ClawHub
Back to skill

Security audit

paperless-ngx-tools

Security checks across malware telemetry and agentic risk

Overview

This is a normal Paperless-ngx helper that can read, upload, download, and create metadata in your document archive when you run its commands.

Install only if you are comfortable giving an agent a Paperless-ngx token that can read documents, upload files, download documents, and create metadata. Use the least-privilege Paperless account available, prefer HTTPS for remote instances, explicitly approve any update/delete/bulk API 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
91% confidence
Finding
The script's `resolveOrCreateId` logic does more than upload or apply existing metadata: it automatically creates new tags, correspondents, and document types when names do not already exist. That expands the skill's effective authority beyond a typical upload workflow and can be abused to modify server-side taxonomy/state, causing unauthorized metadata creation, clutter, or policy bypass if the token has broader permissions than the user expects.

VirusTotal

64/64 vendors flagged this skill as clean.

View on VirusTotal

Static analysis

No suspicious patterns detected.