Novel Polish

Security checks across malware telemetry and agentic risk

Overview

This is a simple novel-polishing prompt with no executable code, network use, credentials, or hidden behavior.

Safe to install for novel and fiction prose editing. Be aware it may activate on broad writing-improvement requests, so choose a more specific editing skill for academic, factual, legal, or non-fiction work if precision matters.

SkillSpector

By NVIDIA

Vulnerability Patterns

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
Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code

Findings (1)

Vague Triggers

Medium

Confidence: 90% confidence
Finding: The skill uses broad activation phrases such as "polish a novel," "improve writing," and "refine prose," which are generic and likely to overlap with many unrelated writing-editing requests. This can cause unintended invocation of the skill in contexts where a more specific or safer skill should respond, increasing the chance of misrouting or undesired behavior.

VirusTotal

64/64 vendors flagged this skill as clean.

View on VirusTotal