user confirmation before sensitive store actions.

Install only if you intend to let an agent help manage a Mobazha store through an authenticated MCP connection. Review actions involving refunds, deletions, order status changes, customer messages, wallet addresses, and payment provider settings before approving them.

SkillSpector

By NVIDIA
Vulnerability Patterns
  • Excessive AgencyUnrestricted Tool Access, Autonomous Decision Making, Scope Creep
  • MCP Tool PoisoningHidden Instructions, Unicode Deception, Parameter Description Injection
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
Findings (2)

Description-Behavior Mismatch

Medium
Confidence
91% confidence
Finding
The manifest description materially understates the skill's capabilities. While it claims to manage products, orders, messages, and settings, the file also exposes finance data, wallet receiving addresses, discount and collection management, profile updates, notifications, and public marketplace search. This mismatch can cause downstream reviewers, policy engines, or users to grant access under an incomplete understanding of what the skill can do.

Context-Inappropriate Capability

Low
Confidence
83% confidence
Finding
The skill includes public marketplace search tools that are outside the narrow stated purpose of managing the user's own store. Even though the data is public, bundling competitor/search functionality into a store-management skill expands scope unexpectedly and can enable unnecessary data access or behavior not anticipated by the user or reviewer.

VirusTotal

64/64 vendors flagged this skill as clean.

View on VirusTotal

Static analysis

No suspicious patterns detected.