ClawHub

Maton MCP Tools

Security checks across malware telemetry and agentic risk

Overview

This appears to be a disclosed Maton OAuth integration, but users should understand it stores a Maton API key and can manage SaaS app connections.

Install only if you trust Maton with the SaaS accounts you connect. Review connected apps regularly, rotate the Maton API key, remove unused connections, and confirm before starting OAuth flows or deleting connections.

SkillSpector

By NVIDIA
Vulnerability Patterns
  • Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
  • 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
Findings (3)

Lp3

Medium
Category
MCP Least Privilege
Confidence
88% confidence
Finding
The skill clearly instructs users to make authenticated network requests to an external service and to install backend/UI components that manage OAuth connections, yet no declared permissions are present. This creates a transparency and policy-enforcement gap: operators and any permission model cannot accurately assess or constrain the skill's network behavior, which is especially relevant because it handles API keys and SaaS integrations.

Vague Triggers

Medium
Confidence
80% confidence
Finding
The description says to use the skill broadly for 'setting up Maton integration, connecting apps ... or managing OAuth connections' without tighter trigger boundaries, exclusions, or user-confirmation requirements. In an agent environment, this can cause over-selection of a skill that initiates external connections and credential-related workflows, increasing the chance of unnecessary OAuth actions or exposure of integration surfaces.

Missing User Warnings

Low
Confidence
93% confidence
Finding
The controller opens a backend-supplied `oauthUrl` directly with `window.open(..., "_blank")` and performs no origin validation or safety controls. If the backend response is compromised or manipulated, the UI can launch a phishing or attacker-controlled page, and using `_blank` without `noopener,noreferrer` can expose the opener context to tabnabbing-style abuse.

VirusTotal

64/64 vendors flagged this skill as clean.

View on VirusTotal