ClawHub

Domain Lookup

Security checks across malware telemetry and agentic risk

Overview

This skill is a disclosed API-based domain lookup helper, but users should notice that it sends lookups to a third-party service and saves the provided API key in a local .env file.

Install only if you are comfortable giving this publisher an API key and sending domain lookup queries to xiaobenyang.com. Treat the saved .env file as sensitive, avoid committing or sharing it, and review the copied school-search references as a quality issue rather than evidence of malicious behavior.

SkillSpector

By NVIDIA
Vulnerability Patterns
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • MCP Least PrivilegeUnderdeclared Capability, Wildcard Permission, Missing Permission Declaration
  • MCP Tool PoisoningHidden Instructions, Unicode Deception, Parameter Description Injection
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
Findings (5)

Lp3

Medium
Category
MCP Least Privilege
Confidence
85% confidence
Finding
The skill appears to require environment access, local file read/write, and network access to function, yet it declares no permissions. This creates a transparency and consent problem: a user or host may not realize the skill can persist secrets locally and contact remote services, increasing the risk of unauthorized data handling or unexpected side effects.

Tp4

High
Category
MCP Tool Poisoning
Confidence
94% confidence
Finding
The skill claims to be a comprehensive local domain-research MCP server, but the documentation shows it is actually a thin client/proxy to an upstream third-party API and stores an API key in a local .env file. This mismatch can mislead users about where their queries and secrets are going, which is dangerous because domain lookup data, user inputs, and credentials may be transmitted to or retained by an external service unexpectedly.

Description-Behavior Mismatch

High
Confidence
92% confidence
Finding
The workflow documentation references unrelated gaokao/school-search behavior inside a domain lookup skill, indicating copy-paste contamination or poor maintenance. In security-sensitive tooling, such inconsistencies are dangerous because they can cause the model or operator to invoke the wrong functions, mishandle user input, or trust incorrect assumptions about what code paths are actually exercised.

Intent-Code Divergence

High
Confidence
90% confidence
Finding
The inline routing example explicitly shows invocation of a school-search function in a skill purportedly dedicated to domain research. This contradiction increases the chance of incorrect tool routing, unintended data disclosure to unrelated backends, or operational confusion during agent execution.

Missing User Warnings

Medium
Confidence
93% confidence
Finding
The code persists an API key into a local .env file automatically, without any confirmation, warning, or file-permission handling. This increases the risk of credential exposure through source control commits, local filesystem access, backups, or accidental sharing of the project directory.

VirusTotal

64/64 vendors flagged this skill as clean.

View on VirusTotal