PDF Read/Write Toolkit

• Outcome: Pass
• Latest audit: May 29, 2026 at 8:39 PM UTC
• Version:
  1.0.0

Overview

This is a straightforward local PDF toolkit whose file access is user-directed and consistent with its stated purpose.

Install only if you are comfortable running local Python PDF-processing libraries on documents you choose. Avoid processing highly sensitive or untrusted PDFs/HTML in a privileged workspace, and remember that metadata extraction can print document metadata such as title and author.

SkillSpector

By NVIDIA

Vulnerability Patterns

• MCP Least Privilege: Underdeclared Capability, Wildcard Permission, Missing Permission Declaration
• 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

Findings (1)

Lp3

Medium

• Category: MCP Least Privilege
• Confidence: 93% confidence
• Finding: The skill clearly performs filesystem reads on user-supplied PDF, HTML, Markdown, CSS, and output paths, but it does not declare any permissions. This creates a mismatch between documented capabilities and the security model, which can lead to unauthorized or overly broad file access if the runtime relies on declared permissions for enforcement or review.

VirusTotal

67/67 vendors flagged this skill as clean.