Security audit
Google Merchant Center
Security checks for vulnerabilities and agentic risk
Overview
This skill is a disclosed Google Merchant Center integration that can make high-impact account changes, but its artifacts consistently require user approval, scoped connections, and credential safeguards.
Install only if you intend to let an agent administer Google Merchant Center through Maton. Review every proposed write, webhook, trigger, hosted function, or raw API-key use carefully, confirm the exact account and resource IDs, and revoke unused connections or automations when the task is finished.
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
Static analysis
No suspicious patterns detected.