ClawHub
Back to skill

Security audit

Google Ads for Shopify via Agiexa

Security checks for vulnerabilities and agentic risk

Overview

This prerelease guide describes planned Google Ads features and offers an optional waitlist signup requiring explicit consent.

Install for information about planned features; it cannot currently analyze or modify ads. Optional signup sends your email, role, and any supplied link or message to Agiexa after permission. Review account permissions separately before enabling future integrations.

A.I.G

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

SkillSpector

Vulnerability Patterns
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • MCP Tool PoisoningHidden Instructions, Unicode Deception, Parameter Description Injection
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
  • Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
Findings (3)

Description-Behavior Mismatch

High
Category
MCP Tool Poisoning
Confidence
99% confidence
Finding

The supplied code is a waitlist submission, not an implementation of the advertised Google Ads tools. Although it contacts the named provider and references Google Ads, its primary behavior is sending signup information and a consent assertion to a waitlist endpoint. This is materially different from retrieving or analyzing advertising performance.

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 9)May include surrounding context.

md
openclaw:
    requires:
      bins:
        - curl
    homepage: https://agiexa.com/integrations/google-ads
---

The manifest advertises Google Ads analytics tools, but the skill redirects task requests to a prerelease waitlist and submits contact details instead.

Medium
Category
Excessive Agency
Confidence
98% confidence
Finding

The manifest describes an agent receiving 31 Google Ads tools to inspect campaign performance and keywords. However, the task-handling instructions explicitly say these capabilities are not yet available, and the supplied executable workflow instead posts the user's email, role, and optional details to a marketing waitlist. Explicit consent limits the privacy risk, but does not resolve the mismatch between the advertised analytics functionality and the implemented prerelease signup workflow.

Content

No source excerpt is available for this finding.