ClawHub
Back to skill

Security audit

OpenClaw Vertex Setup

Security checks across malware telemetry and agentic risk

Overview

This is a coherent setup guide for connecting OpenClaw to Google Vertex AI, with sensitive credential and service-configuration steps that are disclosed and aligned with that purpose.

Before installing, understand that this skill may guide an agent to edit your OpenClaw config, shared env file, auth profile store, and Gateway service. Back up ~/.openclaw, prefer gcloud ADC over real API keys, do not replace the placeholder <authenticated> with a secret unless you understand plaintext storage risk, and verify Gateway is installed from the openclaw binary you intend to use.

SkillSpector

By NVIDIA
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 (1)

Missing User Warnings

Medium
Confidence
84% confidence
Finding
The skill directs users to set persistent credential-related environment variables and to edit an auth profile file with credential-like material, but it provides no guidance on protecting those values, avoiding accidental disclosure, or using least-privilege storage. This increases the chance that secrets or credential pointers become exposed through shell history, world-readable files, logs, or copied config files.

VirusTotal

65/65 vendors flagged this skill as clean.

View on VirusTotal

Static analysis

No suspicious patterns detected.