findTheBook

Security checks across malware telemetry and agentic risk

Overview

This skill is a straightforward book lookup helper that searches public book sites and does not show hidden access, persistence, credential use, or destructive behavior.

Install this only if you are comfortable sending book titles or reading interests to external search and book websites. In controlled environments, review or pin the Python dependencies before use.

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 (4)

Vague Triggers

Medium
Confidence
79% confidence
Finding
The activation examples are broad enough that an agent may invoke this skill for loosely related book-recommendation requests without clear user consent to perform external web lookups. In this skill, over-broad triggering is more dangerous because execution leads to live searches against third-party sites and retrieval of external reading links, expanding data exposure and increasing the chance of unintended browsing behavior.

Missing User Warnings

Medium
Confidence
92% confidence
Finding
The skill states it will automatically search for direct WeChat Reading links in addition to Douban content, but it does not clearly warn users that it will access external resources beyond the named site. This is risky because users may expect a Douban-only lookup while the agent broadens browsing to other services, creating consent, privacy, and policy-boundary issues—especially around locating ebook-reading resources.

Missing User Warnings

Medium
Confidence
94% confidence
Finding
This code sends the user-provided book title to DuckDuckGo to search for Weread links, which causes external data transmission without any explicit disclosure or consent mechanism. In an agent or skill context, even seemingly harmless search terms may contain sensitive user interests or private data, so silent outbound requests create a privacy and data-handling risk.

Missing User Warnings

Medium
Confidence
95% confidence
Finding
The function fetches Douban pages over the network without warning the user that an external HTTP request will be made. This exposes user queries and agent activity to third-party services and can surprise users in environments where network access, privacy, or compliance constraints require explicit disclosure.

VirusTotal

64/64 vendors flagged this skill as clean.

View on VirusTotal