ClawHub
Back to skill

Security audit

Book Video Generator

Security checks across malware telemetry and agentic risk

Overview

This skill is a disclosed book-summary video workflow that uses expected external search, image generation, TTS, and local video output without evidence of hidden or destructive behavior.

Install only if you are comfortable with a workflow that may send book names, author names, generated narration, image prompts, and caption text to search, image-generation, LLM, and TTS providers. Review any added scripts or API configuration before running them, since this published artifact only contains the skill instructions.

SkillSpector

By NVIDIA
Vulnerability Patterns
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
  • Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
Findings (2)

Vague Triggers

Medium
Confidence
87% confidence
Finding
The trigger phrases are broad and closely match ordinary user requests for creating book-summary videos, which can cause the skill to activate unexpectedly when a user did not specifically intend to invoke it. In an agent ecosystem, overbroad activation can route general requests into a workflow that performs external searches, API calls, and file generation, increasing the chance of unintended actions and data disclosure.

Missing User Warnings

Medium
Confidence
94% confidence
Finding
The skill documentation does not clearly warn users that it will send user-provided book names, author names, generated prompts, and possibly other content to third-party services for web search, image generation, and TTS. This lack of transparency can lead to unintended sharing of user input or derived content with external providers, which is especially risky in multi-tool agent environments.

VirusTotal

64/64 vendors flagged this skill as clean.

View on VirusTotal

Static analysis

No suspicious patterns detected.