Back to skill

Security audit

Ntriq X402 Document Intel Batch

Security checks for vulnerabilities and agentic risk

Overview

This skill is a straightforward paid remote document-OCR service, but users should treat submitted document URLs as data shared with the provider.

Install only if you are comfortable sending document image URLs and resulting extracted content to the provider's service and paying $15 USDC via x402. Avoid submitting confidential, regulated, or third-party documents unless you have authorization and understand the provider's retention and privacy practices.

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 (1)

Missing User Warnings

Medium
Category
Not specified by scanner
Confidence
95% confidence
Finding

The skill instructs users to submit document image URLs to a remote endpoint and returns extracted document contents, but it does not warn that potentially sensitive business or personal document data will leave the local environment and be processed by a third-party service. This creates a real privacy and data-handling risk because users may unknowingly transmit confidential documents, and the '100% local inference on Mac Mini' claim could further reduce caution by implying stronger privacy than the remote-call architecture suggests.

Content

No source excerpt is available for this finding.