ClawHub
Back to skill

Security audit

Google Merchant Center Framework

Security checks for vulnerabilities and agentic risk

Overview

This is a Google Merchant Center advice framework with disclosed optional live-data integration and no executable install or persistence behavior.

Before connecting live Google Merchant Center access, make sure the account and data scope are intentional. Treat pricing, feed, campaign, and appeal recommendations as reviewable advice and approve any real account or feed changes yourself.

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
  • Excessive AgencyUnrestricted Tool Access, Autonomous Decision Making, Scope Creep
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
  • Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
Findings (2)

Context Leakage

High
Category
Data Exfiltration
Confidence
75% confidence
Finding

Code or instructions that leak agent conversation context to external services, potentially exposing sensitive user interactions.

Content

Scanner excerpt · SKILL.md (reported line 16)May include surrounding context.

md
## How This Skill Works

**Step 1:** Collect context from the user's message — merchant category, product count, known issues, goals (fix disapprovals, improve performance, launch Shopping ads, etc.).

**Step 2:** Ask one follow-up with all remaining questions using multiple-choice format. Key questions:
- a) Account size: (1) <500 SKUs, (2) 500-10K, (3) 10K-100K, (4) 100K+

Autonomous Decision Making

Medium
Category
Excessive Agency
Confidence
75% confidence
Finding

Skill enables autonomous high-impact decisions without human-in-the-loop verification. Critical operations (destructive commands, financial transactions, data deletion) should require explicit user confirmation.

Content

Scanner excerpt · SKILL.md (reported line 264)May include surrounding context.

md
| 6 | Landing Page Error | 404/500 errors, geo-blocking Googlebot | Fix URLs; unblock Googlebot | Next crawl |
| 7 | Insufficient Product Data | Title/description too short or generic | Title >30 chars with brand+type; description >500 chars | Immediate |
| 8 | Missing Shipping Weight | Carrier-calculated rates but no weight in feed | Add `shipping_weight` or switch to flat-rate | Immediate |
| 9 | Restricted Product | Regulated category without verification | Verify compliance; apply for merchant verification if required | Varies |
| 10 | Duplicate Item ID | Same ID reused for different products | Assign unique, stable IDs per variant | Immediate |

### Disapproval Triage Matrix