ClawHub
Back to skill

Security audit

Book Writing Assistant

Security checks across malware telemetry and agentic risk

Overview

This book-writing helper is coherent and purpose-aligned, but users should understand that it saves manuscript details locally and may activate on broad writing-related phrases.

Install this if you are comfortable with the agent keeping manuscript continuity data in a local book-data.json file. Review or delete that file when you do not want older book ideas, research notes, or character details reused, and be aware the skill may activate on casual book-writing phrases.

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

High
Confidence
93% confidence
Finding
The skill is configured to trigger on very broad, casual phrases related to writing, which can cause it to activate in contexts where the user did not actually intend to use this skill. Overbroad activation increases the chance of unintended data handling, context pollution across projects, and disclosure or persistence of sensitive manuscript content without clear user intent.

VirusTotal

65/65 vendors flagged this skill as clean.

View on VirusTotal

Static analysis

No suspicious patterns detected.