ClawHub
Back to skill

Security audit

wos-literature-toolkit

Security checks across malware telemetry and agentic risk

Overview

This WOS paper-downloading skill is coherent, but it needs review because it directs browser automation with saved institutional login cookies and third-party PDF sources without enough scoping or user controls.

Install only if you are comfortable with browser automation against WOS, persistent institutional session cookies, and paper metadata being used with the listed PDF sources. Before running it, review or obtain the missing scripts, confirm where cookies are saved and how to delete them, and prefer explicit WOS-only requests with confirmation before crawling or bulk downloading.

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
88% confidence
Finding
The skill declares broad activation phrases such as generic paper-download terms, which can cause the agent to invoke this skill in situations beyond narrowly scoped WOS workflows. In this context that is more dangerous because the skill enables crawling, credential-adjacent browser automation, cookie persistence, and PDF acquisition from high-risk sources like Sci-Hub, so mistaken activation can expose users to legal, privacy, and security risks.

Missing User Warnings

Medium
Confidence
95% confidence
Finding
The skill mentions persistent storage of WOS login cookies but does not clearly warn users, describe storage location/protection, or obtain explicit consent. This is dangerous because authentication cookies can grant continued access to subscription resources; if stored insecurely or unexpectedly, they may be reused by other local users, malware, or future automated runs without the user's awareness.

VirusTotal

65/65 vendors flagged this skill as clean.

View on VirusTotal

Static analysis

No suspicious patterns detected.