Ai Writing Humanizer

• Outcome: Pass
• Latest audit: May 28, 2026 at 9:01 AM UTC
• Version:
  0.1.0

Overview

This is a local text-rewriting skill that appears purpose-aligned and does not show exfiltration, persistence, or destructive behavior.

Install this if you want automatic help removing common AI-writing tells from prose. Review edits before sending, especially for legal, medical, academic, financial, quoted, or meaning-sensitive text, because the regex cleanup can remove words or structure that may matter.

SkillSpector

By NVIDIA

Vulnerability Patterns

• Trigger Abuse: Overly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
• MCP Least Privilege: Underdeclared Capability, Wildcard Permission, Missing Permission Declaration
• Prompt Injection: Instruction Override, Hidden Instructions, Exfiltration Commands
• Data Exfiltration: External Transmission, Env Variable Harvesting, File System Enumeration
• Privilege Escalation: Excessive Permissions, Sudo/Root Execution, Credential Access

Findings (2)

Lp3

Medium

• Category: MCP Least Privilege
• Confidence: 88% confidence
• Finding: The skill instructs the agent to invoke a local script and read/write input and output files, but the skill metadata does not declare any permissions. That mismatch can bypass user/admin expectations about what the skill is allowed to access and increases the risk of unintended file access if the skill is auto-loaded or broadly applied.

Vague Triggers

Medium

• Confidence: 84% confidence
• Finding: The instruction to load this skill automatically for any user-facing prose longer than ~150 words is broad and ambiguous, causing the skill to activate in many contexts without clear user intent. Because the skill can rewrite outgoing content and invoke file-processing behavior, over-broad triggering creates unnecessary opportunities for unauthorized transformation of sensitive text or unexpected file operations.

VirusTotal

66/66 vendors flagged this skill as clean.