ClawHub

Book Launch Campaign Kit

Security checks across malware telemetry and agentic risk

Overview

This is a coherent book-launch helper that creates marketing copy/assets and an optional local folder scaffold, with no evidence of hidden access, credential use, persistence, or destructive behavior.

Before running the helper script, choose the target folder deliberately because it will create folders and starter markdown files there. Confirm the desired language and marketplace requirements before using generated copy publicly, especially for Amazon listings or ad materials.

SkillSpector

By NVIDIA
Vulnerability Patterns
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
  • MCP Least PrivilegeUnderdeclared Capability, Wildcard Permission, Missing Permission Declaration
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
Findings (3)

Lp3

Medium
Category
MCP Least Privilege
Confidence
91% confidence
Finding
The skill instructs use of `scripts/scaffold_launch_pack.py` to create a project structure, which implies filesystem write capability, but no corresponding permissions are declared. Undeclared write behavior weakens user awareness and policy enforcement, and could allow the skill to create or modify files in ways the user did not explicitly authorize.

Vague Triggers

Medium
Confidence
79% confidence
Finding
The activation criteria are broad enough to match generic marketing, packaging, and promotion requests, which can cause the skill to trigger outside its intended narrow use case. Overbroad invocation increases the chance of context hijacking, unintended file creation, or generation of Amazon-ready publishing assets when the user did not specifically request this workflow.

Natural-Language Policy Violations

Medium
Confidence
86% confidence
Finding
The skill sets English as the default output language for core assets without requiring user opt-in, which can override user intent and silently shape externally published marketing content. In a launch and publishing context, that can lead to incorrect marketplace copy, misleading localization, or accidental publication in the wrong language.

VirusTotal

67/67 vendors flagged this skill as clean.

View on VirusTotal