paperless-ngx-tools

Security checks across malware telemetry and agentic risk

Overview

This skill is a straightforward Paperless-ngx integration, but it can access and modify your document archive when you run its commands.

Install this only if you are comfortable letting an agent use your Paperless-ngx token to read documents, upload files, and create metadata. Use a least-privilege Paperless account if possible, prefer HTTPS for remote instances, explicitly approve any advanced API update/delete/bulk operation, and pass a safe --output path when downloading files.

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)

Description-Behavior Mismatch

Medium
Confidence
96% confidence
Finding
The script supports creating new document types via the `--create` flag, which goes beyond the declared skill scope of only searching, uploading, tagging, and retrieving documents. This is dangerous because it expands the agent's effective write capabilities in the Paperless-ngx instance, enabling unauthorized taxonomy changes and violating least-privilege expectations users may rely on when granting access.

VirusTotal

64/64 vendors flagged this skill as clean.

View on VirusTotal