human-tech-blog

• Outcome: Pass
• Latest audit: May 29, 2026 at 8:23 PM UTC
• Version:
  1.0.0

Overview

This is a writing-only skill for technical blog posts, with no code, install hooks, data access, or persistence found.

Install this if you want a strong personal technical-blog voice. Check the final draft for fabricated personal experiences, version numbers, links, error messages, and technical claims, and override the skill when you need a different publication style, language convention, or more neutral tone.

SkillSpector

By NVIDIA

Vulnerability Patterns

• Trigger Abuse: Overly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
• 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
• Supply Chain: Unpinned Dependencies, External Script Fetching, Obfuscated Code

Findings (2)

Vague Triggers

High

• Confidence: 95% confidence
• Finding: The skill description mandates activation whenever users mention broad, common phrases like writing a blog, technical article, or making text sound less machine-written. This can cause the skill to override more appropriate tools or user intent, leading to prompt routing abuse, misapplication, or hidden behavioral steering across many benign requests.

Natural-Language Policy Violations

Medium

• Confidence: 86% confidence
• Finding: The skill imposes Chinese typography and formatting rules by default, including full-width punctuation and spacing conventions, without checking the user's locale, platform, or preferences. While not a direct security exploit, it can cause integrity and usability issues by silently altering output style in ways the user did not request, especially in multilingual or publication-specific contexts.

VirusTotal

56/56 vendors flagged this skill as clean.