ClawHub

HTML Markdown Hybrid

Security checks across malware telemetry and agentic risk

Overview

This is a straightforward HTML and Markdown converter; it can fetch webpages and read/write chosen files, but I found no hidden or unrelated behavior.

Install only if you are comfortable with npm dependencies and document-conversion tools. Use explicit input and output paths, avoid pointing batch mode at broad private directories unless intended, fetch only URLs you want processed, and treat HTML generated from untrusted Markdown as potentially unsafe to open or publish without review.

SkillSpector

By NVIDIA
Vulnerability Patterns
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • MCP Least PrivilegeUnderdeclared Capability, Wildcard Permission, Missing Permission Declaration
  • 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)

Lp3

Medium
Category
MCP Least Privilege
Confidence
82% confidence
Finding
The skill advertises and instructs use of scripts that read inputs and write outputs, but it does not declare permissions or clearly surface those capabilities. In an agent setting, undeclared file access can lead to users or orchestrators invoking the skill without understanding that local files may be read or overwritten.

Missing User Warnings

Medium
Confidence
90% confidence
Finding
The skill explicitly supports URL fetching, directory processing, and writing Markdown/report outputs, but the top-level guidance does not clearly warn that using it may trigger network requests and create or overwrite files. In agent workflows, that lack of notice can cause unintended external access, bulk processing of sensitive content, or silent filesystem changes.

VirusTotal

67/67 vendors flagged this skill as clean.

View on VirusTotal