Website Monitor

Security checks across malware telemetry and agentic risk

Overview

This is a straightforward website monitoring skill, with expected network checks and local state storage that users should configure carefully.

Safe to install for ordinary public website monitoring. Choose a private state directory, remember that monitored page text may be stored locally, avoid sensitive URLs, and only add the cron schedule if you want recurring automated checks.

SkillSpector

By NVIDIA

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)

Lp3

Medium

Category: MCP Least Privilege
Confidence: 92% confidence
Finding: The skill documentation instructs use of a Python script that performs outbound network requests and writes monitoring state to disk, but the skill declares no permissions for those capabilities. This creates a transparency and trust problem: users and enforcement layers may authorize or run the skill without realizing it can access remote URLs and persist data locally. In this context, network and file-write behavior are expected for a website monitor, which lowers suspicion of maliciousness, but the undeclared capability mismatch is still a real security issue.

VirusTotal

66/66 vendors flagged this skill as clean.

View on VirusTotal