Back to skill

Security audit

Pdf Invoice Parser

Security checks across malware telemetry and agentic risk

Overview

This is a local PDF invoice extraction tool that reads user-selected PDFs and writes local CSV or JSON outputs, with no hidden network, credential, persistence, or destructive behavior found.

Install and run this in an isolated Python environment where possible. Only process invoices you are authorized to handle, store exported CSV/JSON files securely, and review extracted results because OCR and regex parsing can misread invoice fields.

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 (2)

Lp3

Medium
Category
MCP Least Privilege
Confidence
86% confidence
Finding
The skill clearly instructs users to read local PDF files and write extracted data to CSV/Excel outputs, but the metadata does not declare corresponding permissions. This creates a transparency and governance gap: operators may authorize or run the skill without understanding that it accesses filesystem data and produces new files containing potentially sensitive invoice information.

Missing User Warnings

Medium
Confidence
90% confidence
Finding
The skill is designed to process invoices and financial documents, which commonly contain sensitive business and personal data, yet the documentation provides no warning about handling, storage, redaction, or secure export of that data. In practice this can lead users to bulk-process confidential PDFs and generate CSV/Excel artifacts that are easier to leak, mis-share, or retain insecurely.

VirusTotal

67/67 vendors flagged this skill as clean.

View on VirusTotal

Static analysis

No suspicious patterns detected.