eeat-content-quality-audit

Security checks across malware telemetry and agentic risk

Overview

This is a content audit skill that reviews user-provided material and does not contain hidden execution, credential use, persistence, or destructive behavior.

Installers should treat audit output as advisory and provide only content, URLs, or file paths they are comfortable having reviewed. Avoid private documents, secret-bearing paths, authenticated pages, or internal URLs unless that access is intentional.

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 (1)

Missing User Warnings

Medium

Confidence: 94% confidence
Finding: The skill explicitly invites users to provide URLs or file paths without warning about the sensitivity of local files or the risks of fetching external content. In an agentic environment, this can lead to unintended access to local data, internal paths, or untrusted remote resources, increasing the chance of data exposure or unsafe retrieval behavior.

VirusTotal

65/65 vendors flagged this skill as clean.

View on VirusTotal