ClawHub

Notebook

Security checks across malware telemetry and agentic risk

Overview

This appears to be a local notebook tool, but its file path handling and deletion behavior deserve review before installation.

Review before installing. Use simple type names such as letters, numbers, hyphens, and underscores; avoid storing secrets; keep backups of the notebook folder; and treat delete operations as permanent unless the skill is updated to add confirmation, soft delete, and strict path validation.

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
84% confidence
Finding
The phrase `Say expand and I will ask questions to add depth` creates a very broad natural-language trigger that can be invoked accidentally in unrelated conversation. Because `expand` is also a documented command tied to object modification workflows, unclear scoping can cause unintended state-changing actions or prompt flows when the user did not mean to operate on notebook data.

Missing User Warnings

Medium
Confidence
91% confidence
Finding
The documentation exposes a destructive command, `notebook delete typename title`, without warning that it removes stored notebook objects or indicating whether deletion is reversible. Users may invoke it casually or through agent assistance without understanding the data-loss consequence, increasing the risk of accidental deletion of local knowledge-base entries.

VirusTotal

66/66 vendors flagged this skill as clean.

View on VirusTotal