ClawHub

sf-novel-writer

Security checks across malware telemetry and agentic risk

Overview

This is a disclosed science-fiction writing helper that creates local draft files, with no evidence of hidden data access, exfiltration, or destructive behavior.

Install if you want a structured SF-writing workflow that may create local draft files. Use a simple project name with letters, numbers, underscores, or hyphens, and avoid slashes or '..' because the included setup script does not validate the output path.

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 (3)

Vague Triggers

Medium
Confidence
91% confidence
Finding
The trigger conditions are extremely broad and cover nearly any science-fiction writing request, making accidental invocation likely. Over-broad routing can cause the wrong skill to activate, unnecessarily exposing its instructions and file-handling workflow, and may interfere with user intent or other safer/more specific skills.

Vague Triggers

Medium
Confidence
86% confidence
Finding
The trigger description covers very broad creative-writing requests such as plotting, editing, improving, and continuing text, which can cause the skill to activate outside a narrowly intended science-fiction context. Over-broad activation increases the chance that users are routed into a workflow that writes files, references external skill content, or applies unintended instructions to unrelated requests.

Vague Triggers

Medium
Confidence
83% confidence
Finding
The stage-routing keywords include generic terms like 'idea', 'structure', 'write', 'modify', and 'complete', which are common across many ordinary requests. Ambiguous routing can misclassify user intent and trigger later-stage actions such as file generation or output assembly without sufficient confirmation, especially when combined with the skill's broad overall scope.

VirusTotal

64/64 vendors flagged this skill as clean.

View on VirusTotal