Back to skill

Security audit

Ntriq Video Intelligence Mcp

Security checks for vulnerabilities and agentic risk

Overview

This skill is a straightforward remote video-analysis connector, but users should understand that video URLs are sent to an external paid service.

Install only if you are comfortable sending video URLs to the listed external service and paying the stated per-call fee. Do not submit confidential, regulated, surveillance, or personal footage unless you have approval and understand the provider's data handling terms.

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
96% confidence
Finding

The skill instructs users to submit a video_url to a third-party remote endpoint for analysis, but it does not warn that video content or referenced media may contain sensitive personal, proprietary, or surveillance data. This can lead to inadvertent disclosure of confidential footage, personal information, or regulated data because users are not informed about the privacy implications of sending video content off-platform.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.