Max Humanizer

Security checks across malware telemetry and agentic risk

Overview

This is a disclosed text-editing skill that rewrites writing to sound less AI-generated, with no code execution, network access, credentials, or persistence.

Install only if you want help editing text you are allowed to revise. Do not use it to bypass AI-use disclosure, academic integrity, workplace, legal, platform, or anti-impersonation rules; specify the exact text or files to edit and review the output before accepting changes.

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)

Natural-Language Policy Violations

Medium

Confidence: 92% confidence
Finding: The skill explicitly aims to make text appear more human-written and does not mention any requirement for user consent, labeling, or policy gating. In environments with transparency, academic integrity, compliance, or anti-impersonation requirements, this can enable deceptive use by helping users conceal AI assistance or misrepresent authorship.

VirusTotal

66/66 vendors flagged this skill as clean.

View on VirusTotal