Novel Continue

Security checks across malware telemetry and agentic risk

Overview

This is an instruction-only writing skill for continuing novel text, with no code, credentials, persistence, or external data access.

Safe to install for novel-continuation help. Be aware that generic prompts like "keep writing" might activate it even when you intended another kind of writing task, so specify when the text is or is not fiction.

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: 94% confidence
Finding: The invocation guidance is very broad ('continue a novel', 'keep writing', 'write the next part'), which can cause the skill to trigger on generic writing requests and override more appropriate skills or default handling. In an agent environment, overbroad routing increases the chance of misclassification, unexpected behavior, and accidental processing of unrelated user content.

VirusTotal

64/64 vendors flagged this skill as clean.

View on VirusTotal