Security audit
OpenClaw Vertex Credit-Safe Setup
Security checks for vulnerabilities and agentic risk
Overview
This skill is a disclosed setup checklist for configuring Google Vertex AI in OpenClaw with cost-control guardrails.
Before installing, be aware that this workflow involves Google Cloud billing configuration and a service-account JSON credential. Use a dedicated low-privilege service account, store the JSON file carefully, confirm the target project and billing credits yourself in Google Cloud, and keep the first verification request minimal as the skill instructs.
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