ClawHub
Back to skill

Security audit

markdown-export

Security checks across malware telemetry and agentic risk

Overview

This appears to be a straightforward local Markdown export skill whose file access and Pandoc execution match its stated document-conversion purpose.

Install only if you are comfortable with a skill that runs a local converter and can read/write the document paths you provide. Use trusted Markdown, templates, CSS, resource paths, and Pandoc installations, since custom document assets can affect what Pandoc reads or embeds during conversion.

SkillSpector

By NVIDIA
Vulnerability Patterns
  • MCP Least PrivilegeUnderdeclared Capability, Wildcard Permission, Missing Permission Declaration
  • 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
Findings (1)

Lp3

Medium
Category
MCP Least Privilege
Confidence
95% confidence
Finding
The skill instructs use of a Python script that reads Markdown and template files, writes output files, and invokes Pandoc via the shell, but it declares no permissions for file_read, file_write, or shell execution. This creates a trust and policy gap: an agent may perform sensitive filesystem access or command execution without explicit review, and user-controlled paths/templates increase the risk if the implementation is later unsafe.

VirusTotal

65/65 vendors flagged this skill as clean.

View on VirusTotal

Static analysis

No suspicious patterns detected.