ClawHub
Back to skill

Security audit

markdown-exporter

Security checks across malware telemetry and agentic risk

Overview

This is a normal Markdown conversion skill whose main risk is that it creates output files, including extracted code files, at paths chosen by the user or agent.

Install only if you are comfortable with a third-party Markdown conversion CLI creating files at paths the agent supplies. Use a dedicated output folder, avoid sensitive destinations, check for existing files before export, and treat extracted .py, .sh, .js, or similar code as untrusted until reviewed.

SkillSpector

By NVIDIA
Vulnerability Patterns
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
  • Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
  • Excessive AgencyUnrestricted Tool Access, Autonomous Decision Making, Scope Creep
Findings (1)

Missing User Warnings

Low
Confidence
95% confidence
Finding
The skill exposes many commands that write files to arbitrary user-specified output paths, including commands that can emit multiple numbered files or extract code blocks into a directory or ZIP, but it does not prominently warn users about this behavior in the skill description. In an agent setting, insufficient disclosure increases the chance of unintended overwrites, cluttering sensitive directories, or creating executable-looking files from untrusted Markdown content.

VirusTotal

59/59 vendors flagged this skill as clean.

View on VirusTotal

Static analysis

No suspicious patterns detected.