Security audit

Novel Writer

Security checks across malware telemetry and agentic risk

Overview

This skill appears to automate recurring local writing and file updates in ways that users should review before installing.

Install only if you intentionally want an agent to modify local writing files and possibly run on a schedule. Before use, confirm the exact paths it will read and write, disable or avoid any hourly automation unless you need it, and keep backups of affected project files.

SkillSpector

By NVIDIA

Vulnerability Patterns

Excessive AgencyUnrestricted Tool Access, Autonomous Decision Making, Scope Creep
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 (2)

Missing User Warnings

Medium

Confidence: 96% confidence
Finding: The workflow directs the agent to automatically read from fixed local paths and write/update multiple files, including overwriting project artifacts and copying content to Desktop, without any user confirmation or safety checks. This creates a real risk of unintended local data access, silent modification of user files, and leakage of private content into more exposed locations.

Missing User Warnings

Medium

Confidence: 97% confidence
Finding: The cron section describes recurring automatic execution that writes chapters and updates the outline every hour, again without warning or approval controls. Scheduled autonomous file modification increases the blast radius substantially because changes can continue after the initial interaction, causing persistent unwanted edits, storage growth, and difficulty attributing or rolling back changes.

VirusTotal

50/50 vendors flagged this skill as clean.

View on VirusTotal

Static analysis

No suspicious patterns detected.