Back to skill

Security audit

NoteGPT Page Seo Checker Skill

Security checks for vulnerabilities and agentic risk

Overview

The scanners rate this SEO checker suspicious because its keyword validation can send page-derived keywords to an external service without a privacy warning; the review is incomplete because one referenced path was unresolved.

Before installing, consider whether pages you may audit contain confidential or unreleased keywords and whether you are comfortable with those terms being sent to an external service. The scan inspected all listed components but was marked partial because a local path-like reference could not be resolved, so the evidence is incomplete.

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
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Output HandlingUnvalidated Output Injection, Cross-Context Output, Unbounded Output
  • 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 (2)

Hidden Instructions

High
Category
Prompt Injection
Confidence
70% confidence
Finding

Hidden instructions were detected in comments or invisible text. These could contain malicious directives. Manual review is recommended.

Content

Scanner excerpt · SKILL.md (reported line 274)May include surrounding context.

md
<section class="summary">
    <h2>Summary & Action Items</h2>
    <ul>
      <!-- List all ✗ items with fix instructions -->
    </ul>
    <h2>Recommendation</h2>
    <p>[Green: Ready to publish / Yellow: Fix [N] items / Red: Do not publish]</p>

Keyword validation sends page-derived keywords to an external service without a privacy warning.

Medium
Category
Output Handling
Confidence
93% confidence
Finding

The skill permits sending a page's primary keyword to an external MCP service whenever connected, without first checking whether that information is confidential or obtaining approval for the disclosure. Because the skill explicitly supports staging and test pages, keywords could reveal unreleased products or marketing plans; the risk is lower for already-public production content, and there is no evidence of deliberate exfiltration.

Content

No source excerpt is available for this finding.