Back to skill

Security audit

Google seach console

Security checks across malware telemetry and agentic risk

Overview

This is a documentation-only Google Search Console helper that uses a disclosed Maton API key and OAuth connection, with some administrative examples users should run carefully.

Install this only if you intend to use Maton as a gateway for Google Search Console. Use your own API key, avoid echoing or pasting secrets in shared terminals, replace sample IDs with your verified connection ID, and review any PUT or DELETE command before running it because it can change sitemap configuration or remove an OAuth connection.

SkillSpector

By NVIDIA
Vulnerability Patterns
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
  • Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
  • Excessive AgencyUnrestricted Tool Access, Autonomous Decision Making, Scope Creep
Findings (2)

Missing User Warnings

Medium
Confidence
95% confidence
Finding
The documentation includes a DELETE operation for removing connections without any warning that it is state-changing and potentially disruptive. A user or downstream agent following the example could unintentionally revoke an active OAuth-backed integration and interrupt access to the external service.

Missing User Warnings

Medium
Confidence
96% confidence
Finding
The sitemap submit and delete examples modify external service state, but the skill does not clearly warn users that these actions can change indexing behavior and remove configured sitemaps. In an agent context, lack of guardrails increases the chance of unintended changes to production SEO configuration.

VirusTotal

61/61 vendors flagged this skill as clean.

View on VirusTotal

Static analysis

Detected: suspicious.exposed_resource_identifier

Example code exposes a concrete connection_id instead of a placeholder.

Critical
Code
suspicious.exposed_resource_identifier
Location
SKILL.md:101