ClawHub
Back to skill

Security audit

mcp-company-search

Security checks across malware telemetry and agentic risk

Overview

This is a small read-only company registry search MCP skill, but its package name and environment-variable documentation should be checked before use.

Install only if you trust the npm package and the Nautdev/L402 API provider. Verify whether @vbotholemu/mcp-company-search is the intended package, consider pinning an exact version, and use NAUTDEV_BASE_URL if you need to override the default API endpoint. Avoid submitting sensitive investigation targets unless you are comfortable sharing those queries with the external service.

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 (3)

Lp3

Medium
Category
MCP Least Privilege
Confidence
86% confidence
Finding
The skill requires an environment variable and makes outbound network calls, but it does not declare permissions to reflect those capabilities. This weakens transparency and trust boundaries for users and tooling, making it easier for a skill to access configuration or exfiltrate data without clear review expectations.

Tp4

High
Category
MCP Tool Poisoning
Confidence
78% confidence
Finding
The skill description says it searches registries via an L402 API, but the setup points to a specific Nautdev HTTPS endpoint and the toolset includes behavior not clearly described in the summary. Description-to-behavior mismatches are dangerous because they can mislead reviewers and users about what service is actually contacted and what actions the skill can perform, reducing informed consent and increasing supply-chain risk.

Missing User Warnings

Medium
Confidence
92% confidence
Finding
The tool transmits user-supplied company names and jurisdictions to an external service, which can expose potentially sensitive due-diligence or investigative queries to a third party without any notice, consent, or data-handling controls visible in this code. In an MCP skill context, users may assume queries are handled locally by the agent, so undisclosed outbound transmission increases privacy and compliance risk.

VirusTotal

65/65 vendors flagged this skill as clean.

View on VirusTotal

Static analysis

Detected: suspicious.env_credential_access

Environment variable access combined with network send.

Critical
Code
suspicious.env_credential_access
Location
dist/index.js:7

Environment variable access combined with network send.

Critical
Code
suspicious.env_credential_access
Location
src/index.ts:7