Humanizer Enhanced

Security checks across malware telemetry and agentic risk

Overview

This is a transparent writing-assistant skill that can rewrite user-selected drafts, with no evidence of hidden code, credentials use, persistence, or exfiltration.

Install only if you are comfortable with a skill that rewrites drafts to sound less AI-generated. Use scan-only mode first, review diffs before accepting changes, keep backups or version control for batch runs, and follow any disclosure, academic, workplace, or publication rules about AI-assisted writing.

SkillSpector

By NVIDIA

Vulnerability Patterns

Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
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)

Vague Triggers

Medium

Confidence: 90% confidence
Finding: The skill advertises broad natural-language triggers such as "humanize this," "make it sound human," and general requests to clean up drafts, which can overlap with ordinary editing or writing-assistance requests. That increases the chance the skill activates when the user did not explicitly intend to invoke a text-rewriting tool, causing unexpected content transformation and potentially bypassing safer, narrower workflows.

VirusTotal

64/64 vendors flagged this skill as clean.

View on VirusTotal