Novel Writer Structure

Security checks across malware telemetry and agentic risk

Overview

This skill is a structured novel-writing workflow and does not show hidden code, credential use, network access, or unsafe behavior.

Install this if you want a Chinese-oriented structured workflow for drafting novel chapters and maintaining continuity notes. Keep any outline and state-tracking files limited to the writing project you want the agent to use.

SkillSpector

By NVIDIA

Vulnerability Patterns

MCP Tool PoisoningHidden Instructions, Unicode Deception, Parameter Description Injection
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)

Natural-Language Policy Violations

Medium

Confidence: 92% confidence
Finding: The metadata description hard-codes Chinese-language behavior without indicating that the language is configurable or subject to user preference. In an agent ecosystem, this can cause the skill to override user intent, degrade reliability, and create prompt-routing or policy mismatches when the user expects another language.

VirusTotal

35/35 vendors flagged this skill as clean.

View on VirusTotal