ClawHub
Back to skill

Security audit

technical-article-writer

Security checks across malware telemetry and agentic risk

Overview

This skill is a transparent technical-writing assistant with no hidden install steps, persistence, credential handling, or destructive behavior.

Install this if you want a structured, interview-style workflow for developer articles. Expect it to ask questions before drafting and to use related writing skills if available; review any web-researched Midjourney prompt advice because that part depends on current external documentation.

SkillSpector

By NVIDIA
Vulnerability Patterns
  • Memory PoisoningPersistent Context Injection, Context Window Stuffing, Memory Manipulation
  • 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
Findings (2)

Vague Triggers

Medium
Confidence
95% confidence
Finding
The manifest description says to use this skill whenever the user asks to write a blog post, technical article, or 'any long-form technical content,' and includes broad phrases like 'help me draft an article' and even 'I want to write about X' without specifying format. These triggers overlap with common writing requests and do not clearly bound when the skill should not activate beyond a few exclusions, increasing the chance of accidental invocation.

Context Window Stuffing

Medium
Category
Memory Poisoning
Content
- If you can't infer a thesis, ask the user: "What's the one thing you want the reader to remember?" If they can't answer, help them find it through questions about what surprised them, what they'd tell a colleague, or what they wish they'd known earlier.
- If the content type is ambiguous (could be a tutorial or an explainer), ask which experience the reader should have: following along hands-on, or building a mental model.

Only proceed to Phase 2 once you have enough clarity on topic, audience, content type, and thesis to write a coherent outline. It's cheaper to ask one question now than to rewrite 2000 words later.

**Idea quality filters.** Apply these before investing in a draft:
Confidence
80% confidence
Finding
Skill attempts to fill the context window with filler content, displacing legitimate instructions and safety constraints. This can degrade agent performance or bypass safety boundaries.

VirusTotal

64/64 vendors flagged this skill as clean.

View on VirusTotal

Static analysis

No suspicious patterns detected.