Humanizer

Security checks across malware telemetry and agentic risk

Overview

This is a coherent text-editing skill that can read and edit files for humanizing writing, with no evidence of hidden install steps, exfiltration, or unrelated behavior.

Install if you are comfortable letting the skill read and edit files you explicitly provide. For important documents, ask the agent to show the rewritten output or a diff before applying changes, and review factual claims, neutrality, and point of view before using the result.

SkillSpector

By NVIDIA

Vulnerability Patterns

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
Excessive AgencyUnrestricted Tool Access, Autonomous Decision Making, Scope Creep

Findings (1)

Missing User Warnings

Medium

Confidence: 91% confidence
Finding: The skill is granted Write and Edit capabilities, and its purpose is to rewrite text, but it does not clearly warn that using the skill may directly alter existing content. In an agent setting, this can lead to unintended or silent modification of files, especially if the agent applies the skill to repository content or user documents without an explicit confirmation step.

VirusTotal

65/65 vendors flagged this skill as clean.

View on VirusTotal