Security audit
OpenClaw Vertex Credit-Safe Setup
Security checks for vulnerabilities and agentic risk
Overview
This skill is an instruction-only helper for setting up Google Vertex AI in OpenClaw with disclosed billing and credential precautions.
Before installing, be prepared to review any OpenClaw config changes, use a dedicated least-privilege Google service account, keep the service-account JSON private, and manually verify the charged project and Vertex AI billing line after the test request.
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.