Back to skill

Security audit

Add Analytics

Security checks for vulnerabilities and agentic risk

Overview

This skill transparently helps add Google Analytics tracking code, with privacy and consent considerations users should still review before deployment.

Before installing, confirm you have authority to add Google Analytics to the site, use the consent option where legally or policy required, and avoid sending personal information, credentials, sensitive search terms, full error details, or unnecessary transaction details as analytics event parameters.

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
  • 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
  • Excessive AgencyUnrestricted Tool Access, Autonomous Decision Making, Scope Creep
Findings (4)

Instruction Override

High
Category
Prompt Injection
Confidence
70% confidence
Finding

This pattern attempts to override system instructions or ignore safety constraints. Without LLM analysis, manual review is recommended.

Content

Scanner excerpt · SKILL.md (reported line 17)May include surrounding context.

md
- **Measurement ID**: Format `G-XXXXXXXXXX` (required, ask if not provided)
- **--events**: Include custom event tracking helpers
- **--consent**: Include cookie consent integration
- **--debug**: Enable debug mode for development

## Step 1: Detect Project Type

Instruction Override

High
Category
Prompt Injection
Confidence
70% confidence
Finding

This pattern attempts to override system instructions or ignore safety constraints. Without LLM analysis, manual review is recommended.

Content

Scanner excerpt · SKILL.md (reported line 670)May include surrounding context.

Add debug configuration:

typescript
// For development, enable debug mode
if (process.env.NODE_ENV === 'development') {
  window.gtag('config', 'G-XXXXXXXXXX', {
    debug_mode: true,

Missing User Warnings

Medium
Category
Not specified by scanner
Confidence
96% confidence
Finding

The skill description says it will add Google Analytics but does not clearly warn up front that it injects third-party tracking scripts and sends visitor and event data to Google. That omission can cause users to deploy surveillance functionality without informed consent or adequate privacy review, especially in regulated environments.

Content

No source excerpt is available for this finding.

Missing User Warnings

Medium
Category
Not specified by scanner
Confidence
94% confidence
Finding

The event helpers encourage tracking clicks, searches, logins, purchases, form interactions, shares, and error details, which can capture sensitive behavioral or transactional information. Because the skill does not pair this guidance with strong user-facing privacy warnings, data-minimization advice, or restrictions on sensitive fields, it increases the risk of collecting personal or regulated data and transmitting it to Google.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.