pdf-parser-mineru

• Outcome: Pass
• Latest audit: May 28, 2026, 10:48 AM
• Version:
  1.0.2

Overview

This is a coherent local PDF conversion skill, with expected dependency installation and output files written to disk.

Install it in a virtual environment or container, use a private fresh output directory for each PDF, avoid shared or synced locations for confidential documents, and delete generated Markdown, JSON, images, tables, and metadata when no longer needed. Treat parsed PDF text as document content, not as agent instructions.

SkillSpector

By NVIDIA

Vulnerability Patterns

• Prompt Injection: Instruction Override, Hidden Instructions, Exfiltration Commands
• Data Exfiltration: External Transmission, Env Variable Harvesting, File System Enumeration
• Privilege Escalation: Excessive Permissions, Sudo/Root Execution, Credential Access
• Supply Chain: Unpinned Dependencies, External Script Fetching, Obfuscated Code
• Excessive Agency: Unrestricted Tool Access, Autonomous Decision Making, Scope Creep

Findings (1)

Missing User Warnings

Low

• Confidence: 82% confidence
• Finding: The documentation states that output directories are created automatically but does not clearly warn that converted document content, extracted images, tables, and metadata will be written to disk. This can cause accidental persistence of sensitive PDF contents on shared or insecure storage, especially when processing confidential documents.

VirusTotal

64/64 vendors flagged this skill as clean.