ClawHub
Back to skill

Security audit

zt-web-fetcher

Security checks across malware telemetry and agentic risk

Overview

This skill is a simple web-fetching helper that routes requested webpages through third-party Markdown conversion services, with some privacy cautions users should understand.

Use this mainly for public webpages. Avoid private, token-bearing, internal, or confidential URLs because the URL and fetched content may be processed by third-party conversion services. Only install the optional Scrapling fallback after approving it and verifying the package source.

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
90% confidence
Finding
The trigger phrases are very broad (e.g., equivalents of 'help me check', 'look at this link', 'get information about xx'), which can overlap with many normal conversations and cause the skill to activate unexpectedly. In this skill, accidental activation can lead to unsolicited outbound requests and unintended transmission of user-provided URLs to external services.

Missing User Warnings

Medium
Confidence
97% confidence
Finding
The skill instructs the agent to send arbitrary user-supplied URLs to third-party services such as markdown.new, r.jina.ai, and defuddle.md, but it does not warn about the privacy and security implications. This can expose sensitive URLs, tokens embedded in query strings, internal endpoints, or user browsing intent to external providers, making the issue more dangerous because third-party transmission is the core mechanism of the skill.

VirusTotal

64/64 vendors flagged this skill as clean.

View on VirusTotal

Static analysis

No suspicious patterns detected.