ClawHub
Back to skill

Security audit

Shopify JSON-LD Parser

Security checks across malware telemetry and agentic risk

Overview

This is a small local parser for Shopify JSON-LD with no evidence of hidden access, persistence, credential use, or data exfiltration, though the bundled script has reliability bugs.

Reasonable to install for parsing non-sensitive Shopify or product-page HTML. Be aware the bundled script likely needs repair before it runs, and invoke it only with explicit files you intend the agent to read rather than piping untrusted stdin into it.

SkillSpector

By NVIDIA
Vulnerability Patterns
  • MCP Tool PoisoningHidden Instructions, Unicode Deception, Parameter Description Injection
  • 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)

Intent-Code Divergence

Medium
Confidence
98% confidence
Finding
The script's interface and docstring imply it can accept HTML content via stdin, but when no input path is provided it reads raw stdin bytes and passes them to Path(), treating the supplied HTML as a filesystem path. In practice this can cause incorrect file access attempts, crashes, or unintended reads if attacker-controlled stdin happens to form a valid path, making the tool unsafe and unreliable in pipeline usage.

VirusTotal

65/65 vendors flagged this skill as clean.

View on VirusTotal