Back to skill

Security audit

Paperless-ngx

Security checks for vulnerabilities and agentic risk

Overview

This is a straightforward Paperless-ngx API helper, but it exposes document deletion and bulk destructive operations without explicit preview or confirmation guidance.

Review this skill before installing if your Paperless-ngx instance contains sensitive or business-critical documents. Use the narrowest API token available, avoid unattended delete or bulk_edit requests, and require the agent to show exact document IDs and get explicit confirmation before deletion, reprocessing, or bulk metadata changes.

Vulnerability Patterns
  • Skill Instruction HijackingAlters the agent's session goals or safety constraints when the skill loads
  • Agent Memory PoisoningWrites attacker-controlled rules into memory that affect later sessions
  • Remote Payload Retrieval and ExecutionFetches external code whose behavior can change after review
  • Embedded Malicious CodeShips malicious scripts inside the skill and executes them locally
  • Unauthorized Access and Privilege EscalationObtains permissions beyond the task's legitimate needs
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 (3)

Missing User Warnings

High
Category
Not specified by scanner
Confidence
98% confidence
Finding

The bulk_edit example exposes mass-impact methods including delete and reprocess, but provides no safeguards, preview step, scope validation, or confirmation requirement. In a document-management skill, bulk destructive actions amplify the blast radius of mistakes or prompt injection, potentially affecting many documents at once.

Content

No source excerpt is available for this finding.

External Transmission

Medium
Category
Data Exfiltration
Confidence
60% confidence
Finding

Data is being sent to an external URL. This could be legitimate telemetry or data exfiltration. Manual review is recommended.

Content

Scanner excerpt · SKILL.md (reported line 28)May include surrounding context.

Search Documents

bash
curl -s "$PAPERLESS_URL/api/documents/?query=invoice" \
  -H "Authorization: Token $PAPERLESS_TOKEN"

Missing User Warnings

Medium
Category
Not specified by scanner
Confidence
94% confidence
Finding

The skill explicitly documents a DELETE operation for documents without requiring any confirmation, user-consent check, or warning about irreversible data loss. In an agent context, that omission is dangerous because the model may execute destructive actions from ambiguous or mistaken user requests, causing unintended deletion of records.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.