ClawHub
Back to skill

Security audit

Book Id

Security checks across malware telemetry and agentic risk

Overview

This book-cataloging skill mostly matches its purpose, but it can automatically create files and run an unreviewed local shell script after broad trigger phrases.

Before installing, review or remove the `fix-md.sh` step and use the skill only when you intentionally want book notes and photos written into your workspace. Be careful with ambiguous prompts like `add to library`; confirm the target book and output path before allowing file creation.

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 (2)

Vague Triggers

Medium
Confidence
92% confidence
Finding
The trigger phrases include broad everyday terms such as 'log book' and 'add to library', which can cause the skill to activate in contexts unrelated to book cataloging. This increases the chance of unintended execution of downstream actions like web access, file writes, file copying, and shell invocation based on ambiguous user requests.

Missing User Warnings

Medium
Confidence
96% confidence
Finding
The skill performs system-modifying operations including writing files, copying media, and executing a shell script, but does not present a clear upfront warning or explicit consent step before those actions. In combination with broad triggers, this can lead to unexpected filesystem changes or command execution when a user only intended identification or discussion of a book.

VirusTotal

60/60 vendors flagged this skill as clean.

View on VirusTotal

Static analysis

No suspicious patterns detected.