ClawHub
Back to skill

Security audit

BookMorph Magic

Security checks across malware telemetry and agentic risk

Overview

This appears to be a legitimate book-to-content packaging template, but it includes an under-guarded directory reset that could delete local output data if pointed at the wrong path.

Review before installing. Use only in a dedicated workspace or throwaway output directory, avoid broad output roots, do not use `--clear-existing` unless you have verified the exact destination path, and avoid sharing generated manifests if local filesystem paths are sensitive.

SkillSpector

By NVIDIA
Vulnerability Patterns
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
  • 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
  • Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
Findings (3)

Vague Triggers

Medium
Confidence
91% confidence
Finding
The trigger language is broad enough that the skill could be invoked for loosely related requests such as generic episode production or book-derived content generation without clear user confirmation. In this skill, unintended invocation is more dangerous because the documented workflow proceeds to create/reset directories and generate or bundle artifacts, so accidental activation can lead to unwanted file operations and downstream automation.

Missing User Warnings

Medium
Confidence
94% confidence
Finding
The skill documentation does not prominently warn that the workflow can reset an existing destination via `prepare-dest --clear-existing` and write manifests and media files to disk. In context, this omission increases risk because users or orchestrators may invoke the skill without understanding that existing output directories can be cleared, causing accidental data loss or overwriting prior artifacts.

Vague Triggers

Medium
Confidence
88% confidence
Finding
The default_prompt activates the skill whenever a user wants to turn a book into a package of assets, but it does not define clear boundaries, required confirmations, or eligibility checks. Broad activation can cause the agent to invoke this orchestration template inappropriately, increasing the chance of unintended processing of copyrighted, sensitive, or user-inappropriate content.

VirusTotal

65/65 vendors flagged this skill as clean.

View on VirusTotal

Static analysis

No suspicious patterns detected.