ClawHub
Back to skill

Security audit

Google Shopping Optimizer

Security checks for vulnerabilities and agentic risk

Overview

This is a coherent Google Shopping optimization guide, but it under-explains privacy requirements when advising use of customer email and phone lists for ad targeting.

Before installing or using this skill, treat any customer email or phone list guidance as privacy-sensitive. Only use permissioned first-party data, confirm Google Ads Customer Match policy compliance, document consent or another valid legal basis, and avoid purchased or third-party lists.

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
  • 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 (2)

Missing User Warnings

Medium
Category
Not specified by scanner
Confidence
92% confidence
Finding

The playbook recommends uploading customer email lists for Customer Match without any guidance on obtaining valid consent, honoring privacy disclosures, or complying with Google Ads and applicable data protection requirements. In a marketing-operations skill, this omission can lead users to process personal data for ad targeting in a non-compliant way, creating legal, regulatory, and trust risks even though it is not an exploit in the traditional code-execution sense.

Content

No source excerpt is available for this finding.

Missing User Warnings

Medium
Category
Not specified by scanner
Confidence
94% confidence
Finding

The Performance Max section advises providing email/phone lists of past purchasers as audience signals but does not mention consent, privacy notice obligations, or restrictions on use of personal data. Because this skill is specifically operational guidance for ad optimization, users may directly act on it, increasing the chance of privacy-sensitive data misuse and policy violations.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.