ClawHub
Back to skill

Security audit

Paperless-ngx

Security checks across malware telemetry and agentic risk

Overview

This is a straightforward Paperless-ngx helper, but it can access and change sensitive documents if given a powerful API token.

Install this only for a Paperless-ngx instance you intend the agent to manage. Use a dedicated least-privilege API token where possible, verify PAPERLESS_URL, avoid unnecessary local downloads, and require explicit confirmation before any delete, bulk edit, reprocess, or broad metadata update.

SkillSpector

By NVIDIA
Vulnerability Patterns
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
  • Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
  • Excessive AgencyUnrestricted Tool Access, Autonomous Decision Making, Scope Creep
Findings (2)

Missing User Warnings

Medium
Confidence
88% confidence
Finding
The skill exposes destructive operations such as single-document deletion and bulk delete/reprocess without any guidance to confirm user intent, scope, or reversibility. In an agent setting, this increases the risk of accidental or overly broad data loss because the model may execute deletion based on ambiguous prompts or mistaken document selection.

Missing User Warnings

Medium
Confidence
82% confidence
Finding
The skill documents upload and download of potentially sensitive documents but provides no handling guidance for confidential content, destination validation, or safe storage of retrieved files. In practice this can lead to inadvertent exfiltration, local persistence of sensitive files, or transfer to an unintended Paperless instance if configuration is wrong.

VirusTotal

64/64 vendors flagged this skill as clean.

View on VirusTotal

Static analysis

No suspicious patterns detected.